Spotlight

Papers

Field

Top tools here

Open problems in Medical image segmentation

Lack of benchmarks for evidence-seeking in longitudinal medical reasoning1 paper raises it · 1 addresses it
Current benchmarks test reasoning over preselected evidence rather than the ability to autonomously seek and integrate evidence across clinical records and longitudinal imaging.
- From Given to Gathered Evidence: Agentic Learning for Longitudinal Medical Reasoningraises · addresses
Handling incidental information in clinical documentation and reasoning1 paper raises it · 1 addresses it
Models often misattribute or use irrelevant background information, leading to contamination in clinical notes and reasoning.
- Large language models are vulnerable to incidental information in clinical documentation and reasoningraises · addresses
Mismatch between benchmark evaluations and real-world clinician use1 paper raises it · 1 addresses it
Benchmarks do not reflect the actual tasks and queries clinicians perform, limiting their predictive value for deployment performance.
- Clinician use of language models diverges from how the models are evaluatedraises · addresses
Generating coherent whole-slide histopathology images at gigapixel scale1 paper raises it · 1 addresses it
Existing generative models operate at patch scale, while clinical supervision and labels exist at the whole-slide level, creating a gap in fidelity and usability.
- BigCell: Generating Gigapixel Whole-Slide Imagesraises · addresses
Learning from deployment experience without retraining frozen models1 paper raises it · 1 addresses it
Frozen models cannot adapt to new clinical evidence or updated guidelines, limiting their long-term utility in evolving medical practice.
- Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AIraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Recently funded

Topics in this field

medical image segmentation · tumor segmentation · brain mri279 papers30 this week
clinical reasoning · question answering · large language models234 papers29 this week
pathology foundation models · instance learning · multiple instance learning145 papers23 this week
health records · cohorts · electronic health records115 papers11 this week
radiology report generation · radiology reports · radiology report69 papers11 this week
radiology report generation · radiology reports · medical vision language59 papers10 this week

Topics in this field

Active contributors · 90 days

Nassir NavabThe Value of System 1 Models in Medicine8
Jian WangOverview of CHIP 2026 Shared Task 1: Patient-Specific Phenotype Concept Recognition in Full-Text Biomedical Literature6
Yang YangPatient, Place, Prior (P$^3$): What Counts as Personalization in Medical World Models?6
Dimitris K. IakovidisCross-dataset harmonization for robust endoscopic image analysis6
Wenxuan LiDiagnostic Loss: Asymmetric Supervision for Radiology Report Generation5
Zongwei ZhouDiagnostic Loss: Asymmetric Supervision for Radiology Report Generation5

Active contributors

Activity · 12 weeks

Activity

★ Spotlight this month

arXiv cs.CVOct 15

MedPAO-VL: Interpretable and Protocol-Compliant Agent for Structured Radiology Report Generation

Shrish Shrinath Vaidya, Gowthamaan Palani, Minmini Selvam, Gokulraja Srinivasaraja, Ganapathy Krishnamurthi

Despite the remarkable generalization capabilities of Large Language Models, generating clinically accurate and structured radiology reports from medical images remains a significant challenge. Current end-to-end approaches function as black boxes, prone to factual hallucinations and generating ungrounded findings. This lack of reliability and failure to adhere to domain-specific structuring protocols, fundamentally limits their clinical utility. We present MedPAO-VL, a multimodal agent that shifts the paradigm from monolithic generation to explainable, iterative, protocol-compliant structured report generation. Unlike deterministic models, our plan-act-observe loop functions as a goal-oriented agent: it first perceives the Chest X-Ray through an explainable vision module designed to capture inherent diagnostic uncertainty, then iteratively refines the generated report by observing semantic discrepancies and self-correcting its generation for better alignment with visually detected clinical findings. Evaluation of our framework demonstrates that this agentic reasoning improves clinical correctness and completeness, achieving an expert-rated accuracy score of 3.5/5 and a…

PDF arXiv page Details

Spotlight

Recent papers

All papers in Research

arXiv cs.CLOct 22
How Ground Truth Shapes Retrieval Scores: Evidence-Aware Evaluation of a Retrieval-Augmented Generation System for Breast Lesions
Miguel Mochizuki Silva, Samuel Ismael, Mateus C. Dias, Thaís Gaudêncio, Yuri Malheiros +1
Purpose: To describe an evidence-aware retrieval evaluation protocol for a clinical retrieval-augmented generation (RAG) system over breast lesion management literature, addressing the dependence of retrieval scores on annotation coverage. Methods: An 18-document corpus and an 18-query development benchmark, with one Yes/No or WH-question per document, were used. Retrieval combined dense embeddings, BM25, and cross-encoder reranking. Chunk sizes of 128 to 1024 tokens, overlaps of 0 to 20%, and four retriever configurations were evaluated. Relevance was defined by evidence spans mapped to all containing chunks, treating overlapping chunks with equivalent evidence as relevant. Retrieval was evaluated using R-Precision, Recall@K, MRR, and nDCG@K. Separately, generation was assessed on a 512-token index at K=1 to 5 using DeepEval claim-level metrics, with deepseek-v4-pro as the LLM judge, and BLEU/ROUGE metrics. Results: The selected hybrid retriever, using 384-token chunks and 20% overlap, retrieved accepted evidence in the top three results for 17 of 18 queries. Recall@3, R-Precision, MRR@3, and nDCG@3 each reached 0.94. Ground-truth curation increased evidence spans from 25 to 37…
PDF arXiv
arXiv cs.CLOct 22
Would an LLM Match into a Residency? Uncertainty, Reasoning and Image Use of Open Language Models on the Spanish MIR Examination
Miguel Fernandez-de-Retana, Unai Zulaika, Ruben Sanchez-Corcuera, Aritz Bilbao-Jayo, Aitor Almeida
Accuracy on medical examinations is common evidence offered for the clinical use of language models, yet a health system that intends to run an open model on its own hardware needs to know considerably more: whether the model recognizes when it is likely to be wrong, whether medical fine-tuning improves this ability, whether its correct answers rest on sound clinical reasoning, or whether it actually uses the images it is given. We examine these questions for four open models of 8 to 27 billion parameters on the Spanish MIR residency examination, scoring 1,552 questions from eight editions under the exam's own rules. Answering every question, the three larger models would rank among roughly the first 600 to 3,000 candidates, with 41 to 43 specialties still open to them. Abstention, however, never pays, because even their least confident answers are right more often than the 25% break-even. Medical fine-tuning reduced overconfidence at the cost of accuracy, without improving how well confidence separates right from wrong answers. Moreover, 13-38% of correct answers rejected a distractor for a clinically unsound reason that confidence did not reflect, and removing or swapping the…
PDF arXiv
arXiv cs.CVOct 22
Diffusion-Based Synthesis of Complete 3D Biparametric Prostate MRI
Claudia Giardina, Montse Pardàs, Verónica Vilaplana
Synthetic biparametric MRI (bpMRI) may help alleviate the limited availability of large and representative prostate MRI datasets for deep learning applications. In this work, we present a conditional 3D diffusion framework for anatomy-conditioned synthesis of complete prostate bpMRI from anatomical masks. The framework supports sequential synthesis, in which T2w and diffusion modalities are generated by separately trained models, and joint synthesis, in which all bpMRI modalities are generated simultaneously within a single model. Five configurations were trained using PI-CAI, FastMRI Prostate, and PROSTATEx datasets to investigate different conditioning schemes, target modalities, and synthesis strategies. Evaluation using distribution-based metrics, paired-image similarity, and qualitative assessment demonstrated the feasibility of both synthesis pathways. Joint synthesis achieved competitive distributional fidelity while generating complete bpMRI, whereas direct synthesis of ADC and computed high-b-value DWI outperformed their derivation from synthetic diffusion-weighted images.
PDF arXiv
arXiv cs.AIOct 22
From Prompt Rules to Golden Data Model: Production-Scale Generation of Personalized, Compliant Pharmaceutical Claims
Suyash Mishra, Qiang Li, Subhabrata Adak, Upender Phogat, Srikanth Patil +1
Large language models (LLMs) are increasingly used to generate domain-specific commercial & medical content (e.g., claims, statements, and promotional phrases) in regulated industries such as pharmaceuticals. However, ensuring its regulatory compliance, factual accuracy, and audience-specific personalization remains a major challenge. We report a production case study asking whether moving compliance and personalization signal from prompt-level rules into retrieval time structured context improves pharmaceutical claims generation, using Composer, a deployed internal tool built on a Golden Data Model (GDM) of 1,867 pharmaceutical claims spanning four products. The GDM integrates claim metadata, references, audience labels, material type, usage history, Match Text Variant (MTV) links, and a six dimension quality score (6C). Across six product-audience segments, the context pipeline improves intended indication (+29%), intended content type (+62%) and intended target audience (+67%), 6C quality score (+86%), and claim reuse (+34%). Production log analysis over the deployment period shows a 29.5% reduction in weekly API cost. We report this as descriptive deployment evidence. This…
PDF arXiv
arXiv cs.CVOct 22
Evaluation of Uncertainty-Aware Multi-Software Ensembles for Hippocampal Segmentation
Gabriel Oliveira-Stahl, Anna Schroder, James Moggridge, Hamza A. Salhab, Caroline Micallef +4
Accurate hippocampal segmentation can be a useful tool for diagnosing and monitoring neurological conditions such as Alzheimer's disease and epilepsy. While numerous automated segmentation methods exist, their clinical adoption remains limited. Reliable uncertainty assessment can enhance trust and facilitate clinical translation. This study evaluates ensembles of five heterogeneous hippocampal segmentation methods - InnerEye, ASHS, FastSurfer, HippoSeg, and FreeSurfer - across two dementia datasets and one epilepsy dataset. The sub-ensemble containing InnerEye, FastSurfer, and HippoSeg emerged as both accurate and efficient, highlighting the feasibility of balancing computational cost and performance. Additionally, ensemble-derived uncertainty quantification with sample variance, mutual information, and predictive entropy is shown to reduce inaccurate segmentations by flagging low-confidence cases, potentially providing a mechanism for automatically escalating ambiguous cases for expert assessment. Lastly, this study explores the downstream clinical utility of ensemble-derived uncertainty, finding a significant correlation with motion artefact severity and a modest contribution…
PDF arXiv
arXiv cs.CLOct 22
From Structured Records to Patient Narratives: Preserving Clinical Alignment in LLM-Generated Health Summaries
Bayram Ayadi, Florian Geissler, Johanna Schmidhuber
As wearable and digital health systems increasingly generate longitudinal physiological records, communicating these observations in patient-accessible language remains a significant challenge. Large Language Models (LLMs) offer a promising mechanism for translating structured clinical information into readable narratives, but this process may introduce semantic drift, where clinically precise meaning is distorted during simplification. We investigate evidence-grounded health summarization for menstrual health monitoring using a constrained generation framework that combines structured evidence conditioning with Retrieval-Augmented Generation (RAG) using a prompt-based constrained generation framework. We evaluate semantic alignment using Natural Language Inference (NLI), atomic factuality metrics, and readability measures. Across three LLMs and 4,500 generated summaries, explicit grounding constraints consistently improve clinical alignment, particularly by improving uncertainty preservation and, once faithfulness is evaluated against retrieved evidence, generally preserving or improving faithfulness, while effects on omission remain model-dependent. We also find that improved…
PDF arXiv

Papers

Topics in this field

medical image segmentation · tumor segmentation · brain mri279 papers30 this week
clinical reasoning · question answering · large language models234 papers29 this week
pathology foundation models · instance learning · multiple instance learning145 papers23 this week
health records · cohorts · electronic health records115 papers11 this week
radiology report generation · radiology reports · radiology report69 papers11 this week
radiology report generation · radiology reports · medical vision language59 papers10 this week

Active contributors · 90 days

Nassir NavabThe Value of System 1 Models in Medicine8
Jian WangOverview of CHIP 2026 Shared Task 1: Patient-Specific Phenotype Concept Recognition in Full-Text Biomedical Literature6
Yang YangPatient, Place, Prior (P$^3$): What Counts as Personalization in Medical World Models?6
Dimitris K. IakovidisCross-dataset harmonization for robust endoscopic image analysis6
Wenxuan LiDiagnostic Loss: Asymmetric Supervision for Radiology Report Generation5
Zongwei ZhouDiagnostic Loss: Asymmetric Supervision for Radiology Report Generation5

★ Spotlight this month

arXiv cs.CVOct 15

MedPAO-VL: Interpretable and Protocol-Compliant Agent for Structured Radiology Report Generation

Shrish Shrinath Vaidya, Gowthamaan Palani, Minmini Selvam, Gokulraja Srinivasaraja, Ganapathy Krishnamurthi

Despite the remarkable generalization capabilities of Large Language Models, generating clinically accurate and structured radiology reports from medical images remains a significant challenge. Current end-to-end approaches function as black boxes, prone to factual hallucinations and generating ungrounded findings. This lack of reliability and failure to adhere to domain-specific structuring protocols, fundamentally limits their clinical utility. We present MedPAO-VL, a multimodal agent that shifts the paradigm from monolithic generation to explainable, iterative, protocol-compliant structured report generation. Unlike deterministic models, our plan-act-observe loop functions as a goal-oriented agent: it first perceives the Chest X-Ray through an explainable vision module designed to capture inherent diagnostic uncertainty, then iteratively refines the generated report by observing semantic discrepancies and self-correcting its generation for better alignment with visually detected clinical findings. Evaluation of our framework demonstrates that this agentic reasoning improves clinical correctness and completeness, achieving an expert-rated accuracy score of 3.5/5 and a…

PDF arXiv page Details

Activity · 12 weeks

Fields · AI · updated 43m ago

Medical image segmentation

Found by the topic model: medical image segmentation, clinical reasoning, pathology foundation models.

116papers this week−39.6% vs last week

All papers · 945 With code · 5

Newest Most relevant

738 papers this month

Recent papers

All papers in Research

arXiv cs.CLOct 22
How Ground Truth Shapes Retrieval Scores: Evidence-Aware Evaluation of a Retrieval-Augmented Generation System for Breast Lesions
Miguel Mochizuki Silva, Samuel Ismael, Mateus C. Dias, Thaís Gaudêncio, Yuri Malheiros +1
Purpose: To describe an evidence-aware retrieval evaluation protocol for a clinical retrieval-augmented generation (RAG) system over breast lesion management literature, addressing the dependence of retrieval scores on annotation coverage. Methods: An 18-document corpus and an 18-query development benchmark, with one Yes/No or WH-question per document, were used. Retrieval combined dense embeddings, BM25, and cross-encoder reranking. Chunk sizes of 128 to 1024 tokens, overlaps of 0 to 20%, and four retriever configurations were evaluated. Relevance was defined by evidence spans mapped to all containing chunks, treating overlapping chunks with equivalent evidence as relevant. Retrieval was evaluated using R-Precision, Recall@K, MRR, and nDCG@K. Separately, generation was assessed on a 512-token index at K=1 to 5 using DeepEval claim-level metrics, with deepseek-v4-pro as the LLM judge, and BLEU/ROUGE metrics. Results: The selected hybrid retriever, using 384-token chunks and 20% overlap, retrieved accepted evidence in the top three results for 17 of 18 queries. Recall@3, R-Precision, MRR@3, and nDCG@3 each reached 0.94. Ground-truth curation increased evidence spans from 25 to 37…
PDF arXiv
arXiv cs.CLOct 22
Would an LLM Match into a Residency? Uncertainty, Reasoning and Image Use of Open Language Models on the Spanish MIR Examination
Miguel Fernandez-de-Retana, Unai Zulaika, Ruben Sanchez-Corcuera, Aritz Bilbao-Jayo, Aitor Almeida
Accuracy on medical examinations is common evidence offered for the clinical use of language models, yet a health system that intends to run an open model on its own hardware needs to know considerably more: whether the model recognizes when it is likely to be wrong, whether medical fine-tuning improves this ability, whether its correct answers rest on sound clinical reasoning, or whether it actually uses the images it is given. We examine these questions for four open models of 8 to 27 billion parameters on the Spanish MIR residency examination, scoring 1,552 questions from eight editions under the exam's own rules. Answering every question, the three larger models would rank among roughly the first 600 to 3,000 candidates, with 41 to 43 specialties still open to them. Abstention, however, never pays, because even their least confident answers are right more often than the 25% break-even. Medical fine-tuning reduced overconfidence at the cost of accuracy, without improving how well confidence separates right from wrong answers. Moreover, 13-38% of correct answers rejected a distractor for a clinically unsound reason that confidence did not reflect, and removing or swapping the…
PDF arXiv
arXiv cs.CVOct 22
Diffusion-Based Synthesis of Complete 3D Biparametric Prostate MRI
Claudia Giardina, Montse Pardàs, Verónica Vilaplana
Synthetic biparametric MRI (bpMRI) may help alleviate the limited availability of large and representative prostate MRI datasets for deep learning applications. In this work, we present a conditional 3D diffusion framework for anatomy-conditioned synthesis of complete prostate bpMRI from anatomical masks. The framework supports sequential synthesis, in which T2w and diffusion modalities are generated by separately trained models, and joint synthesis, in which all bpMRI modalities are generated simultaneously within a single model. Five configurations were trained using PI-CAI, FastMRI Prostate, and PROSTATEx datasets to investigate different conditioning schemes, target modalities, and synthesis strategies. Evaluation using distribution-based metrics, paired-image similarity, and qualitative assessment demonstrated the feasibility of both synthesis pathways. Joint synthesis achieved competitive distributional fidelity while generating complete bpMRI, whereas direct synthesis of ADC and computed high-b-value DWI outperformed their derivation from synthetic diffusion-weighted images.
PDF arXiv
arXiv cs.AIOct 22
From Prompt Rules to Golden Data Model: Production-Scale Generation of Personalized, Compliant Pharmaceutical Claims
Suyash Mishra, Qiang Li, Subhabrata Adak, Upender Phogat, Srikanth Patil +1
Large language models (LLMs) are increasingly used to generate domain-specific commercial & medical content (e.g., claims, statements, and promotional phrases) in regulated industries such as pharmaceuticals. However, ensuring its regulatory compliance, factual accuracy, and audience-specific personalization remains a major challenge. We report a production case study asking whether moving compliance and personalization signal from prompt-level rules into retrieval time structured context improves pharmaceutical claims generation, using Composer, a deployed internal tool built on a Golden Data Model (GDM) of 1,867 pharmaceutical claims spanning four products. The GDM integrates claim metadata, references, audience labels, material type, usage history, Match Text Variant (MTV) links, and a six dimension quality score (6C). Across six product-audience segments, the context pipeline improves intended indication (+29%), intended content type (+62%) and intended target audience (+67%), 6C quality score (+86%), and claim reuse (+34%). Production log analysis over the deployment period shows a 29.5% reduction in weekly API cost. We report this as descriptive deployment evidence. This…
PDF arXiv
arXiv cs.CVOct 22
Evaluation of Uncertainty-Aware Multi-Software Ensembles for Hippocampal Segmentation
Gabriel Oliveira-Stahl, Anna Schroder, James Moggridge, Hamza A. Salhab, Caroline Micallef +4
Accurate hippocampal segmentation can be a useful tool for diagnosing and monitoring neurological conditions such as Alzheimer's disease and epilepsy. While numerous automated segmentation methods exist, their clinical adoption remains limited. Reliable uncertainty assessment can enhance trust and facilitate clinical translation. This study evaluates ensembles of five heterogeneous hippocampal segmentation methods - InnerEye, ASHS, FastSurfer, HippoSeg, and FreeSurfer - across two dementia datasets and one epilepsy dataset. The sub-ensemble containing InnerEye, FastSurfer, and HippoSeg emerged as both accurate and efficient, highlighting the feasibility of balancing computational cost and performance. Additionally, ensemble-derived uncertainty quantification with sample variance, mutual information, and predictive entropy is shown to reduce inaccurate segmentations by flagging low-confidence cases, potentially providing a mechanism for automatically escalating ambiguous cases for expert assessment. Lastly, this study explores the downstream clinical utility of ensemble-derived uncertainty, finding a significant correlation with motion artefact severity and a modest contribution…
PDF arXiv
arXiv cs.CLOct 22
From Structured Records to Patient Narratives: Preserving Clinical Alignment in LLM-Generated Health Summaries
Bayram Ayadi, Florian Geissler, Johanna Schmidhuber
As wearable and digital health systems increasingly generate longitudinal physiological records, communicating these observations in patient-accessible language remains a significant challenge. Large Language Models (LLMs) offer a promising mechanism for translating structured clinical information into readable narratives, but this process may introduce semantic drift, where clinically precise meaning is distorted during simplification. We investigate evidence-grounded health summarization for menstrual health monitoring using a constrained generation framework that combines structured evidence conditioning with Retrieval-Augmented Generation (RAG) using a prompt-based constrained generation framework. We evaluate semantic alignment using Natural Language Inference (NLI), atomic factuality metrics, and readability measures. Across three LLMs and 4,500 generated summaries, explicit grounding constraints consistently improve clinical alignment, particularly by improving uncertainty preservation and, once faithfulness is evaluated against retrieved evidence, generally preserving or improving faithfulness, while effects on omission remain model-dependent. We also find that improved…
PDF arXiv

Open problems in Medical image segmentation

Lack of benchmarks for evidence-seeking in longitudinal medical reasoning1 paper raises it · 1 addresses it
Current benchmarks test reasoning over preselected evidence rather than the ability to autonomously seek and integrate evidence across clinical records and longitudinal imaging.
- From Given to Gathered Evidence: Agentic Learning for Longitudinal Medical Reasoningraises · addresses
Handling incidental information in clinical documentation and reasoning1 paper raises it · 1 addresses it
Models often misattribute or use irrelevant background information, leading to contamination in clinical notes and reasoning.
- Large language models are vulnerable to incidental information in clinical documentation and reasoningraises · addresses
Mismatch between benchmark evaluations and real-world clinician use1 paper raises it · 1 addresses it
Benchmarks do not reflect the actual tasks and queries clinicians perform, limiting their predictive value for deployment performance.
- Clinician use of language models diverges from how the models are evaluatedraises · addresses
Generating coherent whole-slide histopathology images at gigapixel scale1 paper raises it · 1 addresses it
Existing generative models operate at patch scale, while clinical supervision and labels exist at the whole-slide level, creating a gap in fidelity and usability.
- BigCell: Generating Gigapixel Whole-Slide Imagesraises · addresses
Learning from deployment experience without retraining frozen models1 paper raises it · 1 addresses it
Frozen models cannot adapt to new clinical evidence or updated guidelines, limiting their long-term utility in evolving medical practice.
- Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AIraises · addresses

Named by an AI from these papers' abstracts.