Conference Proceedings - Cem M. Deniz

Huang, Haoxu; Rawlekar, Samyak; Chopra, Sumit; Deniz, Cem M

Radiology Reports Improve Visual Representations Learned from Radiographs Proceedings Article

In: Oguz, Ipek; Noble, Jack; Li, Xiaoxiao; Styner, Martin; Baumgartner, Christian; Rusu, Mirabela; Heinmann, Tobias; Kontos, Despina; Landman, Bennett; Dawant, Benoit (Ed.): Medical Imaging with Deep Learning, pp. 1385–1405, PMLR, 2024.

Abstract | Links | BibTeX

@inproceedings{pmlr-v227-huang24a,

title = {Radiology Reports Improve Visual Representations Learned from Radiographs},

author = {Haoxu Huang and Samyak Rawlekar and Sumit Chopra and Cem M Deniz},

editor = {Ipek Oguz and Jack Noble and Xiaoxiao Li and Martin Styner and Christian Baumgartner and Mirabela Rusu and Tobias Heinmann and Despina Kontos and Bennett Landman and Benoit Dawant},

url = {https://proceedings.mlr.press/v227/huang24a.html},

year  = {2024},

date = {2024-07-01},

booktitle = {Medical Imaging with Deep Learning},

volume = {227},

pages = {1385–1405},

publisher = {PMLR},

series = {Proceedings of Machine Learning Research},

abstract = {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.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

Close

Cigdem, Ozkan; Hedeyati, Eisa; Rajamohan, Haresh R.; Cho, Kyunghyun; Chang, Gregory; Kijowski, Richard; Deniz, Cem M.

Estimation Of Time-To-Total Knee Replacement Surgery With Deep Learning Using MRI And Clinical Data Proceedings Article

In: Proceedings 32nd Scientific Meeting, ISMRM, pp. 3797, 2024.

BibTeX

Chen, Shengjia; Cigdem, Ozkan; Zhang, Chaojie; Rajamohan, Haresh R.; Cho, Kyunghyun; Kijowski, Richard; Deniz, Cem M.

Denoising AutoEncoder As A Pre-Processor For Knee MRI Analysis Proceedings Article

In: Proceedings 32nd Scientific Meeting, ISMRM, pp. 1965, 2024.

BibTeX

Montin, Eros; Cigdem, Ozkan; Rajamohan, Haresh R.; Cho, Kyunghyun; Kijowski, Richard; Deniz, Cem M.; Lattanzi, Riccardo

Predicting Total Knee Replacement Surgery Using Radiomic Features Extracted From MRI Scans Proceedings Article

In: Proceedings 32nd Scientific Meeting, ISMRM, pp. 1690, 2024.

BibTeX

Zhang, Chaojie; Chen, Shengjia; Rajamohan, Haresh R.; Cho, Kyunghyun; Kijowski, Richard; Deniz, Cem M.

MR-Transformer: Vision Transformers For Total Knee Replacement Prediction Using Magnetic Resonance Imaging Proceedings Article

In: Proceedings 32nd Scientific Meeting, ISMRM, pp. 1008, 2024.

BibTeX

Rajamohan, Haresh Rengaraj; Cho, Kyunghyun; Kijowski, Richard; Deniz, Cem

Deep Learning For Prediction Of Knee Osteoarthritis Structural Progression And Incidence Proceedings Article

In: Osteoarthritis and Cartilage, pp. S75–S76, Elsevier BV, 2024, ISSN: 1063-4584.

Links | BibTeX

Zhang, Chaojie; Chen, Shengjia; Huang, Haoxu; Rajamohan, Haresh Rengaraj; Park, Jungkyu; Kasmanoff, Noah; Cho, Kyunghyun; Chang, Gregory; Kijowski, Richard; Deniz, Cem M.

Total Knee Replacement Prediction Using Twin Class Distribution Estimation Proceedings Article

In: Proceedings 31th Scientific Meeting, ISMRM, pp. 1881, 2023.

BibTeX

Rajamohan, Haresh R.; Cho, Kyunghyun; Kijowski, Richard; Deniz, Cem M.

RiskForm: A Novel Risk Formulation To Improve Progressive Disease Outcome Prediction Proceedings Article

In: Proceedings 31th Scientific Meeting, ISMRM, pp. 1891, 2023.

BibTeX

Hedeyati, Eisa; Rajamohan, Haresh R.; Zhou, Lily; Cho, Kyunghyun; Chang, Gregory; Kijowski, Richard; Deniz, Cem M.

Estimating Time-To-Total Knee Replacement Surgery Using Deep Learning Proceedings Article

In: Proceedings 31th Scientific Meeting, ISMRM, pp. 1894, 2023.

BibTeX

Montin, Eros; Deniz, Cem M.; Rodrigues, Tatiane Cantarelli; Gyftopoulos, Soterios; Kijowski, Richard; Lattanzi, Riccardo

Automatic segmentation of the hip bony structures on 3D Dixon MRI datasets using transfer learning from a neural network developed for the shoulder Proceedings Article

In: Proceedings 30th Scientific Meeting, ISMRM, pp. 1412, 2022.

Links | BibTeX