Suprosanna Shit
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Suprosanna Shit has a total of 702 co-authors. Here are the top co-authors by number of shared publications:
- Bjoern Menze
Department of Quantitative Biomedicine, University of Zurich, Zurich, Switzerland
18 shared publications - Hongwei Li
Department of Diagnostic Radiology, National University of Singapore, Singapore, Singapore
12 shared publications - Daniel Rueckert
Technical University of Munich
11 shared publications - Benedikt Wiestler
Technical University of Munich
10 shared publications - Ivan Ezhov
Department of Informatics, Technical University of Munich, Munich, Germany
8 shared publications - Johannes Christian Paetzold
Weill Cornell Medicine
8 shared publications
Latest Publications
- Open Access
- 28 October 2026
- Published by Springer Nature in Nature Communications
CADS: a comprehensive anatomical dataset and segmentation for whole-body anatomy in computed tomography
Volumetric computed tomography (CT) segmentation supports quantitative image analysis, but most AI-based methods remain organ-specific, with fragmented models, inconsistent label definitions, and heterogeneous training and evaluation protocols. Here we present CADS, a unified data–model framework for scalable and generalizable whole-body CT segmentation. We construct a SNOMED-CT-referenced anatomical label space harmonizing heterogeneous cohorts from over 100 imaging centers, yielding complete annotations of 167 structures across 22,022 CT volumes and markedly expanding anatomical coverage and scale beyond existing resources. To complete labels on sparsely annotated CTs, we combine self-training with shape-informed quality control based on neural implicit functions, curating high-quality pseudo-labels. Trained on this resource, CADS shows robust whole-body segmentation across distribution shifts and improved performance relative to state-of-the-art approaches across 18 public datasets. We further validate it in an independent, expert-reviewed real-world oncology cohort of 2864 CTs. The curated dataset, pretrained models, and user-friendly software together provide an accessible, reproducible foundation for large-scale anatomical segmentation and computational anatomy research.
- 28 October 2026
- Published by Springer Nature in Nature Communications
Open AccessCADS: a comprehensive anatomical dataset and segmentation for whole-body anatomy in computed tomography
Volumetric computed tomography (CT) segmentation supports quantitative image analysis, but most AI-based methods remain organ-specific, with fragmented models, inconsistent label definitions, and heterogeneous training and evaluation protocols. Here we present CADS, a unified data–model framework for scalable and generalizable whole-body CT segmentation. We construct a SNOMED-CT-referenced anatomical label space harmonizing heterogeneous cohorts from over 100 imaging centers, yielding complete annotations of 167 structures across 22,022 CT volumes and markedly expanding anatomical coverage and scale beyond existing resources. To complete labels on sparsely annotated CTs, we combine self-training with shape-informed quality control based on neural implicit functions, curating high-quality pseudo-labels. Trained on this resource, CADS shows robust whole-body segmentation across distribution shifts and improved performance relative to state-of-the-art approaches across 18 public datasets. We further validate it in an independent, expert-reviewed real-world oncology cohort of 2864 CTs. The curated dataset, pretrained models, and user-friendly software together provide an accessible, reproducible foundation for large-scale anatomical segmentation and computational anatomy research.
- 2 October 2026
- Published by Springer Nature
- p. 131-149
VesselTok: Tokenizing Vessel-Like 3D Biomedical Graph Representations for Reconstruction and Generation
- 2 October 2026
- Published by Springer Nature
- p. 131-149
VesselTok: Tokenizing Vessel-Like 3D Biomedical Graph Representations for Reconstruction and Generation
- 25 September 2026
- Published by Springer Nature
- p. 122-132
CTTok: Voxel-Abulary for Autoregressive 3D CT Volume Generation with Large Language Models
- 25 September 2026
- Published by Springer Nature
- p. 122-132
CTTok: Voxel-Abulary for Autoregressive 3D CT Volume Generation with Large Language Models
- 23 July 2026
- Published by Massachusetts Medical Society in NEJM AI
- Vol. 3 (8)
The TopCoW Challenge — Topology-Aware Circle of Willis Segmentation for CT and MR Angiography
- 23 July 2026
- Published by Massachusetts Medical Society in NEJM AI
- Vol. 3 (8)
The TopCoW Challenge — Topology-Aware Circle of Willis Segmentation for CT and MR Angiography
- Open Access
VariViT: A Vision Transformer for Variable Image Sizes
Vision Transformers (ViTs) have emerged as the state-of-the-art architecture in representation learning, leveraging self-attention mechanisms to excel in various tasks. ViTs split images into fixed-size patches, constraining them to a predefined size and necessitating pre-processing steps like resizing, padding, or cropping. This poses challenges in medical imaging, particularly with irregularly shaped structures like tumors. A fixed bounding box crop size produces input images with highly variable foreground-to-background ratios. Resizing medical images can degrade information and introduce artefacts, impacting diagnosis. Hence, tailoring variable-sized crops to regions of interest can enhance feature representation capabilities. Moreover, large images are computationally expensive, and smaller sizes risk information loss, presenting a computation-accuracy tradeoff. We propose VariViT, an improved ViT model crafted to handle variable image sizes while maintaining a consistent patch size. VariViT employs a novel positional embedding resizing scheme for a variable number of patches. We also implement a new batching strategy within VariViT to reduce computational complexity, resulting in faster training and inference times. In our evaluations on two 3D brain MRI datasets, VariViT surpasses vanilla ViTs and ResNet in glioma genotype prediction and brain tumor classification. It achieves F1-scores of 75.5% and 76.3%, respectively, learning more discriminative features. Our proposed batching strategy reduces computation time by up to 30% compared to conventional architectures. These findings underscore the efficacy of VariViT in image representation learning. Our code can be found here: https://github.com/Aswathi-Varma/varivit
Open AccessVariViT: A Vision Transformer for Variable Image Sizes
Vision Transformers (ViTs) have emerged as the state-of-the-art architecture in representation learning, leveraging self-attention mechanisms to excel in various tasks. ViTs split images into fixed-size patches, constraining them to a predefined size and necessitating pre-processing steps like resizing, padding, or cropping. This poses challenges in medical imaging, particularly with irregularly shaped structures like tumors. A fixed bounding box crop size produces input images with highly variable foreground-to-background ratios. Resizing medical images can degrade information and introduce artefacts, impacting diagnosis. Hence, tailoring variable-sized crops to regions of interest can enhance feature representation capabilities. Moreover, large images are computationally expensive, and smaller sizes risk information loss, presenting a computation-accuracy tradeoff. We propose VariViT, an improved ViT model crafted to handle variable image sizes while maintaining a consistent patch size. VariViT employs a novel positional embedding resizing scheme for a variable number of patches. We also implement a new batching strategy within VariViT to reduce computational complexity, resulting in faster training and inference times. In our evaluations on two 3D brain MRI datasets, VariViT surpasses vanilla ViTs and ResNet in glioma genotype prediction and brain tumor classification. It achieves F1-scores of 75.5% and 76.3%, respectively, learning more discriminative features. Our proposed batching strategy reduces computation time by up to 30% compared to conventional architectures. These findings underscore the efficacy of VariViT in image representation learning. Our code can be found here: https://github.com/Aswathi-Varma/varivit
- Top Cited PapersOpen Access
- 12 February 2026
- Published by Springer Nature in Nature Biomedical Engineering
- Vol. 10 (8) , 1610-1628
Generalist foundation models from a multimodal dataset for 3D computed tomography
Advancements in medical imaging AI, particularly in 3D imaging, have been limited due to the scarcity of comprehensive datasets. We introduce CT-RATE, a public dataset that pairs 3D medical images with corresponding textual reports. CT-RATE comprises 25,692 non-contrast 3D chest CT scans from 21,304 unique patients. Each scan is accompanied by its corresponding radiology report. Leveraging CT-RATE, we develop CT-CLIP, a CT-focused contrastive language–image pretraining framework designed for broad applications without the need for task-specific training. We demonstrate how CT-CLIP can be used in multi-abnormality detection and case retrieval, and outperforms state-of-the-art fully supervised models across all key metrics. By combining CT-CLIP’s vision encoder with a pretrained large language model, we create CT-CHAT, a vision–language foundational chat model for 3D chest CT volumes. Fine-tuned on over 2.7 million question–answer pairs derived from the CT-RATE dataset, CT-CHAT underscores the necessity for specialized methods in 3D medical imaging. Collectively, the open-source release of CT-RATE, CT-CLIP and CT-CHAT not only addresses critical challenges in 3D medical imaging but also lays the groundwork for future innovations in medical AI and improved patient care.
- 12 February 2026
- Published by Springer Nature in Nature Biomedical Engineering
- Vol. 10 (8) , 1610-1628
Top Cited PapersOpen AccessGeneralist foundation models from a multimodal dataset for 3D computed tomography
Advancements in medical imaging AI, particularly in 3D imaging, have been limited due to the scarcity of comprehensive datasets. We introduce CT-RATE, a public dataset that pairs 3D medical images with corresponding textual reports. CT-RATE comprises 25,692 non-contrast 3D chest CT scans from 21,304 unique patients. Each scan is accompanied by its corresponding radiology report. Leveraging CT-RATE, we develop CT-CLIP, a CT-focused contrastive language–image pretraining framework designed for broad applications without the need for task-specific training. We demonstrate how CT-CLIP can be used in multi-abnormality detection and case retrieval, and outperforms state-of-the-art fully supervised models across all key metrics. By combining CT-CLIP’s vision encoder with a pretrained large language model, we create CT-CHAT, a vision–language foundational chat model for 3D chest CT volumes. Fine-tuned on over 2.7 million question–answer pairs derived from the CT-RATE dataset, CT-CHAT underscores the necessity for specialized methods in 3D medical imaging. Collectively, the open-source release of CT-RATE, CT-CLIP and CT-CHAT not only addresses critical challenges in 3D medical imaging but also lays the groundwork for future innovations in medical AI and improved patient care.
- 19 September 2025
- Published by Springer Nature
- p. 594-604
Semantically Consistent Discrete Diffusion for 3D Biological Graph Modeling
- 19 September 2025
- Published by Springer Nature
- p. 594-604
Semantically Consistent Discrete Diffusion for 3D Biological Graph Modeling
- Open Access
- 11 August 2025
- Published by Elsevier in Medical Image Analysis
- Vol. 106, 103756
Towards cardiac MRI foundation models: Comprehensive visual-tabular representations for whole-heart assessment and beyond
- 11 August 2025
- Published by Elsevier in Medical Image Analysis
- Vol. 106, 103756
Open AccessTowards cardiac MRI foundation models: Comprehensive visual-tabular representations for whole-heart assessment and beyond
- Open Access
- 9 August 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 7357
DeepISLES: a clinically validated ischemic stroke segmentation model from the ISLES'22 challenge
Diffusion-weighted MRI is critical for diagnosing and managing ischemic stroke, but variability in images and disease presentation limits the generalizability of AI algorithms. We present DeepISLES, a robust ensemble algorithm developed from top submissions to the 2022 Ischemic Stroke Lesion Segmentation challenge we organized. By combining the strengths of best-performing methods from leading research groups, DeepISLES achieves superior accuracy in detecting and segmenting ischemic lesions, generalizing well across diverse axes. Validation on a large external dataset (N = 1685) confirms its robustness, outperforming previous state-of-the-art models by 7.4% in Dice score and 12.6% in F1 score. It also excels at extracting clinical biomarkers and correlates strongly with clinical stroke scores, closely matching expert performance. Neuroradiologists prefer DeepISLES’ segmentations over manual annotations in a Turing-like test. Our work demonstrates DeepISLES’ clinical relevance and highlights the value of biomedical challenges in developing real-world, generalizable AI tools. DeepISLES is freely available at https://github.com/ezequieldlrosa/DeepIsles.
- 9 August 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 7357
Open AccessDeepISLES: a clinically validated ischemic stroke segmentation model from the ISLES'22 challenge
Diffusion-weighted MRI is critical for diagnosing and managing ischemic stroke, but variability in images and disease presentation limits the generalizability of AI algorithms. We present DeepISLES, a robust ensemble algorithm developed from top submissions to the 2022 Ischemic Stroke Lesion Segmentation challenge we organized. By combining the strengths of best-performing methods from leading research groups, DeepISLES achieves superior accuracy in detecting and segmenting ischemic lesions, generalizing well across diverse axes. Validation on a large external dataset (N = 1685) confirms its robustness, outperforming previous state-of-the-art models by 7.4% in Dice score and 12.6% in F1 score. It also excels at extracting clinical biomarkers and correlates strongly with clinical stroke scores, closely matching expert performance. Neuroradiologists prefer DeepISLES’ segmentations over manual annotations in a Turing-like test. Our work demonstrates DeepISLES’ clinical relevance and highlights the value of biomedical challenges in developing real-world, generalizable AI tools. DeepISLES is freely available at https://github.com/ezequieldlrosa/DeepIsles.
- Top Cited PapersOpen Access
- 8 July 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-20
Towards fair decentralized benchmarking of healthcare AI algorithms with the Federated Tumor Segmentation (FeTS) challenge
Computational competitions are the standard for benchmarking medical image analysis algorithms, but they typically use small curated test datasets acquired at a few centers, leaving a gap to the reality of diverse multicentric patient data. To this end, the Federated Tumor Segmentation (FeTS) Challenge represents the paradigm for real-world algorithmic performance evaluation. The FeTS challenge is a competition to benchmark (i) federated learning aggregation algorithms and (ii) state-of-the-art segmentation algorithms, across multiple international sites. Weight aggregation and client selection techniques were compared using a multicentric brain tumor dataset in realistic federated learning simulations, yielding benefits for adaptive weight aggregation, and efficiency gains through client sampling. Quantitative performance evaluation of state-of-the-art segmentation algorithms on data distributed internationally across 32 institutions yielded good generalization on average, albeit the worst-case performance revealed data-specific modes of failure. Similar multi-site setups can help validate the real-world utility of healthcare AI algorithms in the future.
- 8 July 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-20
Top Cited PapersOpen AccessTowards fair decentralized benchmarking of healthcare AI algorithms with the Federated Tumor Segmentation (FeTS) challenge
Computational competitions are the standard for benchmarking medical image analysis algorithms, but they typically use small curated test datasets acquired at a few centers, leaving a gap to the reality of diverse multicentric patient data. To this end, the Federated Tumor Segmentation (FeTS) Challenge represents the paradigm for real-world algorithmic performance evaluation. The FeTS challenge is a competition to benchmark (i) federated learning aggregation algorithms and (ii) state-of-the-art segmentation algorithms, across multiple international sites. Weight aggregation and client selection techniques were compared using a multicentric brain tumor dataset in realistic federated learning simulations, yielding benefits for adaptive weight aggregation, and efficiency gains through client sampling. Quantitative performance evaluation of state-of-the-art segmentation algorithms on data distributed internationally across 32 institutions yielded good generalization on average, albeit the worst-case performance revealed data-specific modes of failure. Similar multi-site setups can help validate the real-world utility of healthcare AI algorithms in the future.