Mohammad Reza Hosseinzadeh Taher
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mohammad Reza Hosseinzadeh Taher has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Jianming Liang
Arizona State University
10 shared publications - Michael B. Gotway
Department of Radiology Mayo Clinic Phoenix Arizona USA
9 shared publications - Fatemeh Haghighi
Arizona State University
4 shared publications Fatemeh Haghighi
School of Computing and Augmented Intelligence, Arizona State University, Tempe, AZ 85281, USA
3 shared publications- Jiaxuan Pang
Arizona State University
3 shared publications - DongAo Ma
Arizona State University
2 shared publications
Latest Publications
- 5 May 2026
- Published by Elsevier in Medical Image Analysis
- Vol. 112, 104117
Autodidactic dense anatomical models
- 5 May 2026
- Published by Elsevier in Medical Image Analysis
- Vol. 112, 104117
Autodidactic dense anatomical models
- 12 October 2025
- Published by Springer Nature
- p. 1-11
Three stylized light bulb illustrations are arranged in a row. The central bulb is yellow, while the two outer bulbs are dark blue. Each bulb is surrounded by small lines, suggesting illumination. The design is simple and uses a minimal color palette. Lamps: Learning Anatomy from Multiple Perspectives via Self-supervision in Chest Radiographs
- 12 October 2025
- Published by Springer Nature
- p. 1-11
Three stylized light bulb illustrations are arranged in a row. The central bulb is yellow, while the two outer bulbs are dark blue. Each bulb is surrounded by small lines, suggesting illumination. The design is simple and uses a minimal color palette. Lamps: Learning Anatomy from Multiple Perspectives via Self-supervision in Chest Radiographs
- 20 September 2025
- Published by Springer Nature
- p. 294-304
Learning Foundation Models from Multi-organ Medical Images by Capturing Consistency and Diversity of Anatomical Structures
- 20 September 2025
- Published by Springer Nature
- p. 294-304
Learning Foundation Models from Multi-organ Medical Images by Capturing Consistency and Diversity of Anatomical Structures
- 21 February 2025
- Published by Elsevier in Medical Image Analysis
- Vol. 102, 103487
Large-scale benchmarking and boosting transfer learning for medical image analysis
- 21 February 2025
- Published by Elsevier in Medical Image Analysis
- Vol. 102, 103487
Large-scale benchmarking and boosting transfer learning for medical image analysis
- 16 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Conference on Computer Vision and Pattern Recognition (CVPR)
- Vol. abs/210504 (2024) , 11269-11281
Representing Part-Whole Hierarchies in Foundation Models by Learning Localizability, Composability, and Decomposability from Anatomy via Self-Supervision
Humans effortlessly interpret images by parsing them into part-whole hierarchies; deep learning excels in learning multi-level feature spaces, but they often lack explicit coding of part-whole relations, a prominent property of medical imaging. To overcome this limitation, we introduce Adam-v2, a new self-supervised learning framework extending Adam [69] by explicitly incorporating part-whole hierarchies into its learning objectives through three key branches: (1) Localizability, acquiring discriminative representations to distinguish different anatomical patterns; (2) Composability, learning each anatomical structure in a parts-to-whole manner; and (3) Decomposability, comprehending each anatomical structure in a whole-to-parts manner. Experimental results across 10 tasks, compared to 11 baselines in zero-shot, few-shot transfer, and full fine-tuning settings, showcase Adam-v2's superior performance over large-scale medical models and existing SSL methods across diverse downstream tasks. The higher generality and robustness of Adam-v2's representations originate from its explicit construction of hierarchies for distinct anatomical structures from unlabeled medical images. Adam-v2 preserves a semantic balance of anatomical diversity and harmony in its embedding, yielding representations that are both generic and semantically meaningful, yet overlooked in existing SSL methods. All code and pretrained models are available at GitHub.com/JLiangLab/Eden.
- 16 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Conference on Computer Vision and Pattern Recognition (CVPR)
- Vol. abs/210504 (2024) , 11269-11281
Representing Part-Whole Hierarchies in Foundation Models by Learning Localizability, Composability, and Decomposability from Anatomy via Self-Supervision
Humans effortlessly interpret images by parsing them into part-whole hierarchies; deep learning excels in learning multi-level feature spaces, but they often lack explicit coding of part-whole relations, a prominent property of medical imaging. To overcome this limitation, we introduce Adam-v2, a new self-supervised learning framework extending Adam [69] by explicitly incorporating part-whole hierarchies into its learning objectives through three key branches: (1) Localizability, acquiring discriminative representations to distinguish different anatomical patterns; (2) Composability, learning each anatomical structure in a parts-to-whole manner; and (3) Decomposability, comprehending each anatomical structure in a whole-to-parts manner. Experimental results across 10 tasks, compared to 11 baselines in zero-shot, few-shot transfer, and full fine-tuning settings, showcase Adam-v2's superior performance over large-scale medical models and existing SSL methods across diverse downstream tasks. The higher generality and robustness of Adam-v2's representations originate from its explicit construction of hierarchies for distinct anatomical structures from unlabeled medical images. Adam-v2 preserves a semantic balance of anatomical diversity and harmony in its embedding, yielding representations that are both generic and semantically meaningful, yet overlooked in existing SSL methods. All code and pretrained models are available at GitHub.com/JLiangLab/Eden.
- 28 January 2024
- Published by Elsevier in Medical Image Analysis
- Vol. 94, 103086
Self-supervised learning for medical image analysis: Discriminative, restorative, or adversarial?
- 28 January 2024
- Published by Elsevier in Medical Image Analysis
- Vol. 94, 103086
Self-supervised learning for medical image analysis: Discriminative, restorative, or adversarial?
- 14 October 2023
- Published by Springer Nature
- Vol. 14293, 94-104
Towards Foundation Models Learned from Anatomy in Medical Imaging via Self-supervision
Human anatomy is the foundation of medical imaging and boasts one striking characteristic: its hierarchy in nature, exhibiting two intrinsic properties: (1) locality: each anatomical structure is morphologically distinct from the others; and (2) compositionality: each anatomical structure is an integrated part of a larger whole. We envision a foundation model for medical imaging that is consciously and purposefully developed upon this foundation to gain the capability of “understanding” human anatomy and to possess the fundamental properties of medical imaging. As our first step in realizing this vision towards foundation models in medical imaging, we devise a novel self-supervised learning (SSL) strategy that exploits the hierarchical nature of human anatomy. Our extensive experiments demonstrate that the SSL pretrained model, derived from our training strategy, not only outperforms state-of-the-art (SOTA) fully/self-supervised baselines but also enhances annotation efficiency, offering potential few-shot segmentation capabilities with performance improvements ranging from 9% to 30% for segmentation tasks compared to SSL baselines. This performance is attributed to the significance of anatomy comprehension via our learning strategy, which encapsulates the intrinsic attributes of anatomical structures—locality and compositionality—within the embedding space, yet overlooked in existing SSL methods. All code and pretrained models are available at GitHub.com/JLiangLab/Eden.
- 14 October 2023
- Published by Springer Nature
- Vol. 14293, 94-104
Towards Foundation Models Learned from Anatomy in Medical Imaging via Self-supervision
Human anatomy is the foundation of medical imaging and boasts one striking characteristic: its hierarchy in nature, exhibiting two intrinsic properties: (1) locality: each anatomical structure is morphologically distinct from the others; and (2) compositionality: each anatomical structure is an integrated part of a larger whole. We envision a foundation model for medical imaging that is consciously and purposefully developed upon this foundation to gain the capability of “understanding” human anatomy and to possess the fundamental properties of medical imaging. As our first step in realizing this vision towards foundation models in medical imaging, we devise a novel self-supervised learning (SSL) strategy that exploits the hierarchical nature of human anatomy. Our extensive experiments demonstrate that the SSL pretrained model, derived from our training strategy, not only outperforms state-of-the-art (SOTA) fully/self-supervised baselines but also enhances annotation efficiency, offering potential few-shot segmentation capabilities with performance improvements ranging from 9% to 30% for segmentation tasks compared to SSL baselines. This performance is attributed to the significance of anatomy comprehension via our learning strategy, which encapsulates the intrinsic attributes of anatomical structures—locality and compositionality—within the embedding space, yet overlooked in existing SSL methods. All code and pretrained models are available at GitHub.com/JLiangLab/Eden.
- 15 September 2022
- Published by Springer Nature
- Vol. 13542, 77-87
POPAR: Patch Order Prediction and Appearance Recovery for Self-supervised Medical Image Analysis
Vision transformer-based self-supervised learning (SSL) approaches have recently shown substantial success in learning visual representations from unannotated photographic images. However, their acceptance in medical imaging is still lukewarm, due to the significant discrepancy between medical and photographic images. Consequently, we propose POPAR (patch order prediction and appearance recovery), a novel vision transformer-based self-supervised learning framework for chest X-ray images. POPAR leverages the benefits of vision transformers and unique properties of medical imaging, aiming to simultaneously learn patch-wise high-level contextual features by correcting shuffled patch orders and fine-grained features by recovering patch appearance. We transfer POPAR pretrained models to diverse downstream tasks. The experiment results suggest that (1) POPAR outperforms state-of-the-art (SoTA) self-supervised models with vision transformer backbone; (2) POPAR achieves significantly better performance over all three SoTA contrastive learning methods; and (3) POPAR also outperforms fully-supervised pretrained models across architectures. In addition, our ablation study suggests that to achieve better performance on medical imaging tasks, both fine-grained and global contextual features are preferred. All code and models are available at GitHub.com/JLiangLab/POPAR. Keywords Vision transformer Self-supervised learning Medical image analysis Transfer learning
- 15 September 2022
- Published by Springer Nature
- Vol. 13542, 77-87
POPAR: Patch Order Prediction and Appearance Recovery for Self-supervised Medical Image Analysis
Vision transformer-based self-supervised learning (SSL) approaches have recently shown substantial success in learning visual representations from unannotated photographic images. However, their acceptance in medical imaging is still lukewarm, due to the significant discrepancy between medical and photographic images. Consequently, we propose POPAR (patch order prediction and appearance recovery), a novel vision transformer-based self-supervised learning framework for chest X-ray images. POPAR leverages the benefits of vision transformers and unique properties of medical imaging, aiming to simultaneously learn patch-wise high-level contextual features by correcting shuffled patch orders and fine-grained features by recovering patch appearance. We transfer POPAR pretrained models to diverse downstream tasks. The experiment results suggest that (1) POPAR outperforms state-of-the-art (SoTA) self-supervised models with vision transformer backbone; (2) POPAR achieves significantly better performance over all three SoTA contrastive learning methods; and (3) POPAR also outperforms fully-supervised pretrained models across architectures. In addition, our ablation study suggests that to achieve better performance on medical imaging tasks, both fine-grained and global contextual features are preferred. All code and models are available at GitHub.com/JLiangLab/POPAR. Keywords Vision transformer Self-supervised learning Medical image analysis Transfer learning
- 15 September 2022
- Published by Springer Nature
- Vol. 13542, 12-22
Benchmarking and Boosting Transformers for Medical Image Classification
Visual transformers have recently gained popularity in the computer vision community as they began to outrank convolutional neural networks (CNNs) in one representative visual benchmark after another. However, the competition between visual transformers and CNNs in medical imaging is rarely studied, leaving many important questions unanswered. As the first step, we benchmark how well existing transformer variants that use various (supervised and self-supervised) pre-training methods perform against CNNs on a variety of medical classification tasks. Furthermore, given the data-hungry nature of transformers and the annotation-deficiency challenge of medical imaging, we present a practical approach for bridging the domain gap between photographic and medical images by utilizing unlabeled large-scale in-domain data. Our extensive empirical evaluations reveal the following insights in medical imaging: (1) good initialization is more crucial for transformer-based models than for CNNs, (2) self-supervised learning based on masked image modeling captures more generalizable representations than supervised models, and (3) assembling a larger-scale domain-specific dataset can better bridge the domain gap between photographic and medical images via self-supervised continuous pre-training. We hope this benchmark study can direct future research on applying transformers to medical imaging analysis. All codes and pre-trained models are available on our GitHub page https://github.com/JLiangLab/BenchmarkTransformers. Keywords Vision Transformer Transfer learning Domain-adaptive pre-training Benchmarking
- 15 September 2022
- Published by Springer Nature
- Vol. 13542, 12-22
Benchmarking and Boosting Transformers for Medical Image Classification
Visual transformers have recently gained popularity in the computer vision community as they began to outrank convolutional neural networks (CNNs) in one representative visual benchmark after another. However, the competition between visual transformers and CNNs in medical imaging is rarely studied, leaving many important questions unanswered. As the first step, we benchmark how well existing transformer variants that use various (supervised and self-supervised) pre-training methods perform against CNNs on a variety of medical classification tasks. Furthermore, given the data-hungry nature of transformers and the annotation-deficiency challenge of medical imaging, we present a practical approach for bridging the domain gap between photographic and medical images by utilizing unlabeled large-scale in-domain data. Our extensive empirical evaluations reveal the following insights in medical imaging: (1) good initialization is more crucial for transformer-based models than for CNNs, (2) self-supervised learning based on masked image modeling captures more generalizable representations than supervised models, and (3) assembling a larger-scale domain-specific dataset can better bridge the domain gap between photographic and medical images via self-supervised continuous pre-training. We hope this benchmark study can direct future research on applying transformers to medical imaging analysis. All codes and pre-trained models are available on our GitHub page https://github.com/JLiangLab/BenchmarkTransformers. Keywords Vision Transformer Transfer learning Domain-adaptive pre-training Benchmarking
- Top Cited Papers
- 30 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 40 (10) , 2857-2868
Transferable Visual Words: Exploiting the Semantics of Anatomical Patterns for Self-Supervised Learning
This paper introduces a new concept called “transferable visual words” (TransVW), aiming to achieve annotation efficiency for deep learning in medical image analysis. Medical imaging—focusing on particular parts of the body for defined clinical purposes—generates images of great similarity in anatomy across patients and yields sophisticated anatomical patterns across images, which are associated with rich semantics about human anatomy and which are natural visual words . We show that these visual words can be automatically harvested according to anatomical consistency via self-discovery, and that the self-discovered visual words can serve as strong yet free supervision signals for deep models to learn semantics-enriched generic image representation via self-supervision (self-classification and self-restoration). Our extensive experiments demonstrate the annotation efficiency of TransVW by offering higher performance and faster convergence with reduced annotation cost in several applications. Our TransVW has several important advantages, including (1) TransVW is a fully autodidactic scheme, which exploits the semantics of visual words for self-supervised learning, requiring no expert annotation; (2) visual word learning is an add-on strategy, which complements existing self-supervised methods, boosting their performance; and (3) the learned image representation is semantics-enriched models, which have proven to be more robust and generalizable, saving annotation efforts for a variety of applications through transfer learning. Our code, pre-trained models, and curated visual words are available at https://github.com/JLiangLab/TransVW .
- 30 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 40 (10) , 2857-2868
Top Cited PapersTransferable Visual Words: Exploiting the Semantics of Anatomical Patterns for Self-Supervised Learning
This paper introduces a new concept called “transferable visual words” (TransVW), aiming to achieve annotation efficiency for deep learning in medical image analysis. Medical imaging—focusing on particular parts of the body for defined clinical purposes—generates images of great similarity in anatomy across patients and yields sophisticated anatomical patterns across images, which are associated with rich semantics about human anatomy and which are natural visual words . We show that these visual words can be automatically harvested according to anatomical consistency via self-discovery, and that the self-discovered visual words can serve as strong yet free supervision signals for deep models to learn semantics-enriched generic image representation via self-supervision (self-classification and self-restoration). Our extensive experiments demonstrate the annotation efficiency of TransVW by offering higher performance and faster convergence with reduced annotation cost in several applications. Our TransVW has several important advantages, including (1) TransVW is a fully autodidactic scheme, which exploits the semantics of visual words for self-supervised learning, requiring no expert annotation; (2) visual word learning is an add-on strategy, which complements existing self-supervised methods, boosting their performance; and (3) the learned image representation is semantics-enriched models, which have proven to be more robust and generalizable, saving annotation efforts for a variety of applications through transfer learning. Our code, pre-trained models, and curated visual words are available at https://github.com/JLiangLab/TransVW .