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 time and modalities.
- From Given to Gathered Evidence: Agentic Learning for Longitudinal Medical Reasoningraises · addresses
Gigapixel whole-slide image generation and segmentation1 paper raises it · 1 addresses it
Existing generative models for histopathology operate at patch scale, while clinical supervision and diagnoses require whole-slide level coherence and fidelity.
- BigCell: Generating Gigapixel Whole-Slide Imagesraises · addresses
Resistance to incidental information in clinical reasoning1 paper raises it · 0 address it
Models may misattribute or use irrelevant background information in clinical documentation, leading to errors in reasoning and documentation.
- Large language models are vulnerable to incidental information in clinical documentation and reasoningraises
Misalignment between clinical benchmarks and real-world use1 paper raises it · 0 address it
Benchmarks often do not reflect the types of queries and tasks clinicians perform in practice, limiting their predictive value for deployment.
- Clinician use of language models diverges from how the models are evaluatedraises
Anatomically unsupported detail in generative super-resolution for medical imaging1 paper raises it · 1 addresses it
Super-resolution methods may produce visually plausible but anatomically incorrect structures, such as vessels, in CT images.
- VascuSR: Iterative Anatomy-Aware Diffusion for CT Super-Resolutionraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Recently funded

Topics in this field

medical image segmentation · tumor segmentation · brain mri286 papers31 this week
pathology foundation models · instance learning · multiple instance learning155 papers26 this week
clinical reasoning · question answering · large language models239 papers25 this week
radiology report generation · radiology reports · radiology report73 papers12 this week
radiology report generation · radiology reports · medical vision language61 papers12 this week
health records · cohorts · electronic health records118 papers9 this week

Topics in this field

Active contributors · 90 days

Active contributors

Activity · 12 weeks

Activity

Recent papers

All papers in Research

arXiv cs.CVOct 17
Arbitrary-Scale Anisotropic 3D MRI Super-Resolution with Gaussian Prototypes
Aditya Rastogi, Ramon Leiser, Prateek Singh, Martha Foltyn-Dumitru, Martin Bendszus +6
Reducing MRI acquisition time improves patient comfort, reduces motion artefacts, and increases scanner throughput. Clinical protocols often shorten acquisitions by sacrificing spatial resolution, particularly along the slice axis. Super-resolution can recover higher-resolution images, but existing methods are typically specialised to one scale or acquisition geometry, limiting their use across heterogeneous clinical protocols. We present GSMR3D, a continuous volumetric model that reconstructs arbitrary isotropic and anisotropic resolutions with a single checkpoint per MRI contrast. It combines a learned dictionary of anisotropic 3D Gaussian prototypes with scale-conditioned frequency encoding and an exact measurement-consistency projection, keeping reconstructions consistent with the acquired low-resolution data. We train separate models on 3,731 contrast-enhanced T1-weighted and 30,254 T1-weighted brain MRI volumes from clinical and population-based cohorts. We evaluate GSMR3D against geometry-specific specialists for isotropic, in-plane, and through-plane super-resolution using reconstruction quality and downstream tasks: brain tumour segmentation, brain-metastasis detection,…
PDF arXiv
arXiv cs.AIOct 17
Medical Fine-Tuning Reshapes, Not Reduces, Patient-Facing AI Risk: A Rubric-Based, LLM-Judge Evaluation Framework
Savan Doshi
Patient-facing medical question answering with large language models (LLMs) is moving from research demonstrations to production deployments, yet evaluation remains anchored on factual correctness. Factuality is necessary but not sufficient: a response can be factually grounded and still issue a directive that, if acted on, would harm the patient. We introduce a risk-sensitive evaluation framework that scores responses by the presence and severity of six categories of risk-bearing language (treatment directives, contraindications, dosage expressions, urgency-triage cues, high-alert medication mentions, and overconfident assertions), anchored on published clinical harm taxonomies. Severity is classified by a three-judge LLM ensemble. We apply this framework to six 7-9B instruction-tuned models, three general (Mistral-7B, Phi-3.5-mini, Llama-3.1-8B) and three medically adapted (BioMistral-7B, OpenBioLLM-Llama3-8B, Med42-Llama3-8B), on 200 real patient questions from the K-QA benchmark. Two findings emerge. First, ensemble risk-bearing language is statistically independent of factual hallucination rate (pooled Spearman $ρ= -0.065$, $n = 300$, 95% CI $[-0.18, +0.05]$; distance…
PDF arXiv
arXiv eess.IVOct 17
Evidence Field: Adaptive Covering Programs for Medical Imaging
Isarar Siddique, Raiyan Siddique, Arshi Niyaz, Jamyang Ugyen Tshomo, Atish Raza
Medical image classifiers typically return predictions without a native contract for independently reconstructing their spatial decision computation. Evidence Field is a trainable spatial-program architecture that jointly produces class scores, selected covering programs and signed evidence. Its encoder combines absolute and image-relative response fields with associative spatial moments and learned characteristic sums. A typed classifier scores individual regions and parent-conditioned multiplicative groups; a covering recursion selects scale, partition and composition. We establish exact one-fold coverage, optimality within the registered grammar, a bound relating smooth training to hard inference, signed-score conservation and class-centred offset invariance. Direct contractions and their adjoint specify arithmetic and storage scaling on two- and three-dimensional grids. Native output records bind inputs, parameters, supports, types and contextual dependencies to individual and ensemble predictions. In a separately reported histopathology application, patient-separated training and evaluation across held-out centres provide empirical evidence for the architecture. Trained…
PDF arXiv
arXiv cs.LGOct 17
Native Probability Outputs for Clinical Triage: An Evaluation of Calibration and Decision Accuracy
Liang You, Zhiyin Zhou, Dawei Tang, Chuchu Wu, Jingzhuo Hu
Patient-facing triage requires an appropriate care recommendation and recognition of when information is insufficient. We evaluate whether Jev, a decision model that returns probabilities over predefined actions, supports both judgments. Using CARE-Bench, we compare Jev with four general-purpose language models and three input-independent baselines across 925 decision points from 439 public cases. On the public test subset, Jev ranks fourth of five models by macro-F1 (0.461) but has the lowest observed multiclass Brier score (0.610), an 18.7\% improvement over uniform prediction (case-bootstrap 95\% interval, 4.9--31.1\%). Noul has lower binary Brier than Choice (0.215 versus 0.276). A evaluation of 453 HealthBench conversations again gives Jev the lowest observed Brier score (0.299), but measures a distinct emergency-referral judgment. Jev combines lower probability error with missed clarification needs in the four-action task. Asking about information sufficiency separately increases recall but also produces frequent unnecessary clarification assignments.
PDF arXiv
arXiv cs.AIOct 17
From Prediction to Action: Population Health World Model for Digital Medicine
Xike Xie, Yu Li, Weizhong Yang, Amalie Dyda, Shaohua Kevin Zhou
Digital medicine now captures data that traces individual health trajectories and reveals population health dynamics through electronic health records, claims, remote monitoring, wearable devices, mobile devices, social sensing data, medical images, etc. But much of its modeling still centers on task-specific, outcome-specific, and prediction-specific estimation. The next frontier is not simply better prediction, but action in an evolving health world shaped by multiple decision-makers, heterogeneous populations, resource constraints, and feedback in care delivery. This is why digital medicine now needs world models: not only to estimate what will happen, but to represent how actions change what can happen next -- whom to prioritize, how to allocate scarce resources, how to adapt care across subgroups, and how interventions reshape future health trajectories and population dynamics. We call such a model population health world model (PHWM): a more foundational representation of an evolving health world in which health states, individual trajectories, population health dynamics, interventions, constraints, and feedback are intrinsically coupled. Building a PHWM endows three unmet…
PDF arXiv
arXiv cs.CVOct 17
CaMeWM: A Causal Medical World Model for Generative Tumor Evolution and Treatment Planning
Huanlong Gao, Xuelei He, Fengjun Zhao, Xiaowei He
Treatment planning is intrinsically counterfactual: clinicians must compare how a patient's tumor and survival would evolve under competing regimens, whereas a retrospective cohort records only the regimen received and one follow-up scan. A treatment-conditioned generator trained on such data can therefore reproduce historical treatment allocation rather than simulate the interventional disease dynamics needed to rank regimens. We introduce \textbf{CaMeWM}, a causal medical world model for supported post-TACE tumor evolution and treatment planning. CaMeWM implements one intervention-to-decision loop rather than three independent prediction tasks: it first admits a queried regimen only for clinically comparable histories with empirical treatment support; it then generates a distribution of lesion-local follow-up worlds through an action-conditioned response descriptor, deterministic anchor, and residual 3D diffusion transition; and it finally maps sampled worlds to restricted mean survival time (RMST) with a response-Cox utility model. Under pre-treatment adjustment and positivity, this loop estimates a prespecified, support-restricted g-formula target; all selection and nuisance…
PDF arXiv

Papers

Topics in this field

medical image segmentation · tumor segmentation · brain mri286 papers31 this week
pathology foundation models · instance learning · multiple instance learning155 papers26 this week
clinical reasoning · question answering · large language models239 papers25 this week
radiology report generation · radiology reports · radiology report73 papers12 this week
radiology report generation · radiology reports · medical vision language61 papers12 this week
health records · cohorts · electronic health records118 papers9 this week

Active contributors · 90 days

Recent papers

All papers in Research

arXiv cs.CVOct 17
Arbitrary-Scale Anisotropic 3D MRI Super-Resolution with Gaussian Prototypes
Aditya Rastogi, Ramon Leiser, Prateek Singh, Martha Foltyn-Dumitru, Martin Bendszus +6
Reducing MRI acquisition time improves patient comfort, reduces motion artefacts, and increases scanner throughput. Clinical protocols often shorten acquisitions by sacrificing spatial resolution, particularly along the slice axis. Super-resolution can recover higher-resolution images, but existing methods are typically specialised to one scale or acquisition geometry, limiting their use across heterogeneous clinical protocols. We present GSMR3D, a continuous volumetric model that reconstructs arbitrary isotropic and anisotropic resolutions with a single checkpoint per MRI contrast. It combines a learned dictionary of anisotropic 3D Gaussian prototypes with scale-conditioned frequency encoding and an exact measurement-consistency projection, keeping reconstructions consistent with the acquired low-resolution data. We train separate models on 3,731 contrast-enhanced T1-weighted and 30,254 T1-weighted brain MRI volumes from clinical and population-based cohorts. We evaluate GSMR3D against geometry-specific specialists for isotropic, in-plane, and through-plane super-resolution using reconstruction quality and downstream tasks: brain tumour segmentation, brain-metastasis detection,…
PDF arXiv
arXiv cs.AIOct 17
Medical Fine-Tuning Reshapes, Not Reduces, Patient-Facing AI Risk: A Rubric-Based, LLM-Judge Evaluation Framework
Savan Doshi
Patient-facing medical question answering with large language models (LLMs) is moving from research demonstrations to production deployments, yet evaluation remains anchored on factual correctness. Factuality is necessary but not sufficient: a response can be factually grounded and still issue a directive that, if acted on, would harm the patient. We introduce a risk-sensitive evaluation framework that scores responses by the presence and severity of six categories of risk-bearing language (treatment directives, contraindications, dosage expressions, urgency-triage cues, high-alert medication mentions, and overconfident assertions), anchored on published clinical harm taxonomies. Severity is classified by a three-judge LLM ensemble. We apply this framework to six 7-9B instruction-tuned models, three general (Mistral-7B, Phi-3.5-mini, Llama-3.1-8B) and three medically adapted (BioMistral-7B, OpenBioLLM-Llama3-8B, Med42-Llama3-8B), on 200 real patient questions from the K-QA benchmark. Two findings emerge. First, ensemble risk-bearing language is statistically independent of factual hallucination rate (pooled Spearman $ρ= -0.065$, $n = 300$, 95% CI $[-0.18, +0.05]$; distance…
PDF arXiv
arXiv eess.IVOct 17
Evidence Field: Adaptive Covering Programs for Medical Imaging
Isarar Siddique, Raiyan Siddique, Arshi Niyaz, Jamyang Ugyen Tshomo, Atish Raza
Medical image classifiers typically return predictions without a native contract for independently reconstructing their spatial decision computation. Evidence Field is a trainable spatial-program architecture that jointly produces class scores, selected covering programs and signed evidence. Its encoder combines absolute and image-relative response fields with associative spatial moments and learned characteristic sums. A typed classifier scores individual regions and parent-conditioned multiplicative groups; a covering recursion selects scale, partition and composition. We establish exact one-fold coverage, optimality within the registered grammar, a bound relating smooth training to hard inference, signed-score conservation and class-centred offset invariance. Direct contractions and their adjoint specify arithmetic and storage scaling on two- and three-dimensional grids. Native output records bind inputs, parameters, supports, types and contextual dependencies to individual and ensemble predictions. In a separately reported histopathology application, patient-separated training and evaluation across held-out centres provide empirical evidence for the architecture. Trained…
PDF arXiv
arXiv cs.LGOct 17
Native Probability Outputs for Clinical Triage: An Evaluation of Calibration and Decision Accuracy
Liang You, Zhiyin Zhou, Dawei Tang, Chuchu Wu, Jingzhuo Hu
Patient-facing triage requires an appropriate care recommendation and recognition of when information is insufficient. We evaluate whether Jev, a decision model that returns probabilities over predefined actions, supports both judgments. Using CARE-Bench, we compare Jev with four general-purpose language models and three input-independent baselines across 925 decision points from 439 public cases. On the public test subset, Jev ranks fourth of five models by macro-F1 (0.461) but has the lowest observed multiclass Brier score (0.610), an 18.7\% improvement over uniform prediction (case-bootstrap 95\% interval, 4.9--31.1\%). Noul has lower binary Brier than Choice (0.215 versus 0.276). A evaluation of 453 HealthBench conversations again gives Jev the lowest observed Brier score (0.299), but measures a distinct emergency-referral judgment. Jev combines lower probability error with missed clarification needs in the four-action task. Asking about information sufficiency separately increases recall but also produces frequent unnecessary clarification assignments.
PDF arXiv
arXiv cs.AIOct 17
From Prediction to Action: Population Health World Model for Digital Medicine
Xike Xie, Yu Li, Weizhong Yang, Amalie Dyda, Shaohua Kevin Zhou
Digital medicine now captures data that traces individual health trajectories and reveals population health dynamics through electronic health records, claims, remote monitoring, wearable devices, mobile devices, social sensing data, medical images, etc. But much of its modeling still centers on task-specific, outcome-specific, and prediction-specific estimation. The next frontier is not simply better prediction, but action in an evolving health world shaped by multiple decision-makers, heterogeneous populations, resource constraints, and feedback in care delivery. This is why digital medicine now needs world models: not only to estimate what will happen, but to represent how actions change what can happen next -- whom to prioritize, how to allocate scarce resources, how to adapt care across subgroups, and how interventions reshape future health trajectories and population dynamics. We call such a model population health world model (PHWM): a more foundational representation of an evolving health world in which health states, individual trajectories, population health dynamics, interventions, constraints, and feedback are intrinsically coupled. Building a PHWM endows three unmet…
PDF arXiv
arXiv cs.CVOct 17
CaMeWM: A Causal Medical World Model for Generative Tumor Evolution and Treatment Planning
Huanlong Gao, Xuelei He, Fengjun Zhao, Xiaowei He
Treatment planning is intrinsically counterfactual: clinicians must compare how a patient's tumor and survival would evolve under competing regimens, whereas a retrospective cohort records only the regimen received and one follow-up scan. A treatment-conditioned generator trained on such data can therefore reproduce historical treatment allocation rather than simulate the interventional disease dynamics needed to rank regimens. We introduce \textbf{CaMeWM}, a causal medical world model for supported post-TACE tumor evolution and treatment planning. CaMeWM implements one intervention-to-decision loop rather than three independent prediction tasks: it first admits a queried regimen only for clinically comparable histories with empirical treatment support; it then generates a distribution of lesion-local follow-up worlds through an action-conditioned response descriptor, deterministic anchor, and residual 3D diffusion transition; and it finally maps sampled worlds to restricted mean survival time (RMST) with a response-Cox utility model. Under pre-treatment adjustment and positivity, this loop estimates a prespecified, support-restricted g-formula target; all selection and nuisance…
PDF arXiv

Activity · 12 weeks

Fields · AI · updated 42m ago

Medical image segmentation

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

119papers this week−39.0% vs last week

All papers · 978 With code · 5

Newest Most relevant

751 papers this month

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 time and modalities.
- From Given to Gathered Evidence: Agentic Learning for Longitudinal Medical Reasoningraises · addresses
Gigapixel whole-slide image generation and segmentation1 paper raises it · 1 addresses it
Existing generative models for histopathology operate at patch scale, while clinical supervision and diagnoses require whole-slide level coherence and fidelity.
- BigCell: Generating Gigapixel Whole-Slide Imagesraises · addresses
Resistance to incidental information in clinical reasoning1 paper raises it · 0 address it
Models may misattribute or use irrelevant background information in clinical documentation, leading to errors in reasoning and documentation.
- Large language models are vulnerable to incidental information in clinical documentation and reasoningraises
Misalignment between clinical benchmarks and real-world use1 paper raises it · 0 address it
Benchmarks often do not reflect the types of queries and tasks clinicians perform in practice, limiting their predictive value for deployment.
- Clinician use of language models diverges from how the models are evaluatedraises
Anatomically unsupported detail in generative super-resolution for medical imaging1 paper raises it · 1 addresses it
Super-resolution methods may produce visually plausible but anatomically incorrect structures, such as vessels, in CT images.
- VascuSR: Iterative Anatomy-Aware Diffusion for CT Super-Resolutionraises · addresses

Named by an AI from these papers' abstracts.