Publications Catalog (132)

This study examines how Turkish learners of English and native English speakers comprehend and produce subject–verb number agreement. It finds differences in how the groups use syntactic and linear distance cues, and evidence that agreement is processed through different mechanisms in comprehension and production.

Accurate disease prognosis is essential for patient care but is often hindered by the scarcity of longitudinal data. This study explores deep learning training strategies that utilize large, accessible diagnostic datasets to pretrain models aimed at predicting future disease progression in knee osteoarthritis (OA), Alzheimer's disease (AD), and breast cancer (BC). While diagnostic pretraining improves prognostic task performance, naive fine-tuning for prognosis can cause 'catastrophic forgetting,' where the model's original diagnostic accuracy degrades, a significant patient safety concern in real-world settings. To address this, we propose a sequential learning strategy with experience replay. We used cohorts with knee radiographs, brain MRIs, and digital mammograms to predict 4-year structural worsening in OA, 2-year cognitive decline in AD, and 5-year cancer diagnosis in BC. Our results showed that diagnostic pretraining on larger datasets improved prognosis model performance compared to standard baselines, boosting both the Area Under the Receiver Operating Characteristic curve (AUROC) (e.g., Knee OA external: 0.770 vs 0.747; Breast Cancer: 0.874 vs 0.848) and the Area Under the Precision-Recall Curve (AUPRC) (e.g., Alzheimer's Disease: 0.752 vs 0.683). Additionally, a sequential learning approach with experience replay achieved prognostic performance comparable to dedicated single-task models (e.g., Breast Cancer AUROC 0.876 vs 0.874) while also preserving diagnostic ability. This method maintained high diagnostic accuracy (e.g., Breast Cancer Balanced Accuracy 50.4% vs 50.9% for a dedicated diagnostic model), unlike simpler multitask methods prone to catastrophic forgetting (e.g., 37.7%). Our findings show that leveraging large diagnostic datasets is a reliable and data-efficient way to enhance prognostic models while maintaining essential diagnostic skills.

INTRODUCTION MRI enables assessment of morphological and compositional changes in knee cartilage and meniscus relevant to osteoarthritis (OA) progression. Accurate quantification depends on reliable segmentation, which remains challenging due to the thin, curved geometry of cartilage and complex shape of the meniscus. Manual delineation is time-consuming and impractical for large-scale studies. Deep learning models, including nnU-Net and transformer-based foundation models such as MedSAM2, have shown promise for automated segmentation; however, the effectiveness of fine-tuning MedSAM2 for multi-structure knee segmentation and its performance relative to nnU-Net on established benchmarks such as the IWOAI Challenge has not been reported. OBJECTIVE 1) To evaluate and compare the performance of domain-specific fine-tuned MedSAM2 and nnU-Net for automated multi-structure knee MRI segmentation using all OAI baseline cohort. 2) To compare the segmentation performance of both models on the IWOAI Knee Segmentation Challenge dataset. METHODS Sagittal DESS knee MR images from the OAI baseline dataset (n = 9,592 MRI of left and right knees) and corresponding segmentation masks were used. Data was split at the subject level using stratified sampling across KL grades into 70/10/20 training, validation, and test sets. MedSAM2 was fine-tuned for 75 epochs, resampling sagittal slices to 512 x 512 resolution, using a combined Focal and Dice loss (20:1 weighting). Prompts were derived from the 25th, 50th, and 75th percentile slices of each 3D volume, with ground truth masks from these slices passed as initial prompts to propagate segmentation to the rest of the slices. For the IWOAI Challenge evaluation, the same data splits of the challenge (n = 120 training, 28 validation, 28 test) were used for fine-tuning both MedSAM2 and 3D nnU-Net. Performance was assessed using Dice score and IoU. RESULTS Using the entire OAI baseline dataset (Objective 1), KneeSAM2 achieved a mean Dice of 0.92 and IoU of 0.88, surpassing pretrained MedSAM2 by 0.20 in Dice and 0.23 in IoU. Improvements were most pronounced for smaller structures: patellar cartilage (Dice 0.90 vs. 0.41), meniscus (0.90 vs. 0.48), and tibial cartilage (0.89 vs. 0.64). Using the IWOAI Challenge dataset (Objective 2), MedSAM2-FT outperformed the published IWOAI benchmark for patellar cartilage (Dice 0.88 vs. 0.86) and matched it for femoral cartilage (0.90 vs. 0.90) but showed lower performance for tibial cartilage (0.75 vs. 0.89) and meniscus (0.85 vs. 0.88). The nnU-Net model, trained on the same IWOAI data splits, achieved the highest performance overall (Dice: femoral cartilage 0.95, tibial cartilage 0.95, patellar cartilage 0.93, meniscus 0.94), surpassing all other models. CONCLUSION Domain-specific fine-tuning improved MedSAM2 performance for segmenting small and anatomically complex knee structures, supporting the need for targeted adaptation of transformer-based foundation models (Objective 1). However, on the IWOAI Challenge benchmark (Objective 2), fine-tuned MedSAM2 showed competitive but variable performance across structures, whereas nnU-Net consistently achieved higher accuracy. These findings suggest that, under the current experimental settings and datasets, nnU-Net may offer stronger performance for multi-structure knee OA segmentation. Further improvements in prompting strategies, model adaptation, and training efficiency are needed to better leverage foundation models for specialized medical imaging tasks.

INTRODUCTION Knee osteoarthritis (KOA) is a prevalent joint disorder causing significant physical disability worldwide. Estimating time-to-pain progression could help identify high-risk patients and guide treatment decisions. While prior studies have explored binary progression prediction, predicting the specific year of pain onset within a multi-year timeframe remains underexplored. Pain is inherently subjective and multifactorial, and it is unclear whether baseline clinical assessments or structural imaging features carry sufficient signal to predict when pain progression will occur. OBJECTIVE To investigate whether baseline clinical variables or MRI-derived radiomics features can predict the year of knee pain progression (Years 1-8) in KOA patients. METHODS We utilized data from the Osteoarthritis Initiative (OAI) database. Subjects with a baseline WOMAC pain score increase of >=9 (scaled 0-100) sustained for at least two years were classified as having knee pain progression. Only progression cases were included. From 1,224 baseline clinical variables in OAI, Lasso regularization optimized via Optuna selected 18 features. A self-supervised pretrained TabNet classifier was trained for 8-class time-to-progression prediction (Years 1-8) using masked feature reconstruction followed by supervised fine-tuning with cross-entropy loss. For comparison, 3D radiomics features extracted from bones and soft tissue segmentation masks of baseline DESS MRI were combined with Lasso feature selection and XGBoost classification (Figure 1). Data was split into training/validation/test sets (n=2,064/306/589). Performance was evaluated using accuracy within +-1 year and mean absolute error (MAE) in years. RESULTS The TabNet model using clinical variables achieved 57.8% accuracy within +-1 year and MAE of 1.72 years. Feature importance analysis identified KOOS Quality of Life, SF-12 Physical Summary Scale, WOMAC Pain Scores (for affected and contralateral knee), CES-D Depression Score, and knee pain severity as the most attended features. However, the model predominantly predicted early progression years (Year 1 recall=0.83) while failing to identify later progression time points (Years 5-8 recall~0), indicating that it largely defaulted to predicting the majority class rather than learning meaningful temporal patterns. The radiomics-based approach (Lasso + XGBoost on DESS features) performed worse, achieving 48.2% accuracy within +-1 year. Feature selection yielded 20 radiomic features spanning six anatomical regions (femur, femur cartilage, tibia, tibia cartilage, patella cartilage, and meniscus), including first-order, texture, and shape features extracted using wavelet, logarithm, exponential, LBP-3D, and gradient filters. Neither approach demonstrated sufficient discriminative ability for fine-grained temporal prediction of pain progression. CONCLUSION Neither baseline clinical variables nor MRI-derived radiomics features could meaningfully predict the year of knee pain progression. These findings highlight the inherent difficulty of temporal pain prediction: pain is a subjective experience influenced by psychological, social, and neurological factors beyond what baseline clinical scores or structural joint features can capture. The severe class imbalance across progression years further compounds this challenge. These results suggest that predicting time-to-pain progression in KOA may require richer data, deep learning-based imaging features, or multimodal integration, and underscore that this remains a fundamentally difficult prediction task.

An automated pipeline converts routine Dixon MRI into useful strength indicators, providing quadriceps muscle segmentations across three MR vendors. Beyond cross-sectional area (CSA), radiomics captures compositional cues that improve muscle strength and torque estimation, particularly in heterogeneous multi-vendor cohorts.

This study assesses whether self-supervised learning (SSL) improves knee osteoarthritis (OA) modeling for diagnosis and prognosis relative to ImageNet-pretrained initialization. We compared (i) image-only SSL pretrained on knee radiographs from the OAI, MOST, and NYU cohorts, and (ii) multimodal image-text SSL pretrained on hospital knee radiographs paired with radiologist impressions. For diagnostic Kellgren-Lawrence (KL) grade prediction, SSL yielded mixed results. While image-only SSL improved accuracy during linear probing (frozen encoder), it did not outperform ImageNet pretraining during full fine-tuning. Similarly, multimodal SSL failed to improve grading performance. A likely explanation is mismatch between the hospital pretraining corpus and the downstream diagnostic task: the hospital image-text dataset was restricted to knees from patients with clinically identified OA in routine care, rather than a cohort spanning the full spectrum from normal to severe disease needed for balanced KL grading. In addition, radiology impressions do not explicitly encode KL grade, limiting supervision for learning KL-specific decision boundaries. In contrast, this same multimodal initialization significantly improved prognostic modeling. It outperformed ImageNet baselines in predicting 4-year structural incidence and progression, including on external validation (MOST AUROC: 0.701 vs. 0.599 at 10\% labeled data). Overall, these results suggest that our hospital image-text data may be less effective for diagnostic grading when the pretraining cohort is limited to OA knees, but can provide a strong signal for prognostic modeling when the downstream task is better aligned with the pretraining data distribution.

While large-scale pretraining has revolutionized language modeling, its potential remains underexplored in healthcare with structured electronic health records (EHRs). We present RAVEN, a novel generative pretraining strategy for sequential EHR data based on Recurrence-Aware next-Visit EveNt prediction. Leveraging a dataset of over one million unique individuals, our model learns to autoregressively generate tokenized clinical events for the next visit conditioned on patient history. We introduce regularization on predicting repeated events and highlight a key pitfall in EHR-based foundation model evaluations: repeated event tokens can inflate performance metrics when new onsets are not distinguished from subsequent occurrences. Furthermore, we empirically investigate the scaling behaviors in a data-constrained, compute-saturated regime, showing that simply increasing model size is suboptimal without commensurate increases in data volume. We evaluate our model via zero-shot prediction for forecasting the incidence of a diverse set of diseases, where it rivals fully fine-tuned representation-based Transformer models and outperforms both standard simulation-based next-token approaches and a prompted medical large language model baseline. Finally, without additional parameter updates, we show that RAVEN can generalize to an external patient cohort under lossy clinical code mappings and feature coverage gaps.

Purpose To develop a transformer-based deep learning model-MR-Transformer-that leverages ImageNet pretraining and three-dimensional spatial correlations to predict the progression of knee osteoarthritis to total knee replacement using MRI. Materials and Methods This retrospective study included 353 case-control matched pairs of coronal intermediate-weighted turbo spin-echo (COR-IW-TSE) and sagittal intermediate-weighted turbo spin-echo with fat suppression (SAG-IW-TSE-FS) knee MRI scans from the Osteoarthritis Initiative database, with a follow-up period up to 9 years, and 270 case-control matched pairs of coronal short-tau inversion recovery (COR-STIR) and sagittal proton-density fat-saturated (SAG-PD-FAT-SAT) knee MRI scans from the Multicenter Osteoarthritis Study database, with a follow-up period up to 7 years. Performance of the MR-Transformer to predict the progression of knee osteoarthritis was compared with that of existing state-of-the-art deep learning models (TSE-Net, 3DMeT, and MRNet) using sevenfold nested cross-validation across the four MRI tissue sequences. Results Among the 353 Osteoarthritis Initiative case-control pairs, 215 were women (mean age, 63 years ± 8 [SD]); among the 270 Multicenter Osteoarthritis Study case-control pairs, 203 were women (mean age, 65 years ± 7). The MR-Transformer achieved areas under the receiver operating characteristic curve (AUCs) of 0.88 (95% CI: 0.85, 0.91), 0.88 (95% CI: 0.85, 0.90), 0.86 (95% CI: 0.82, 0.89), and 0.84 (95% CI: 0.81, 0.87) for COR-IW-TSE, SAG-IW-TSE-FS, COR-STIR, and SAG-PD-FAT-SAT, respectively. The model achieved a higher AUC than that of 3DMeT for all MRI sequences (

BACKGROUND: The methods for predicting time-to-total knee replacement (TKR) do not provide enough information to make robust and accurate predictions. PURPOSE: Develop and evaluate an artificial intelligence-based model for predicting time-to-TKR by analyzing longitudinal knee data and identifying key features associated with accelerated knee osteoarthritis progression. METHODS: A total of 547 subjects underwent TKR in the Osteoarthritis Initiative over nine years, and their longitudinal data was used for model training and testing. 518 and 164 subjects from Multi-Center Osteoarthritis Study and internal hospital data were used for external testing, respectively. The clinical variables, magnetic resonance (MR) images, radiographs, and quantitative and semi-quantitative assessments from images were analyzed. Deep learning (DL) models were used to extract features from radiographs and MR images. DL features were combined with clinical and image assessment features for survival analysis. A Lasso Cox feature selection method combined with a random survival forest model was used to estimate time-to-TKR. RESULTS: Utilizing only clinical variables for time-to-TKR predictions provided the estimation accuracy of 60.4% and C-index of 62.9%. Combining DL features extracted from radiographs, MR images with clinical, quantitative, and semi-quantitative image assessment features achieved the highest accuracy of 73.2%, (p=.001) and C-index of 77.3% for predicting time-to-TKR. CONCLUSIONS: The proposed predictive model demonstrated the potential of DL models and multimodal data fusion in accurately predicting time-to-TKR surgery that may help assist physicians to personalize treatment strategies and improve patient outcomes.

We developed deep learning models for predicting Total Knee Replacement (TKR) need within various time horizons in knee osteoarthritis patients, with a novel capability: the models can perform TKR prediction using a single scan, and furthermore when a previous scan is available, they leverage a progressive risk formulation to improve their predictions. Unlike conventional approaches that treat each scan of a patient independently, our method incorporates a constraint based on disease's progressive nature, ensuring that predicted TKR risk either increases or remains stable over time when multiple scans of a knee are available. This was achieved by enforcing a progressive risk formulation constraint during training with patients who have more than one available scan in the studies. Knee radiographs and MRIs from the Osteoarthritis Initiative (OAI) and Multicenter Osteoarthritis Study (MOST) were used in this work and deep learning models were trained to predict TKR within 1, 2, and 4-year time periods. The proposed approach, utilizing a dual-model risk constraint architecture, demonstrated superior performance compared to baseline - conventional models trained with standard binary cross entropy loss. It achieved an AUROC of 0.87 and AUPRC of 0.47 for 1-year TKR prediction on the OAI radiograph test set, considerably improving over the baseline AUROC of 0.79 and AUPRC of 0.34. For the MOST radiograph test set, the proposed approach achieved an AUROC of 0.77 and AUPRC of 0.25 for 1-year predictions, outperforming the baseline AUROC of 0.71 and AUPRC of 0.19. Similar trends were observed in the MRI testsets.

Accurate prediction of the year of total knee replacement (TKR) is challenging due to the complex interplay of factors influencing the surgical decision. Current deep learning models often rely on single-modality data, limiting their predictive power. Multimodal approaches integrating imaging and patient data offer the potential to improve predictions and support clinical decisions. This study presents an end-to-end trained, transformer-based multimodal model that integrates MR imaging with tabular data, including clinical variables and image readings, to predict the year of TKR for each subject. Our model leverages cross-modal attention to fuse features from an image encoder with a self-supervised pretrained tabular encoder, achieving the highest accuracy of 63.4% among tested models. We evaluated its performance against three unimodal models and four multimodal fusion strategies, including simple concatenation, DAFT, and multimodal interaction. The results demonstrate that our model's cross-modal interaction approach with pretrained TabNet not only outperformed all unimodal models but also showed improvements over other multimodal fusion techniques, highlighting the effectiveness of cross-modal attention fusion for integrating complex data modalities in TKR year prediction tasks.

Motivation: Accurate time-to-total knee replacement (TKR) predictions are essential for effective patient management and resource planning. Goal(s): Develop an AI-based survival analysis model to estimate time-to-TKR using multimodal data, identifying key features associated with KOA progression. Approach: This study used data from the OAI and external datasets, integrating clinical variables, MR images, radiographs, and image assessments in an AI survival analysis framework. Results: The model achieved an accuracy of 73.2% and a C-index of 77.3%, highlighting the effectiveness of multimodal fusion in TKR prediction.

Motivation: Predicting time-to-total knee replacement (TKR) is essential for tailoring treatment strategies. Goal(s): Evaluate and compare the effectiveness of supervised and self-supervised deep learning (DL)-extracted features, alongside radiomics features, in predicting time-to-TKR within a 9-year timeframe. Approach: Radiomics features, and features from DL models trained in supervised and self-supervised modes were extracted from images. A Lasso feature selection was applied, and XGBoost was used for prediction. Results: Features extracted from supervised DL model achieved the highest accuracy of 71.6%, outperforming features from radiomics and self-supervised learning.

Investigates systematic inter-reader and cross-cohort Kellgren-Lawrence (KL) grading inconsistencies across large-scale knee osteoarthritis radiographic datasets (OAI and MOST) and evaluates their impact on training and benchmarking deep learning diagnostic models.

Large-scale pretraining has transformed modeling of language and other data types, but its potential remains underexplored in healthcare with structured electronic health records (EHRs). We present a novel generative pretraining strategy for sequential EHR data using next-visit event prediction. Our model learns to autoregressively generate various tokenized clinical events for the next visit based on patient history and inherently handles the joint prediction of heterogeneous data types. Additionally, we introduce regularization on predicting repeated events and highlight a key pitfall in EHR-based foundation model evaluations: repeated event tokens can inflate performance metrics when new onsets are not distinguished from subsequent occurrences. Our model is evaluated via zero-shot prediction for forecasting dementia and knee osteoarthritis incidence within 2 and 5 years, and the model performance rivals a fully fine-tuned masked pretrained Transformer baseline, demonstrating that our approach captures complex clinical dependencies without requiring costly task-specific fine-tuning.

Accurately predicting the expected duration of time until total knee replacement (time-to-TKR) is crucial for patient management and healthcare planning. Predicting when surgery may be needed, especially within shorter windows like three years, allows clinicians to plan timely interventions and healthcare systems to allocate resources more effectively. Existing models lack the precision for such time-based predictions. A survival analysis model for predicting time-to-TKR was developed using features from medical images and clinical measurements.From the Osteoarthritis Initiative (OAI) dataset, all knees with clinical variables, MRI scans, radiographs, and quantitative and semi-quantitative assessments from images were identified. This resulted in 895 knees that underwent TKR within the 9-year follow-up period, as specified by the OAI study design, and 786 control knees that did not undergo TKR (right-censored, indicating their status beyond the 9-year follow-up is unknown). These knees were utilized for model training and testing. Additionally, 518 and 164 subjects from Multi-Center Osteoarthritis Study (MOST) and internal hospital data were used for external testing, respectively. Deep learning (DL) models were utilized to extract features from radiographs and MR scans. Extracted features, clinical variables, and image assessments were used in survival analysis with Lasso Cox feature selection and a random survival forest model to predict time-to-TKR.The proposed model exhibited strong discrimination power by integrating self-supervised DL features with clinical variables (e.g., age, BMI, and pain score) and image assessment measurements (e.g., Kellgren-Lawrence [KL] grade, joint space narrowing, bone marrow lesion size, and cartilage morphology) from multiple modalities. The model achieved an AUC of 94.5 (95% CI: 94.0, 95.1) for predicting the time-to-TKR.The proposed model demonstrated the potential of self-supervised learning and multi-modal data fusion in accurately predicting time-to-TKR that may assist physicians to develop personalize treatment strategies.

Different pathologies of the hip are characterized by the abnormal shape of the bony structures of the joint, namely the femur and the acetabulum. Three-dimensional (3D) models of the hip can be used for diagnosis, biomechanical simulation, and planning of surgical treatments. These models can be generated by building 3D surfaces of the joint's structures segmented on magnetic resonance (MR) images. Deep learning can avoid time-consuming manual segmentations, but its performance depends on the amount and quality of the available training data. Data augmentation and transfer learning are two approaches used when there is only a limited number of datasets. In particular, data augmentation can be used to artificially increase the size and diversity of the training datasets, whereas transfer learning can be used to build the desired model on top of a model previously trained with similar data. This study investigates the effect of data augmentation and transfer learning on the performance of deep learning for the automatic segmentation of the femur and acetabulum on 3D MR images of patients diagnosed with femoroacetabular impingement. Transfer learning was applied starting from a model trained for the segmentation of the bony structures of the shoulder joint, which bears some resemblance to the hip joint. Our results suggest that data augmentation is more effective than transfer learning, yielding a Dice similarity coefficient compared to ground-truth manual segmentations of 0.84 and 0.89 for the acetabulum and femur, respectively, whereas the Dice coefficient was 0.78 and 0.88 for the model based on transfer learning. The Accuracy for the two anatomical regions was 0.95 and 0.97 when using data augmentation, and 0.87 and 0.96 when using transfer learning. Data augmentation can improve the performance of deep learning models by increasing the diversity of the training dataset and making the models more robust to noise and variations in image quality. The proposed segmentation model could be combined with radiomic analysis for the automatic evaluation of hip pathologies.

Chest X-ray imaging is a widely accessible and non-invasive diagnostic tool for detecting thoracic abnormalities. While numerous AI models assist radiologists in interpreting these images, most overlook patients' historical data. To bridge this gap, we introduce Temporal MIMIC dataset, which integrates five years of patient history, including radiographic scans and reports from MIMIC-CXR and MIMIC-IV, encompassing 12,221 patients and thirteen pathologies. Building on this, we present HIST-AID, a framework that enhances automatic diagnostic accuracy using historical reports. HIST-AID emulates the radiologist's comprehensive approach, leveraging historical data to improve diagnostic accuracy. Our experiments demonstrate significant improvements, with AUROC increasing by 6.56% and AUPRC by 9.51% compared to models that rely solely on radiographic scans. These gains were consistently observed across diverse demographic groups, including variations in gender, age, and racial categories. We show that while recent data boost performance, older data may reduce accuracy due to changes in patient conditions. Our work paves the potential of incorporating historical data for more reliable automatic diagnosis, providing critical support for clinical decision-making.

Although human’s ability to visually understand the structure of the World plays a crucial role in perceiving the World and making appropriate decisions, human perception does not solely rely on vision but amalgamates the information from acoustic, verbal, and visual stimuli. An active area of research has been revolving around designing an efficient framework that adapts to multiple modalities and ideally improves the performance of existing tasks. While numerous frameworks have proved effective on natural datasets like ImageNet, a limited number of studies have been carried out in the biomedical domain. In this work, we extend the available frameworks for natural data to biomedical data by leveraging the abundant, unstructured multi-modal data available as radiology images and reports. We attempt to answer the question, ”For multi-modal learning, self-supervised learning and joint learning using both learning strategies, which one improves the visual representation for downstream chest radiographs classification tasks the most?”. Our experiments indicated that in limited labeled data settings with 1% and 10% labeled data, the joint learning with multi-modal and self-supervised models outperforms self-supervised learning and is at par with multi-modal learning. Additionally, we found that multi-modal learning is generally more robust on out-of-distribution datasets.

Current methods for assessing knee osteoarthritis (OA) do not provide comprehensive information to make robust and accurate outcome predictions. Deep learning (DL) risk assessment models were developed to predict the progression of knee OA to total knee replacement (TKR) over a 108-month follow-up period using baseline knee MRI. Participants of our retrospective study consisted of 353 case-control pairs of subjects from the Osteoarthritis Initiative with and without TKR over a 108-month follow-up period matched according to age, sex, ethnicity, and body mass index. A traditional risk assessment model was created to predict TKR using baseline clinical risk factors. DL models were created to predict TKR using baseline knee radiographs and MRI. All DL models had significantly higher (p < 0.001) AUCs than the traditional model. The MRI and radiograph ensemble model and MRI ensemble model (where TKR risk predicted by several contrast-specific DL models were averaged to get the ensemble TKR risk prediction) had the highest AUCs of 0.90 (80% sensitivity and 85% specificity) and 0.89 (79% sensitivity and 86% specificity), respectively, which were significantly higher (p < 0.05) than the AUCs of the radiograph and multiple MRI models (where the DL models were trained to predict TKR risk using single contrast or 2 contrasts together as input). DL models using baseline MRI had a higher diagnostic performance for predicting TKR than a traditional model using baseline clinical risk factors and a DL model using baseline knee radiographs.

Summary Objectives The KNee OsteoArthritis Prediction (KNOAP2020) challenge was organized to objectively compare methods for the prediction of incident symptomatic radiographic knee osteoarthritis within 78 months on a test set with blinded ground truth. Design The challenge participants were free to use any available data sources to train their models. A test set of 423 knees from the Prevention of Knee Osteoarthritis in Overweight Females (PROOF) study consisting of magnetic resonance imaging (MRI) and X-ray image data along with clinical risk factors at baseline was made available to all challenge participants. The ground truth outcomes, i.e., which knees developed incident symptomatic radiographic knee osteoarthritis (according to the combined ACR criteria) within 78 months, were not provided to the participants. To assess the performance of the submitted models, we used the area under the receiver operating characteristic curve (ROCAUC) and balanced accuracy (BACC). Results Seven teams submitted 23 entries in total. A majority of the algorithms were trained on data from the Osteoarthritis Initiative. The model with the highest ROCAUC (0.64 (95% confidence interval (CI): 0.57–0.70)) used deep learning to extract information from X-ray images combined with clinical variables. The model with the highest BACC (0.59 (95% CI: 0.52–0.65)) ensembled three different models that used automatically extracted X-ray and MRI features along with clinical variables. Conclusion The KNOAP2020 challenge established a benchmark for predicting incident symptomatic radiographic knee osteoarthritis. Accurate prediction of incident symptomatic radiographic knee osteoarthritis is a complex and still unsolved problem requiring additional investigation.

Objective To evaluate whether the deep learning (DL) segmentation methods from the six teams that participated in the IWOAI 2019 Knee Cartilage Segmentation Challenge are appropriate for quantifying cartilage loss in longitudinal clinical trials. Design We included 556 subjects from the Osteoarthritis Initiative study with manually read cartilage volume scores for the baseline and 1-year visits. The teams used their methods originally trained for the IWOAI 2019 challenge to segment the 1130 knee MRIs. These scans were anonymized and the teams were blinded to any subject or visit identifiers. Two teams also submitted updated methods. The resulting 9,040 segmentations are available online. The segmentations included tibial, femoral, and patellar compartments. In post-processing, we extracted medial and lateral tibial compartments and geometrically defined central medial and lateral femoral sub-compartments. The primary study outcome was the sensitivity to measure cartilage loss as defined by the standardized response mean (SRM). Results For the tibial compartments, several of the DL segmentation methods had SRMs similar to the gold standard manual method. The highest DL SRM was for the lateral tibial compartment at 0.38 (the gold standard had 0.34). For the femoral compartments, the gold standard had higher SRMs than the automatic methods at 0.31/0.30 for medial/lateral compartments. Conclusion The lower SRMs for the DL methods in the femoral compartments at 0.2 were possibly due to the simple sub-compartment extraction done during post-processing. The study demonstrated that state-of-the-art DL segmentation methods may be used in standardized longitudinal single-scanner clinical trials for well-defined cartilage compartments.

Objective The aim of this literature review is to yield a comprehensive and exhaustive overview of the existing evidence and up-to-date applications of artificial intelligence for knee osteoarthritis. Methods A literature review was performed by using PubMed, Google Scholar, and IEEE databases for articles published in peer-reviewed journals in 2022. The articles focusing on the use of artificial intelligence in diagnosis and prognosis of knee osteoarthritis and accelerating the image acquisition were selected. For each selected study, the code availability, considered number of patients and knees, imaging type, covariates, grading type of osteoarthritis, models, validation approaches, objectives, and results were reviewed. Results 395 articles were screened, and 35 of them were reviewed. Eight articles were based on diagnosis, six on prognosis prediction, three on classification, three on accelerated image acquisition, and 15 on segmentation of knee osteoarthritis. 57% of the articles used MRI, 26% radiography, 6% MRI together with radiography, 6% ultrasonography, and 6% only clinical data. 23% of the articles made the computer codes available for their study, and 26% used clinical data. External validation and nested cross-validation were used in 17% and 14% of articles, respectively. Conclusions The use of artificial intelligence provided a promising potential to enhance the detection and management of knee osteoarthritis. Translating the developed models into clinics is still in the early stages of development. The translation of artificial intelligence models is expected to be further examined in prospective studies to support clinicians in improving routine healthcare practice.

Purpose To organize a multi-institute knee MRI segmentation challenge for characterizing the semantic and clinical efficacy of automatic segmentation methods relevant for monitoring osteoarthritis progression. Materials and Methods A dataset partition consisting of three-dimensional knee MRI from 88 retrospective patients at two time points (baseline and 1-year follow-up) with ground truth articular (femoral, tibial, and patellar) cartilage and meniscus segmentations was standardized. Challenge submissions and a majority-vote ensemble were evaluated against ground truth segmentations using Dice score, average symmetric surface distance, volumetric overlap error, and coefficient of variation on a holdout test set. Similarities in automated segmentations were measured using pairwise Dice coefficient correlations. Articular cartilage thickness was computed longitudinally and with scans. Correlation between thickness error and segmentation metrics was measured using the Pearson correlation coefficient. Two empirical upper bounds for ensemble performance were computed using combinations of model outputs that consolidated true positives and true negatives. Results Six teams (T1–T6) submitted entries for the challenge. No differences were observed across any segmentation metrics for any tissues (P = .99) among the four top-performing networks (T2, T3, T4, T6). Dice coefficient correlations between network pairs were high (> 0.85). Per-scan thickness errors were negligible among networks T1–T4 (P = .99), and longitudinal changes showed minimal bias (< 0.03 mm). Low correlations (ρ < 0.41) were observed between segmentation metrics and thickness error. The majority-vote ensemble was comparable to top-performing networks (P = .99). Empirical upper-bound performances were similar for both combinations (P = .99). Conclusion Diverse networks learned to segment the knee similarly, where high segmentation accuracy did not correlate with cartilage thickness accuracy and voting ensembles did not exceed individual network performance. See also the commentary by Elhalawani and Mak in this issue. Keywords: Cartilage, Knee, MR-Imaging, Segmentation © RSNA, 2020 Supplemental material is available for this article.

Background The methods for assessing knee osteoarthritis (OA) do not provide enough comprehensive information to make robust and accurate outcome predictions. Purpose To develop a deep learning (DL) prediction model for risk of OA progression by using knee radiographs in patients who underwent total knee replacement (TKR) and matched control patients who did not undergo TKR. Materials and Methods In this retrospective analysis that used data from the OA Initiative, a DL model on knee radiographs was developed to predict both the likelihood of a patient undergoing TKR within 9 years and Kellgren-Lawrence (KL) grade. Study participants included a case-control matched subcohort between 45 and 79 years. Patients were matched to control patients according to age, sex, ethnicity, and body mass index. The proposed model used a transfer learning approach based on the ResNet34 architecture with sevenfold nested cross-validation. Receiver operating characteristic curve analysis and conditional logistic regression assessed model performance for predicting probability and risk of TKR compared with clinical observations and two binary outcome prediction models on the basis of radiographic readings: KL grade and OA Research Society International (OARSI) grade. Results Evaluated were 728 participants including 324 patients (mean age, 64 years ± 8 [standard deviation]; 222 women) and 324 control patients (mean age, 64 years ± 8; 222 women). The prediction model based on DL achieved an area under the receiver operating characteristic curve (AUC) of 0.87 (95% confidence interval [CI]: 0.85, 0.90), outperforming a baseline prediction model by using KL grade with an AUC of 0.74 (95% CI: 0.71, 0.77; P < .001). The risk for TKR increased with probability that a person will undergo TKR from the DL model (odds ratio [OR], 7.7; 95% CI: 2.3, 25; P < .001), KL grade (OR, 1.92; 95% CI: 1.17, 3.13; P = .009), and OARSI grade (OR, 1.20; 95% CI: 0.41, 3.50; P = .73). Conclusion The proposed deep learning model better predicted risk of total knee replacement in osteoarthritis than did binary outcome models by using standard grading systems. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Richardson in this issue.

Purpose: To use convolutional neural networks (CNNs) for fully automated MRI segmentation of the glenohumeral joint and evaluate the accuracy of three-dimensional (3D) MRI models created with this method. Materials and methods: Shoulder MR images of 100 patients (average age, 44 years; range, 14-80 years; 60 men) were retrospectively collected from September 2013 to August 2018. CNNs were used to develop a fully automated segmentation model for proton density-weighted images. Shoulder MR images from an additional 50 patients (mean age, 33 years; range, 16-65 years; 35 men) were retrospectively collected from May 2014 to April 2019 to create 3D MRI glenohumeral models by transfer learning using Dixon-based sequences. Two musculoskeletal radiologists performed measurements on fully and semiautomated segmented 3D MRI models to assess glenohumeral anatomy, glenoid bone loss (GBL), and their impact on treatment selection. Performance of the CNNs was evaluated using Dice similarity coefficient (DSC), sensitivity, precision, and surface-based distance measurements. Measurements were compared using matched-pairs Wilcoxon signed rank test. Results: The two-dimensional CNN model for the humerus and glenoid achieved a DSC of 0.95 and 0.86, a precision of 95.5% and 87.5%, an average precision of 98.6% and 92.3%, and a sensitivity of 94.8% and 86.1%, respectively. The 3D CNN model, for the humerus and glenoid, achieved a DSC of 0.95 and 0.86, precision of 95.1% and 87.1%, an average precision of 98.7% and 91.9%, and a sensitivity of 94.9% and 85.6%, respectively. There was no difference between glenoid and humeral head width fully and semiautomated 3D model measurements (P value range, .097-.99). Conclusion: CNNs could potentially be used in clinical practice to provide rapid and accurate 3D MRI glenohumeral bone models and GBL measurements.

Purpose This study investigates the implications of all degrees of freedom of within-scan patient head motion on patient safety. Methods Electromagnetic simulations were performed by displacing and/or rotating a virtual body model inside an 8-channel transmit array to simulate 6 degrees of freedom of motion. Rotations of up to 20° and displacements of up to 20 mm including off-axis axial/coronal translations were investigated, yielding 104 head positions. Quadrature excitation, RF shimming, and multi-spoke parallel-transmit excitation pulses were designed for axial slice-selection at 7T, for seven slices across the head. Variation of whole-head specific absorption rate (SAR) and 10-g averaged local SAR of the designed pulses, as well as the change in the maximum eigenvalue (worst-case pulse) were investigated by comparing off-center positions to the central position. Results In their respective worst-cases, patient motion increased the eigenvalue-based local SAR by 42%, whole-head SAR by 60%, and the 10-g averaged local SAR by 210%. Local SAR was observed to be more sensitive to displacements along right?left and anterior?posterior directions than displacement in the superior?inferior direction and rotation. Conclusion This is the first study to investigate the effect of all 6 degrees of freedom of motion on safety of practical pulses. Although the results agree with the literature for overlapping cases, the results demonstrate higher increases (up to 3.1-fold) in local SAR for off-axis displacement in the axial plane, which had received less attention in the literature. This increase in local SAR could potentially affect the local SAR compliance of subjects, unless realistic within-scan patient motion is taken into account during pulse design.

Knee osteoarthritis (OA) is a chronic degenerative disorder of joints and it is the most common reason leading to total knee joint replacement. Diagnosis of OA involves subjective judgment on symptoms, medical history, and radiographic readings using Kellgren-Lawrence grade (KL-grade). Deep learning-based methods such as Convolution Neural Networks (CNN) have recently been applied to automatically diagnose radiographic knee OA. In this study, we applied Residual Neural Network (ResNet) to first detect knee joint from radiographs and later combine ResNet with Convolutional Block Attention Module (CBAM) to make a prediction of the KL-grade automatically. The proposed model achieved a multi-class average accuracy of 74.81%, mean squared error of 0.36, and quadratic Kappa score of 0.88, which demonstrates a significant improvement over the published results. The attention maps were analyzed to provide insights on the decision process of the proposed model. Code is available at https://github.com/denizlab/OAI-KL-Grade-Classification.

Osteoarthritis (OA) is a chronic degenerative disorder of joints and is the most common reason leading to total knee joint replacement (TKR). In this paper, we implemented a semi-supervised learning approach based on Unsupervised Data Augmentation (UDA) along with valid perturbations for radiographs to enhance the performance of supervised TKR outcome prediction model. Our results suggest that the use of semi-supervised approach provides superior results compared to the supervised approach (AUC of 0.79 &plusmn; 0.04 vs 0.74 &plusmn; 0.04).

Magnetic resonance imaging (MRI) has been driven toward ultrahigh magnetic fields (UHF) in order to benefit from correspondingly higher signal-to-noise ratio and spectral resolution. Technological challenges associated with UHF, such as increased radiofrequency (RF) energy deposition and RF excitation inhomogeneity, limit realization of the full potential of these benefits. Parallel RF transmission (pTx) enables decreases in the inhomogeneity of RF excitations and in RF energy deposition by using multiple-transmit RF coils driven independently and operating simultaneously. pTx plays a fundamental role in UHF MRI by bringing the potential applications of UHF into reality. In this review article, we review the recent developments in pTx pulse design and RF safety in pTx. Simultaneous multislice imaging and inner volume imaging using pTx are reviewed with a focus on UHF applications. Emerging pTx design approaches using improved pTx design frameworks and calibrations are reviewed together with calibration-free approaches that remove the necessity of time-consuming calibrations necessary for successful pTx. Lastly, we focus on the safety of pTx that is improved by using intersubject variability analysis, proactively managing pTx and temperature-based pTx approaches.

Magnetic resonance imaging (MRI) has been proposed as a complimentary method to measure bone quality and assess fracture risk. However, manual segmentation of MR images of bone is time-consuming, limiting the use of MRI measurements in the clinical practice. The purpose of this paper is to present an automatic proximal femur segmentation method that is based on deep convolutional neural networks (CNNs). This study had institutional review board approval and written informed consent was obtained from all subjects. A dataset of volumetric structural MR images of the proximal femur from 86 subjects were manually-segmented by an expert. We performed experiments by training two different CNN architectures with multiple number of initial feature maps, layers and dilation rates, and tested their segmentation performance against the gold standard of manual segmentations using four-fold cross-validation. Automatic segmentation of the proximal femur using CNNs achieved a high dice similarity score of 0.95 ± 0.02 with precision = 0.95 ± 0.02, and recall = 0.95 ± 0.03. The high segmentation accuracy provided by CNNs has the potential to help bring the use of structural MRI measurements of bone quality into clinical practice for management of osteoporosis.

Purpose Introduce a novel coil design using an electrically long transversely oriented slot in a conductive sheet. Theory and Methods Theoretical considerations, numerical simulations, and experimental measurements are presented for transverse slot antennas as compared with electric dipole antennas. Results Simulations show improved central and average transmit and receive efficiency, as well as larger coverage in the transverse plane, for a single slot as compared to a single dipole element. Experiments on a body phantom confirm the simulation results for a slot antenna relative to a dipole, demonstrating a large region of relatively high sensitivity and homogeneity. Images in a human subject also show a large imaging volume for a single slot and six slot antenna array. High central transmit efficiency was observed for slot arrays relative to dipole arrays. Conclusion Transverse slots can exhibit improved sensitivity and larger field of view compared with traditional conductive dipoles. Simulations and experiments indicate high potential for slot antennas in high field MRI.

Purpose To explore the use of polyvinylpyrrolidone (PVP) for simulated materials with tissue‐equivalent dielectric properties. Methods PVP and salt were used to control, respectively, relative permittivity and electrical conductivity in a collection of 63 samples with a range of solute concentrations. Their dielectric properties were measured with a commercial probe and fitted to a 3D polynomial in order to establish an empirical recipe. The material's thermal properties and MR spectra were measured. Results The empirical polynomial recipe (available at https://www.amri.ninds.nih.gov/cgi-bin/phantomrecipe) provides the PVP and salt concentrations required for dielectric materials with permittivity and electrical conductivity values between approximately 45 and 78, and 0.1 to 2 siemens per meter, respectively, from 50 MHz to 4.5 GHz. The second‐ (solute concentrations) and seventh‐ (frequency) order polynomial recipe provided less than 2.5% relative error between the measured and target properties. PVP side peaks in the spectra were minor and unaffected by temperature changes. Conclusion PVP‐based phantoms are easy to prepare and nontoxic, and their semitransparency makes air bubbles easy to identify. The polymer can be used to create simulated material with a range of dielectric properties, negligible spectral side peaks, and long T2 relaxation time, which are favorable in many MR applications.

Objective To use high-permittivity materials (HPM) positioned near radiofrequency (RF) surface coils to manipulate transmit/receive field patterns. Materials and methods A large HPM pad was placed below the RF coil to extend the field of view (FOV). The resulting signal-to-noise ratio (SNR) was compared with that of other coil configurations covering the same FOV in simulations and experiments at 7 T. Transmit/receive efficiency was evaluated when HPM discs with or without a partial shield were positioned at a distance from the coil. Finally, we evaluated the increase in transmit homogeneity for a four-channel array with HPM discs interposed between adjacent coil elements. Results Various configurations of HPM increased SNR, transmit/receive efficiency, excitation/reception sensitivity overlap, and FOV when positioned near a surface coil. For a four-channel array driven in quadrature, shielded HPM discs enhanced the field below the discs as well as at the center of the sample as compared with other configurations with or without unshielded HPM discs. Conclusion Strategically positioning HPM at a distance from a surface coil or array can increase the overlap between excitation/reception sensitivities, and extend the FOV of a single coil for reduction of the number of channels in an array while minimally affecting the SNR.

Background There is growing interest in detecting cerebro‐cerebellar circuits, which requires adequate blood oxygenation level dependent contrast and signal‐to‐noise ratio (SNR) throughout the brain. Although 7T scanners offer increased SNR, coverage of commercial head coils is currently limited to the cerebrum. Purpose To improve cerebellar functional MRI (fMRI) at 7T with high permittivity material (HPM) pads extending the sensitivity of a commercial coil. Study Type Simulations were used to determine HPM pad configuration and assess radiofrequency (RF) safety. In vivo experiments were performed to evaluate RF field distributions and SNR and assess improvements of cerebellar fMRI. Subjects Eight healthy volunteers enrolled in a prospective motor fMRI study with and without HPM. Field Strength/Sequence Gradient echo (GRE) echo planar imaging for fMRI, turbo FLASH for flip angle mapping, GRE sequence for SNR maps, and T1‐weighted MPRAGE were acquired with and without HPM pads at 7T. Assessment Field maps, SNR maps, and anatomical images were evaluated for coverage. Simulation results were used to assess SAR levels of the experiment. Activation data from fMRI experiments were compared with and without HPM pads. Statistical Tests fMRI data were analyzed using FEAT FSL for each subject followed by group level analysis using paired t‐test of acquisitions with and without HPM. Results Simulations showed 52% improvement in transmit efficiency in cerebellum with HPM and SAR levels well below recommended limits. Experiments showed 27% improvement in SNR in cerebellum and improvement in coverage on T1‐weighted images. fMRI showed greater cerebellar activation in individual subjects with the HPM pad present (Z > = 4), especially in inferior slices of cerebellum, with 59% average increase in number of activated voxels in the cerebellum. Group‐level analysis showed improved functional activation (Z > = 2.3) in cerebellar regions with HPM pads without loss of measured activation elsewhere. Data Conclusion HPM pads can improve cerebellar fMRI at 7T with a commonly‐used head coil without compromising RF safety.

RF safety in parallel transmission (pTx) is generally ensured by imposing specific absorption rate (SAR) limits during pTx RF pulse design. There is increasing interest in using temperature to ensure safety in MRI. In this work, we present a local temperature correlation matrix formalism and apply it to impose strict constraints on maximum absolute temperature in pTx RF pulse design for head and hip regions. Electromagnetic field simulations were performed on the head and hip of virtual body models. Temperature correlation matrices were calculated for four different exposure durations ranging between 6 and 24 min using simulated fields and body‐specific constants. Parallel transmission RF pulses were designed using either SAR or temperature constraints, and compared with each other and unconstrained RF pulse design in terms of excitation fidelity and safety. The use of temperature correlation matrices resulted in better excitation fidelity compared with the use of SAR in parallel transmission RF pulse design (for the 6 min exposure period, 8.8% versus 21.0% for the head and 28.0% versus 32.2% for the hip region). As RF exposure duration increases (from 6 min to 24 min), the benefit of using temperature correlation matrices on RF pulse design diminishes. However, the safety of the subject is always guaranteed (the maximum temperature was equal to 39°C). This trend was observed in both head and hip regions, where the perfusion rates are very different.

In recent years, there has been an increasing interest in millimeterwave (mm-wave) technologies operating at frequencies between 10 and 300 GHz. mm-wave communication provides higher transfer rates that will be employed in the next-generation wireless networks. However, mm-wave device exposure compliance assessment is challenging due to a reduced wavelength and an increased number of antennas. In this article, we discuss physical features of future mmwave communication networks and describe the requirements for proper exposure compliance assessment. Leading technologies that can be prospectively used for mm-wave exposure compliance are surveyed. Their pros and cons with respect to operating frequency, availability, sensitivity, and speed are discussed.

Deposition of radiofrequency (RF) energy can be quantified via electric field or temperature change measurements. Magnetic resonance imaging has been used as a tool to measure three dimensional small temperature changes associated with RF radiation exposure. When duration of RF exposure is long, conversion from temperature change to specific absorption rate (SAR) is nontrivial due to prominent heat-diffusion and conduction effects. In this work, we demonstrated a method for calculation of SAR via an inversion of the heat equation including heat-diffusion and conduction effects. This method utilizes high-resolution three dimensional magnetic resonance temperature images and measured thermal properties of the phantom to achieve accurate calculation of SAR. Accuracy of the proposed method was analyzed with respect to operating frequency of a dipole antenna and parameters used in heat equation inversion. Bioelectromagnetics. 37:493-503, 2016. textcopyright 2016 Wiley Periodicals, Inc.

Purpose Develop a practical comprehensive package for proactive management of parallel radiofrequency (RF) transmission. Methods With a constrained optimization framework and predictive models from a prescan based multichannel calibration, we presented a method supporting design and optimization of parallel RF excitation pulses that accurately obey the forward/reflected peak and average power limits of the RF power amplifiers in parallel transmit imaging experiments and Bloch simulations. Moreover, local SAR limits were incorporated into the parallel RF excitation pulses using electromagnetic field simulations. Virtual transmit coils concept for minimization of reflected power (effecting subject‐specific matching) was additionally demonstrated by leveraging experimentally calibrated power models. Results Incorporation of experimentally calibrated power prediction models resulted in accurate compliance with prescribed hardware and global specific absorption rate (SAR) limits. Incorporation of spatial average 10 g SAR models, facilitated by simplifying numerical approximations, provided assurance of patient safety. RF pulses designed with various constraints demonstrated excellent excitation fidelity—the normalized root‐mean‐square error of the simulated excitation profiles was 2.6% for the fully constrained pulses, comparable to that of the unconstrained pulses. An RF shimming example showed a reduction of the reflected‐to‐forward power ratio to 1.7% from a conventional approach's 8.1%. Conclusion Using the presented RF pulse design method, effective proactive management of the multifaceted power and SAR limits was demonstrated in experimental and simulation studies.

Electromagnetic field simulations are increasingly used to assure RF safety of patients during MRI exams. In practice, however, tissue property distribution of the patient being imaged is not known, but may be represented with a pre-existing model. Repeatedly, agreement in transmit magnetic (B1 ) field distributions between two geome- tries has been used to suggest agreement in heating distributions. Here we examine rel- ative effects of anatomical differences on B1 distribution, specific absorption rate (SAR), and temperature change (DT). Numerical simulations were performed for a single surface coil positioned adjacent a homogeneous phantom and bovine phantom, each with slight geometric variations, and adjacent two different human body models. Experimental dem- onstration was performed on a bovine phantom using MR thermometry and B1 mapping. Simulations and experiments demonstrate that B1 distributions in different samples can be well correlated, while notable difference in maximum SAR and DT occur. This work illustrates challenges associated with utilizing simulations or experiments for RF safety assurance purposes. Reliance on B1 distributions alone for validation of simulations and/or experiments with a sample or subject for assurance of safety in another should be performed with caution.

Purpose Strict regulations are imposed on the amount of radiofrequency (RF) energy that devices can emit to prevent excessive deposition of RF energy into the body. In this study, we investigated the application of MR temperature mapping and 10‐g average specific absorption rate (SAR) computation for safety evaluation of RF‐emitting devices. Methods Quantification of the RF power deposition was shown for an MRI‐compatible dipole antenna and a non–MRI‐compatible mobile phone via phantom temperature change measurements. Validation of the MR temperature mapping method was demonstrated by comparison with physical temperature measurements and electromagnetic field simulations. MR temperature measurements alongside physical property measurements were used to reconstruct 10‐g average SAR. Results The maximum temperature change for a dipole antenna and the maximum 10‐g average SAR were 1.83°C and 12.4 W/kg, respectively, for simulations and 1.73°C and 11.9 W/kg, respectively, for experiments. The difference between MR and probe thermometry was <0.15°C. The maximum temperature change and the maximum 10‐g average SAR for a cell phone radiating at maximum output for 15 min was 1.7°C and 0.54 W/kg, respectively. Conclusion Information acquired using MR temperature mapping and thermal property measurements can assess RF/microwave safety with high resolution and fidelity.

Purpose We investigated global specific absorption rate (SAR) and radiofrequency (RF) power requirements in parallel transmission as the distance between the transmit coils and the sample was increased. Methods We calculated ultimate intrinsic SAR (UISAR), which depends on object geometry and electrical properties but not on coil design, and we used it as the reference to compare the performance of various transmit arrays. We investigated the case of fixing coil size and increasing the number of coils while moving the array away from the sample, as well as the case of fixing coil number and scaling coil dimensions. We also investigated RF power requirements as a function of lift‐off, and tracked local SAR distributions associated with global SAR optima. Results In all cases, the target excitation profile was achieved and global SAR (as well as associated maximum local SAR) decreased with lift‐off, approaching UISAR, which was constant for all lift‐offs. We observed a lift‐off value that optimizes the balance between global SAR and power losses in coil conductors. We showed that, using parallel transmission, global SAR can decrease at ultra high fields for finite arrays with a sufficient number of transmit elements. Conclusion For parallel transmission, the distance between coils and object can be optimized to reduce SAR and minimize RF power requirements associated with homogeneous excitation

Purpose To determine the feasibility of using finite element analysis applied to 3-T magnetic resonance (MR) images of proximal femur microarchitecture for detection of lower bone strength in subjects with fragility fractures compared with control subjects without fractures. Materials and Methods This prospective study was institutional review board approved and HIPAA compliant. Written informed consent was obtained. Postmenopausal women with (n = 22) and without (n = 22) fragility fractures were matched for age and body mass index. All subjects underwent standard dual-energy x-ray absorptiometry. Images of proximal femur microarchitecture were obtained by using a high-spatial-resolution three-dimensional fast low-angle shot sequence at 3 T. Finite element analysis was applied to compute elastic modulus as a measure of strength in the femoral head and neck, Ward triangle, greater trochanter, and intertrochanteric region. The Mann-Whitney test was used to compare bone mineral density T scores and elastic moduli between the groups. The relationship (R2) between elastic moduli and bone mineral density T scores was assessed. Results Patients with fractures showed lower elastic modulus than did control subjects in all proximal femur regions (femoral head, 8.51–8.73 GPa vs 9.32–9.67 GPa; P = .04; femoral neck, 3.11–3.72 GPa vs 4.39–4.82 GPa; P = .04; Ward triangle, 1.85–2.21 GPa vs 3.98–4.13 GPa; P = .04; intertrochanteric region, 1.62–2.18 GPa vs 3.86–4.47 GPa; P = .006–.007; greater trochanter, 0.65–1.21 GPa vs 1.96–2.62 GPa; P = .01–.02), but no differences in bone mineral density T scores. There were weak relationships between elastic moduli and bone mineral density T scores in patients with fractures (R2 = 0.25–0.31, P = .02–.04), but not in control subjects. Conclusion Finite element analysis applied to high-spatial-resolution 3-T MR images of proximal femur microarchitecture can allow detection of lower elastic modulus, a marker of bone strength, in subjects with fragility fractures compared with control subjects. MR assessment of proximal femur strength may provide information about bone quality that is not provided by dual-energy x-ray absorptiometry.

PURPOSE: High-resolution imaging of deeper anatomy such as the hip is challenging due to low signal-to-noise ratio (SNR), necessitating long scan times. Multi-element coils can increase SNR and reduce scan time through parallel imaging (PI). We assessed the feasibility of using a 26-element receive coil setup to perform 3 Tesla (T) MRI of proximal femur microarchitecture without and with PI. MATERIALS AND METHODS: This study had institutional review board approval. We scanned 13 subjects on a 3T scanner using 26 receive-elements and a three-dimensional fast low-angle shot (FLASH) sequence without and with PI (acceleration factors [AF] 2, 3, 4). We assessed SNR, depiction of individual trabeculae, PI performance (1/g-factor), and image quality with PI (1 = nonvisualization to 5 = excellent). RESULTS: SNR maps demonstrate higher SNR for the 26-element setup compared with a 12-element setup for hip MRI. Without PI, individual proximal femur trabeculae were well-depicted, including microarchitectural deterioration in osteoporotic subjects. With PI, 1/g values for the 26-element/12-element receive-setup were 0.71/0.45, 0.56/0.25, and 0.44/0.08 at AF2, AF3, and AF4, respectively. Image quality was: AF1, excellent (4.8 ± 0.4); AF2, good (4.2 ± 1.0); AF3, average (3.3 ± 1.0); AF4, nonvisualization (1.4 ± 0.9). CONCLUSION: A 26-element receive-setup permits 3T MRI of proximal femur microarchitecture with good image quality up to PI AF2.

Purpose To demonstrate the feasibility of performing bone microarchitecture, high-resolution cartilage, and clinical imaging of the hip at 7T. Materials and Methods This study had Institutional Review Board approval. Using an 8-channel coil constructed in-house, we imaged the hips of 15 subjects on a 7T magnetic resonance imaging (MRI) scanner. We applied: 1) a T1-weighted 3D fast low angle shot (3D FLASH) sequence (0.23 ? 0.23 ? 1-1.5 mm3) for bone microarchitecture imaging; 2) T1-weighted 3D FLASH (water excitation) and volumetric interpolated breath-hold examination (VIBE) sequences (0.23 ? 0.23 ? 1.5 mm3) with saturation or inversion recovery-based fat suppression for cartilage imaging; 3) 2D intermediate-weighted fast spin-echo (FSE) sequences without and with fat saturation (0.27 ? 0.27 ? 2 mm) for clinical imaging. Results Bone microarchitecture images allowed visualization of individual trabeculae within the proximal femur. Cartilage was well visualized and fat was well suppressed on FLASH and VIBE sequences. FSE sequences allowed visualization of cartilage, the labrum (including cartilage and labral pathology), joint capsule, and tendons. Conclusion This is the first study to demonstrate the feasibility of performing a clinically comprehensive hip MRI protocol at 7T, including high-resolution imaging of bone microarchitecture and cartilage, as well as clinical imaging. Copyright ? 2013 Wiley Periodicals, Inc.

OBJECTIVE: The objective of the study was to investigate the feasibility of 7-T shoulder magnetic resonance imaging by developing transmit and receive radiofrequency (RF) coil arrays and exploring RF shim methods.$backslash$n$backslash$nMATERIALS AND METHODS: A mechanically flexible 8-channel transmit array and an anatomically conformable 10-channel receive array were designed and implemented. The transmit performance of various RF shim methods was assessed through local flip angle measurements in the right and left shoulders of 6 subjects. The receive performance was assessed through signal-to-noise ratio measurements using the developed 7-T coil and a baseline commercial 3-T coil.$backslash$n$backslash$nRESULTS: The 7-T transmit array driven with phase-coherent RF shim weights provided adequate B₁⁺ efficiency and uniformity for turbo spin echo shoulder imaging. B₁⁺ twisting that is characteristic of high-field loop coils necessitates distinct RF shim weights in the right and left shoulders. The 7-T receive array provided a 2-fold signal-to-noise ratio improvement over the 3-T array in the deep articular shoulder cartilage.$backslash$n$backslash$nCONCLUSIONS: Shoulder imaging at 7-T is feasible with a custom transmit/receive array either in a single-channel transmit mode with a fixed RF shim or in a parallel transmit mode with a subject-specific RF shim.

Radiofrequency shimming with multiple channel excitation has been proposed to increase the transverse magnetic field uniformity and reduce specific absorption rate at high magnetic field strengths (≥7 T) where high-frequency effects can make traditional single channel volume coils unsuitable for transmission. In the case of deep anatomic regions and power-demanding pulse sequences, optimization of transmit efficiency may be a more critical requirement than homogeneity per se. This work introduces a novel method to maximize transmit efficiency using multiple channel excitation and radiofrequency shimming. Shimming weights are calculated in order to obtain the lowest possible net radiofrequency power deposition into the subject for a given transverse magnetic field strength. The method was demonstrated in imaging studies of articular cartilage of the hip joint at 7 T. We show that the new radiofrequency shimming method can enable reduction in power deposition while maintaining an average flip angle or adiabatic condition in the hip cartilage. Building upon the improved shimming, we further show that the signal-to-noise ratio in hip cartilage at 7 T can be substantially greater than that at 3 T, illustrating the potential benefits of high field hip imaging.

In ultra-high-field magnetic resonance imaging, parallel radiofrequency (RF) transmission presents both opportunities and challenges for specific absorption rate management. On one hand, parallel transmission provides flexibility in tailoring electric fields in the body while facilitating magnetization profile control. On the other hand, it increases the complexity of energy deposition as well as possibly exacerbating local specific absorption rate by improper design or delivery of RF pulses. This study shows that the information needed to characterize RF heating in parallel transmission is contained within a local power correlation matrix. Building upon a calibration scheme involving a finite number of magnetic resonance thermometry measurements, this work establishes a way of estimating the local power correlation matrix. Determination of this matrix allows prediction of temperature change for an arbitrary parallel transmit RF pulse. In the case of a three transmit coil MR experiment in a phantom, determination and validation of the power correlation matrix were conducted in less than 200 min with induced temperature changes of textless4 degrees C. Further optimization and adaptation are possible, and simulations evaluating potential feasibility for in vivo use are presented. The method allows general characteristics indicative of RF coil/pulse safety determined in situ.

Radiofrequency (RF) emitting wireless devices such as mobile phones are required to undergo standardized safety testing prior to entering the consumer market. Strict regulations are imposed on the amount of RF energy these devices are allowed to emit to prevent excessive deposition of RF energy into the body. In this work, a novel safety evaluation test for wireless devices using magnetic resonance thermometry is proposed.

The markedly increased degrees of freedom introduced by parallel radiofrequency transmission presents both opportunities and challenges for specific absorption rate (SAR) management. On one hand they enable E-field tailoring and SAR reduction while facilitating excitation profile control. On other hand they increase the complexity of SAR behavior and the risk of inadvertently exacerbating SAR by improper design or playout of radiofrequency pulses. The substantial subject-dependency of SAR in high field magnetic resonance can be a compounding factor. Building upon a linear system concept and a calibration scheme involving a finite number of in situ measurements, this work establishes a clinically applicable method for characterizing global SAR behavior as well as channel-by-channel power transmission. The method offers a unique capability of predicting, for any excitation, the SAR and power consequences that are specific to the subject to be scanned and the MRI hardware. The method was validated in simulation and experimental studies, showing promise as the foundation to a prospective paradigm where power and SAR are not only monitored but, through prediction-guided optimization, proactively managed.

Specific absorption rate management and excitation fidelity are key aspects of radiofrequency pulse design for parallel transmission at ultra-high magnetic field strength. The design of radiofrequency pulses for multiple channels is often based on the solution of regularized least-squares optimization problems for which a regularization term is typically selected to control the integrated or peak pulse waveform amplitude. Unlike single-channel transmission, the specific absorption rate of parallel transmission is significantly influenced by interferences between the electric fields associated with the individual transmission elements, which a conventional regularization term does not take into account. This work explores the effects upon specific absorption rate of incorporating experimentally measurable electric field interactions into parallel transmission pulse design. Results of numerical simulations and phantom experiments show that the global specific absorption rate during parallel transmission decreases when electric field interactions are incorporated into pulse design optimization. The results also show that knowledge of electric field interactions enables robust prediction of the net power delivered to the sample or subject by parallel radiofrequency pulses before they are played out on a scanner.

Echo-Modulation-Curves (EMC) T2 fitting was evaluated for reproducibility and prediction of knee osteoarthritis incidence in the Osteoarthritis Initiative. EMC fitting showed improved reproducibility and predictive accuracy compared with mono-exponential T2 mapping.