Pritam Mukherjee
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
Pritam Mukherjee has a total of 108 co-authors. Here are the top co-authors by number of shared publications:
- Ronald M. Summers
Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Clinical Center, National Institutes of Health, Bethesda, USA
13 shared publications - Olivier Gevaert
Department of Biomedical Data Science Stanford University 94305 Stanford CA USA
8 shared publications - Benjamin Hou
Division of Intramural Research, National Library of Medicine, National Institutes of Health, Bethesda, USA
4 shared publications - Ricardo Bigolin Lanfredi
Scientific Computing and Imaging Institute University of Utah Salt Lake City UT USA
4 shared publications - Tejas Sudharshan Mathai
Radiology and Imaging Sciences, National Institutes of Health (NIH) Clinical Center, 10 Center Dr, Bldg 10, Rm 1C224, Bethesda, MD 20892
4 shared publications - Yan Zhuang
Icahn School of Medicine at Mount Sinai
4 shared publications
Latest Publications
- Open Access
- 10 November 2026
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 28, e81708
Labeling Clinical Notes With Large Language Models: Retrospective Benchmarking Study
Background: Clinical notes are rich sources of clinical information and are routinely used in clinical practice to infer past diagnoses and other comorbidities. Large language models (LLMs) may simplify the task by extracting this information from clinical notes. Objective: The study aims to evaluate the performance of state-of-the-art LLMs on the task of labeling English clinical notes. Methods: This institutional review board–approved retrospective study comprised 380 clinical notes obtained from 2 institutions in the United States. The notes were manually labeled for the presence or absence of 29 conditions (simplified Elixhauser Comorbidity Index) by 2 human readers—a radiology resident and a medical student under the supervision of a senior radiologist. Forty-six LLMs, including 4 closed-source commercial models from the GPT and Claude families, and 42 open-weights LLMs from the Llama (13 models) and the Qwen (29 models) families were used to label each note. The GPT-o3-mini-high reasoning model was used to parse the free-text model responses to binary yes/no answers. Using the manual labels as the reference standard, the recall, precision, and F 1 -scores for the models were evaluated. The effect of factors such as the length of the notes and the family, size, and release recency of the LLMs was analyzed using generalized linear models. Results: The top-performing LLMs included the GPT and Claude models, and the larger open-weights models included Llama 3 70B, Llama 3.1 70B, Llama 3.1 405B, Llama 3.3 70B, Qwen 1.5 72B, Qwen 1.5 110B, Qwen 2 72B, and Qwen 2 VL 72B, which achieved F 1 -scores above 70%. The most recent and higher-capacity releases of the LLMs have been improving mainly in their precision. The evaluation of 29 conditions showed a large variance in performance depending on the condition. Conclusions: In this evaluation with 46 LLMs, larger open-weights LLMs such as the Llama 3.3 70B performed on par with or better than the GPT and Claude models, achieving F 1 -scores above 70%. The performance of open-weights models improved significantly with model size and recency. These results suggest that locally run open-weights LLMs can be potentially used to label clinical notes.
- 10 November 2026
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 28, e81708
Open AccessLabeling Clinical Notes With Large Language Models: Retrospective Benchmarking Study
Background: Clinical notes are rich sources of clinical information and are routinely used in clinical practice to infer past diagnoses and other comorbidities. Large language models (LLMs) may simplify the task by extracting this information from clinical notes. Objective: The study aims to evaluate the performance of state-of-the-art LLMs on the task of labeling English clinical notes. Methods: This institutional review board–approved retrospective study comprised 380 clinical notes obtained from 2 institutions in the United States. The notes were manually labeled for the presence or absence of 29 conditions (simplified Elixhauser Comorbidity Index) by 2 human readers—a radiology resident and a medical student under the supervision of a senior radiologist. Forty-six LLMs, including 4 closed-source commercial models from the GPT and Claude families, and 42 open-weights LLMs from the Llama (13 models) and the Qwen (29 models) families were used to label each note. The GPT-o3-mini-high reasoning model was used to parse the free-text model responses to binary yes/no answers. Using the manual labels as the reference standard, the recall, precision, and F 1 -scores for the models were evaluated. The effect of factors such as the length of the notes and the family, size, and release recency of the LLMs was analyzed using generalized linear models. Results: The top-performing LLMs included the GPT and Claude models, and the larger open-weights models included Llama 3 70B, Llama 3.1 70B, Llama 3.1 405B, Llama 3.3 70B, Qwen 1.5 72B, Qwen 1.5 110B, Qwen 2 72B, and Qwen 2 VL 72B, which achieved F 1 -scores above 70%. The most recent and higher-capacity releases of the LLMs have been improving mainly in their precision. The evaluation of 29 conditions showed a large variance in performance depending on the condition. Conclusions: In this evaluation with 46 LLMs, larger open-weights LLMs such as the Llama 3.3 70B performed on par with or better than the GPT and Claude models, achieving F 1 -scores above 70%. The performance of open-weights models improved significantly with model size and recency. These results suggest that locally run open-weights LLMs can be potentially used to label clinical notes.
- 1 March 2026
- Published by Radiological Society of North America (RSNA) in Radiology: Imaging Cancer
- Vol. 8 (2) , e260046
Deep Learning–based Detection of Colorectal Liver Metastases: Performance, Robustness, and Clinical Implications
- 1 March 2026
- Published by Radiological Society of North America (RSNA) in Radiology: Imaging Cancer
- Vol. 8 (2) , e260046
Deep Learning–based Detection of Colorectal Liver Metastases: Performance, Robustness, and Clinical Implications
- 20 September 2025
- Published by Springer Nature
- p. 316-326
LEAVS: An LLM-Based Labeler for Abdominal CT Supervision
Extracting structured labels from radiology reports has been employed to create vision models that detect several types of abnormalities simultaneously. However, existing works focus mainly on the chest region. Few works have investigated abdominal radiology reports due to the more complex anatomy and a wider range of pathologies in the abdomen. We propose LEAVS (Large language model Extractor for Abdominal Vision Supervision). This labeler can annotate the certainty of presence and the urgency of seven types of abnormalities for nine abdominal organs on CT radiology reports. To ensure broad coverage, we chose abnormalities that encompass most of the finding types from CT reports. Our approach employs a specialized chain-of-thought prompting strategy for a locally run LLM using sentence extraction and multiple-choice questions in a tree-based decision system. We demonstrate that the LLM can extract several abnormality types across abdominal organs with an average F1 score of 0.89, significantly outperforming competing labelers and humans. Additionally, we show that the extraction of urgency labels achieves performance comparable to that of human annotations. Finally, we demonstrate that the abnormality labels contain valuable information for training a vision model that classifies several organs as normal or abnormal. We release our code and structured annotations for a publicly available dataset containing over 1,000 CT volumes.
- 20 September 2025
- Published by Springer Nature
- p. 316-326
LEAVS: An LLM-Based Labeler for Abdominal CT Supervision
Extracting structured labels from radiology reports has been employed to create vision models that detect several types of abnormalities simultaneously. However, existing works focus mainly on the chest region. Few works have investigated abdominal radiology reports due to the more complex anatomy and a wider range of pathologies in the abdomen. We propose LEAVS (Large language model Extractor for Abdominal Vision Supervision). This labeler can annotate the certainty of presence and the urgency of seven types of abnormalities for nine abdominal organs on CT radiology reports. To ensure broad coverage, we chose abnormalities that encompass most of the finding types from CT reports. Our approach employs a specialized chain-of-thought prompting strategy for a locally run LLM using sentence extraction and multiple-choice questions in a tree-based decision system. We demonstrate that the LLM can extract several abnormality types across abdominal organs with an average F1 score of 0.89, significantly outperforming competing labelers and humans. Additionally, we show that the extraction of urgency labels achieves performance comparable to that of human annotations. Finally, we demonstrate that the abnormality labels contain valuable information for training a vision model that classifies several organs as normal or abnormal. We release our code and structured annotations for a publicly available dataset containing over 1,000 CT volumes.
- 1 August 2025
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 316 (2) , e250617
One Year On: Assessing Progress of Multimodal Large Language Model Performance on RSNA 2024 Case of the Day Questions
Multimodal large language models have significantly improved in assessing RSNA Case of the Day Questions over the past year, with OpenAI’s latest models outperforming those from Google and Meta; notably, OpenAI o1 had an accuracy comparable to expert radiologists.
- 1 August 2025
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 316 (2) , e250617
One Year On: Assessing Progress of Multimodal Large Language Model Performance on RSNA 2024 Case of the Day Questions
Multimodal large language models have significantly improved in assessing RSNA Case of the Day Questions over the past year, with OpenAI’s latest models outperforming those from Google and Meta; notably, OpenAI o1 had an accuracy comparable to expert radiologists.
- Open Access
- 1 July 2025
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 20 (9) , 1-10
Improved muscle and fat segmentation for body composition measures on quantitative CT
Purpose: Body composition analysis on abdominal CT scans is useful for opportunistic screening. It also offers prognostic insights into mortality and cardiovascular risk. However, current segmentation methods for muscle and fat often fail on quantitative CT scans used for bone densitometry. These scans are commonly used to diagnose and monitor osteoporosis. This study aims to develop an accurate segmentation method for such scans and compare its performance with existing methods. Methods: We applied an nnU-Net framework to segment muscle, subcutaneous fat, visceral fat, and an added ‘body’ class for other non-background voxels. Training data included CT scans with bone densitometry phantoms, with segmentation annotations generated using our previous segmentation method followed by manual refinement. The proposed method was evaluated on 980 CT scans across two internal and external datasets, including 30 CT scans with phantoms in internal and external datasets (15 scans in each). Comparison was made with TotalSegmentator and our previous approach. Results: The proposed method achieved the highest accuracy for muscle and subcutaneous fat segmentation across all four datasets ( $$p<0.05$$ ) and delivered comparable accuracy for visceral fat. In comparison with TotalSegmentator and the previous method, there were no false segmentations in the densitometry phantom included within the display field-of-view of the patient scan. Conclusion: Experimental results showed that the proposed method improved segmentation accuracy for muscle and subcutaneous fat while maintaining high accuracy for visceral fat. Notably, segmentation accuracy was also high in the quantitative CT scans for bone densitometry. These findings highlight the potential of the method to advance body composition analysis in clinical practice.- 1 July 2025
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 20 (9) , 1-10
Open AccessImproved muscle and fat segmentation for body composition measures on quantitative CT
Purpose: Body composition analysis on abdominal CT scans is useful for opportunistic screening. It also offers prognostic insights into mortality and cardiovascular risk. However, current segmentation methods for muscle and fat often fail on quantitative CT scans used for bone densitometry. These scans are commonly used to diagnose and monitor osteoporosis. This study aims to develop an accurate segmentation method for such scans and compare its performance with existing methods. Methods: We applied an nnU-Net framework to segment muscle, subcutaneous fat, visceral fat, and an added ‘body’ class for other non-background voxels. Training data included CT scans with bone densitometry phantoms, with segmentation annotations generated using our previous segmentation method followed by manual refinement. The proposed method was evaluated on 980 CT scans across two internal and external datasets, including 30 CT scans with phantoms in internal and external datasets (15 scans in each). Comparison was made with TotalSegmentator and our previous approach. Results: The proposed method achieved the highest accuracy for muscle and subcutaneous fat segmentation across all four datasets ( $$p<0.05$$ ) and delivered comparable accuracy for visceral fat. In comparison with TotalSegmentator and the previous method, there were no false segmentations in the densitometry phantom included within the display field-of-view of the patient scan. Conclusion: Experimental results showed that the proposed method improved segmentation accuracy for muscle and subcutaneous fat while maintaining high accuracy for visceral fat. Notably, segmentation accuracy was also high in the quantitative CT scans for bone densitometry. These findings highlight the potential of the method to advance body composition analysis in clinical practice. - Open Access
- 25 June 2025
- Published by Elsevier in Journal of Biomedical Informatics
- Vol. 168, 104864
How well do multimodal LLMs interpret CT scans? An auto-evaluation framework for analyses
- 25 June 2025
- Published by Elsevier in Journal of Biomedical Informatics
- Vol. 168, 104864
Open AccessHow well do multimodal LLMs interpret CT scans? An auto-evaluation framework for analyses
- 4 April 2025
- Published by SPIE-Intl Soc Optical Eng
- Vol. 13407, 51-349
Leveraging anatomical priors for automated pancreas segmentation on abdominal CT
An accurate segmentation of the pancreas on CT is crucial to identify pancreatic pathologies and extract imaging-based biomarkers. However, prior research on pancreas segmentation has primarily focused on modifying the segmentation model architecture or utilizing pre- and post-processing techniques. In this article, we investigate the utility of anatomical priors to enhance the segmentation performance of the pancreas. Two 3D full-resolution nnU-Net models were trained, one with 8 refined labels from the public PANORAMA dataset, and another that combined them with labels derived from the public TotalSegmentator (TS) tool. The addition of anatomical priors resulted in a 6% increase in Dice score (p < .001) and a 36.5 mm decrease in Hausdorff distance for pancreas segmentation (p < .001). Moreover, the pancreas was always detected when anatomy priors were used, whereas there were 8 instances of failed detections without their use. The use of anatomy priors shows promise for pancreas segmentation and subsequent derivation of imaging biomarkers.
- 4 April 2025
- Published by SPIE-Intl Soc Optical Eng
- Vol. 13407, 51-349
Leveraging anatomical priors for automated pancreas segmentation on abdominal CT
An accurate segmentation of the pancreas on CT is crucial to identify pancreatic pathologies and extract imaging-based biomarkers. However, prior research on pancreas segmentation has primarily focused on modifying the segmentation model architecture or utilizing pre- and post-processing techniques. In this article, we investigate the utility of anatomical priors to enhance the segmentation performance of the pancreas. Two 3D full-resolution nnU-Net models were trained, one with 8 refined labels from the public PANORAMA dataset, and another that combined them with labels derived from the public TotalSegmentator (TS) tool. The addition of anatomical priors resulted in a 6% increase in Dice score (p < .001) and a 36.5 mm decrease in Hausdorff distance for pancreas segmentation (p < .001). Moreover, the pancreas was always detected when anatomy priors were used, whereas there were 8 instances of failed detections without their use. The use of anatomy priors shows promise for pancreas segmentation and subsequent derivation of imaging biomarkers.
- 1 April 2025
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 315 (1) , e241979
MRISegmenter: A Fully Accurate and Robust Automated Multiorgan and Structure Segmentation Tool for T1-weighted Abdominal MRI
MRISegmenter provided accurate and robust segmentation of 62 organs and structures, including 15 main organs, seven vessels, eight muscles, and 32 bones at T1-weighted abdominal MRI.
- 1 April 2025
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 315 (1) , e241979
MRISegmenter: A Fully Accurate and Robust Automated Multiorgan and Structure Segmentation Tool for T1-weighted Abdominal MRI
MRISegmenter provided accurate and robust segmentation of 62 organs and structures, including 15 main organs, seven vessels, eight muscles, and 32 bones at T1-weighted abdominal MRI.
- 23 March 2025
- Published by Elsevier in Academic Radiology
- Vol. 32 (7) , 4013-4021
Assessing the Reliability of Pancreatic CT Imaging Biomarkers for Diabetes Prediction: A Dual Center Retrospective Study
- 23 March 2025
- Published by Elsevier in Academic Radiology
- Vol. 32 (7) , 4013-4021
Assessing the Reliability of Pancreatic CT Imaging Biomarkers for Diabetes Prediction: A Dual Center Retrospective Study
- 10 November 2024
- Published by Elsevier in Medical Image Analysis
- Vol. 99, 103383
Enhancing chest X-ray datasets with privacy-preserving large language models and multi-type annotations: A data-driven approach for improved classification
- 10 November 2024
- Published by Elsevier in Medical Image Analysis
- Vol. 99, 103383
Enhancing chest X-ray datasets with privacy-preserving large language models and multi-type annotations: A data-driven approach for improved classification