Papers

Field

Top tools here

Open problems in Image segmentation

Lack of benchmarks for agentic evidence-seeking in medical imaging1 paper raises it · 1 addresses it
Current benchmarks assess reasoning over preselected evidence rather than the ability to autonomously seek and use longitudinal imaging and clinical records.
- 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 histopathology models operate at patch scale, but clinical supervision and diagnoses require whole-slide level coherence and fidelity.
- BigCell: Generating Gigapixel Whole-Slide Imagesraises · addresses
Anatomically unsupported detail in generative super-resolution for CT1 paper raises it · 1 addresses it
Generative SR can produce visually plausible but anatomically incorrect vascular structures, leading to unreliable clinical interpretations.
- VascuSR: Iterative Anatomy-Aware Diffusion for CT Super-Resolutionraises · addresses
Mismatch between clinical use and evaluation benchmarks1 paper raises it · 1 addresses it
Benchmarks often fail to reflect real-world clinical queries, leading to poor generalization of model performance in deployment.
- Clinician use of language models diverges from how the models are evaluatedraises · addresses
Parameter-efficient fine-tuning for large-scale medical models1 paper raises it · 1 addresses it
Training or fully fine-tuning large models on limited neural or medical data is computationally expensive and often impractical.
- Scaling Parameter-Efficient Fine-Tuning for Brain Encodingraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Recently funded

Topics in this field

image segmentation · volumetric · medical image381 papers49 this week
clinical reasoning · question answering · language models195 papers38 this week
patient history · clinical data · health records104 papers27 this week
eeg foundation models · electroencephalography eeg · eeg foundation144 papers18 this week
radiology report generation · medical vision language · vision language models106 papers18 this week
electrocardiogram ecg · electrocardiogram · ecgs137 papers14 this week

Topics in this field

Active contributors · 90 days

Active contributors

Activity · 12 weeks

Coming with more sources: repos

Activity

Recent papers

All in Research →

arXiv cs.AIOct 19
MoveBench: A Rubric-Based Benchmark for Evaluating Large Language Models in Sports and Health Coaching
Yitong Li, Jiang Bian, Jingling Wang, Pan Ding, Chengying Gu
Despite rapid advances in large language models (LLMs), their deployment in the sports and health domain remains high-risk due to the absence of domain-specific evaluation benchmarks. Existing general-purpose benchmarks (e.g., MMLU and HELM) primarily assess broad knowledge and reasoning capabilities, but fail to capture critical domain requirements such as exercise safety, physiological appropriateness, personalization, and actionable coaching quality. This gap is particularly concerning in fitness and health applications, where incorrect or unsafe recommendations can lead to physical harm. To address this limitation, we introduce MoveBench, the first comprehensive benchmarking framework specifically designed for evaluating LLMs in sports and health coaching. The proposed benchmark integrates heterogeneous task formats, including multiple-choice questions (MCQs) and open-ended question answering (OpenQA), grounded in real-world user scenarios and paired with structured rubrics emphasizing safety compliance, scientific validity, and training logic. Through large-scale evaluation of 15 diverse LLMs on 809 questions with 5,012 rubric-level criteria, our results reveal substantial…
PDF arXiv
arXiv cs.CVOct 19
How Robust Are Prognostic Radiomic Features? Comparing Selection Techniques on Pooled Glioblastoma Cohorts
Yannick Sodonougbo, Marlene Schnieders, Alexia Rizoudis, Santiago Cepeda, Frank Kramer +1
Radiomic survival studies in glioblastoma report heterogeneous prognostic features, but how much of this stems from the methodology itself is rarely examined. We analysed the association of 463 radiomic, anatomical and clinical features from pre-treatment MRI with overall survival in 705 IDH-wildtype glioblastoma patients from three public cohorts, using three techniques: a log-rank test after median split, univariate Cox regression (both Benjamini-Hochberg corrected) and an XGBoost regressor interpreted with SHAP. The log-rank test selected 99 features, Cox regression 72 and SHAP its top 20; five were selected by all three: age, a peritumoural T2 texture feature, the number of connected peritumoural mask components and two image-level intensity maxima. The two survival tests shared 51 features, about half of the SHAP top 20 were also selected by either test, and where selections overlapped, effect directions agreed. Many selections were PyRadiomics diagnostic descriptors that are not restricted to tumour voxels. Analytical pipeline choices, including ranking method, pre-filtering and descriptor handling, can substantially influence which features appear prognostic.
PDF arXiv
arXiv cs.CVOct 19
Context-Aware Topological Distillation Graph Network for Asymmetric EEG-Eye Movement Emotion Recognition
Peijun Shi, Xiujin Zhu, Zhenguo Lao, Chee-Onn Chow, Wei Ru Wong +2
EEG-eye movement emotion recognition can support mental-health monitoring and adaptive interfaces, but most fusion models treat the two signals as parallel features, classify each window alone and degrade when eye data are lost. We propose the Context-Aware Topological Distillation Graph Network (CTD-GNet), in which EEG features form the nodes of an electrode graph, and eye movements and preceding windows modulate its edges, nodes and readout, the edges through electrode-specific prompts. Bidirectional distillation of the graph, node relations and predictions couples this multimodal teacher with a single-window EEG student, improving the teacher and aligning the two graphs 35-fold. In leave-one-subject-out tests on SEED and SEED-IV against 17 baselines, CTD-GNet has the highest mean accuracy, 84.91% and 76.17%, significantly above 9 and 6 of 13 eye-based baselines after Holm correction, the smallest cross-subject spread among multimodal models and the highest worst-subject accuracy. It is the most accurate model at every rate of missing eye data on SEED-IV, keeps 66.1% on SEED without eye data, more than any EEG-only model, and stays 9.3 and 11.9 points above all single-window…
PDF arXiv
arXiv cs.CVOct 19
Learning the Dose Manifold: A Latent Diffusion Framework for Volumetric Dose Prediction in Automated Radiotherapy Treatment Planning
J. Boyer-Chammard, R. Vauclin, M. C. Biston, P. Maury, M. Gau +5
Automated treatment planning (ATP) aims to reduce the unwarranted inter-planner variability of manual planning, while improving treatment quality and efficiency. Most ATP pipelines rely on the prediction of the achievable three-dimensional dose distribution for a given anatomy and the subsequent optimization of machine parameters to reproduce it. Diffusion-based methods are largely slice-wise due to the high dimensionality of radiotherapy data, and assume a one-to-one mapping between anatomy and optimal dose despite the multi-objective nature of treatment planning. They are evaluated on their ability to match reference doses and rarely on their integration in ATP frameworks. We present LaDose, a latent diffusion framework for fully volumetric dose prediction. An autoencoder learned on dose distributions, trained so that perturbed latents decode to plausible doses, compresses dose maps 128-fold and enables 3D diffusion on a single GPU. Prescription values are represented as exact scalar vectors that bypass the image encoder, avoiding resampling and latent compression. Multiscale classifier-free guidance allows for the modulation of clinical trade-offs at inference, without…
PDF arXiv
arXiv cs.LGOct 19
UtilityBench: Measuring Language Model Utility When Errors Have Different Costs
Qifeng Lei, Zhiyong Yang, Zitai Wang, Shilong Bao, Linchao Zhang +2
As language models are increasingly deployed in real-world scenarios with important outcomes, the impact of their mistakes often extends far beyond what correctness can capture. In domains like medicine, a single error can lead to serious consequences and put patient safety at risk. However, mainstream evaluation protocols still treat all errors as equal, overlooking the spectrum of real-world costs. To address this, we propose a utility-based evaluation paradigm that explicitly incorporates the varying consequences of errors. Guided by this principle, we develop UtilityBench, a large-scale benchmark of 15,000 instances with verifiable answers, quantifying error severity using Best-Worst Scaling to elicit meaningful, data-driven cost estimates. These quantified utilities shape when a model should answer or abstain, guiding it to make decisions that align with the true importance of each scenario. As another merit, we introduce UtilityAUC, a metric that measures the area under the utility curve determined by a model's response ordering, thereby enabling utility preference alignment beyond error frequency. Our theoretical analysis demonstrates that UtilityAUC can distinguish…
PDF arXiv
arXiv cs.CVOct 19
Multi-scale Fusion of Fast Vision Mamba and Foundation Model Features for Patch-Level Gleason Grading in Computational Pathology
Zihe Zhang, Weimiao Yu, Piumi Don Simonge
Automated Gleason grading of prostate whole slide images (WSIs) enables faster and more consistent cancer risk stratification. However, it remains a challenging task due to the subtle morphological differences between grades, the severe class imbalance arising from rare patterns, and the diagnostic features that span multiple spatial scales. Pathology foundation models (FMs) extract strong patch representations but often operate at a single-scale, which limits spatial context and disproportionately affects classes that depend on broader context. The challenge of fusing multiple scales and complementary models, with minimal data and computational resources, remains unresolved. We propose a multi-scale classifier built on state-space models. Our method combines two complementary feature sources: a frozen foundation model, and a lightweight FastVim, pre-trained on ImageNet and distilled from the foundation model, that reads the raw image crops. At each scale, a Mamba model encodes the features from both sources with linear-time spatial context, and a jointly trained head fuses the encoded representations into one prediction. On the PANDA dataset, our method reaches macro F1 of 0.894…
PDF arXiv

Papers

Topics in this field

image segmentation · volumetric · medical image381 papers49 this week
clinical reasoning · question answering · language models195 papers38 this week
patient history · clinical data · health records104 papers27 this week
eeg foundation models · electroencephalography eeg · eeg foundation144 papers18 this week
radiology report generation · medical vision language · vision language models106 papers18 this week
electrocardiogram ecg · electrocardiogram · ecgs137 papers14 this week

Active contributors · 90 days

Recent papers

All in Research →

arXiv cs.AIOct 19
MoveBench: A Rubric-Based Benchmark for Evaluating Large Language Models in Sports and Health Coaching
Yitong Li, Jiang Bian, Jingling Wang, Pan Ding, Chengying Gu
Despite rapid advances in large language models (LLMs), their deployment in the sports and health domain remains high-risk due to the absence of domain-specific evaluation benchmarks. Existing general-purpose benchmarks (e.g., MMLU and HELM) primarily assess broad knowledge and reasoning capabilities, but fail to capture critical domain requirements such as exercise safety, physiological appropriateness, personalization, and actionable coaching quality. This gap is particularly concerning in fitness and health applications, where incorrect or unsafe recommendations can lead to physical harm. To address this limitation, we introduce MoveBench, the first comprehensive benchmarking framework specifically designed for evaluating LLMs in sports and health coaching. The proposed benchmark integrates heterogeneous task formats, including multiple-choice questions (MCQs) and open-ended question answering (OpenQA), grounded in real-world user scenarios and paired with structured rubrics emphasizing safety compliance, scientific validity, and training logic. Through large-scale evaluation of 15 diverse LLMs on 809 questions with 5,012 rubric-level criteria, our results reveal substantial…
PDF arXiv
arXiv cs.CVOct 19
How Robust Are Prognostic Radiomic Features? Comparing Selection Techniques on Pooled Glioblastoma Cohorts
Yannick Sodonougbo, Marlene Schnieders, Alexia Rizoudis, Santiago Cepeda, Frank Kramer +1
Radiomic survival studies in glioblastoma report heterogeneous prognostic features, but how much of this stems from the methodology itself is rarely examined. We analysed the association of 463 radiomic, anatomical and clinical features from pre-treatment MRI with overall survival in 705 IDH-wildtype glioblastoma patients from three public cohorts, using three techniques: a log-rank test after median split, univariate Cox regression (both Benjamini-Hochberg corrected) and an XGBoost regressor interpreted with SHAP. The log-rank test selected 99 features, Cox regression 72 and SHAP its top 20; five were selected by all three: age, a peritumoural T2 texture feature, the number of connected peritumoural mask components and two image-level intensity maxima. The two survival tests shared 51 features, about half of the SHAP top 20 were also selected by either test, and where selections overlapped, effect directions agreed. Many selections were PyRadiomics diagnostic descriptors that are not restricted to tumour voxels. Analytical pipeline choices, including ranking method, pre-filtering and descriptor handling, can substantially influence which features appear prognostic.
PDF arXiv
arXiv cs.CVOct 19
Context-Aware Topological Distillation Graph Network for Asymmetric EEG-Eye Movement Emotion Recognition
Peijun Shi, Xiujin Zhu, Zhenguo Lao, Chee-Onn Chow, Wei Ru Wong +2
EEG-eye movement emotion recognition can support mental-health monitoring and adaptive interfaces, but most fusion models treat the two signals as parallel features, classify each window alone and degrade when eye data are lost. We propose the Context-Aware Topological Distillation Graph Network (CTD-GNet), in which EEG features form the nodes of an electrode graph, and eye movements and preceding windows modulate its edges, nodes and readout, the edges through electrode-specific prompts. Bidirectional distillation of the graph, node relations and predictions couples this multimodal teacher with a single-window EEG student, improving the teacher and aligning the two graphs 35-fold. In leave-one-subject-out tests on SEED and SEED-IV against 17 baselines, CTD-GNet has the highest mean accuracy, 84.91% and 76.17%, significantly above 9 and 6 of 13 eye-based baselines after Holm correction, the smallest cross-subject spread among multimodal models and the highest worst-subject accuracy. It is the most accurate model at every rate of missing eye data on SEED-IV, keeps 66.1% on SEED without eye data, more than any EEG-only model, and stays 9.3 and 11.9 points above all single-window…
PDF arXiv
arXiv cs.CVOct 19
Learning the Dose Manifold: A Latent Diffusion Framework for Volumetric Dose Prediction in Automated Radiotherapy Treatment Planning
J. Boyer-Chammard, R. Vauclin, M. C. Biston, P. Maury, M. Gau +5
Automated treatment planning (ATP) aims to reduce the unwarranted inter-planner variability of manual planning, while improving treatment quality and efficiency. Most ATP pipelines rely on the prediction of the achievable three-dimensional dose distribution for a given anatomy and the subsequent optimization of machine parameters to reproduce it. Diffusion-based methods are largely slice-wise due to the high dimensionality of radiotherapy data, and assume a one-to-one mapping between anatomy and optimal dose despite the multi-objective nature of treatment planning. They are evaluated on their ability to match reference doses and rarely on their integration in ATP frameworks. We present LaDose, a latent diffusion framework for fully volumetric dose prediction. An autoencoder learned on dose distributions, trained so that perturbed latents decode to plausible doses, compresses dose maps 128-fold and enables 3D diffusion on a single GPU. Prescription values are represented as exact scalar vectors that bypass the image encoder, avoiding resampling and latent compression. Multiscale classifier-free guidance allows for the modulation of clinical trade-offs at inference, without…
PDF arXiv
arXiv cs.LGOct 19
UtilityBench: Measuring Language Model Utility When Errors Have Different Costs
Qifeng Lei, Zhiyong Yang, Zitai Wang, Shilong Bao, Linchao Zhang +2
As language models are increasingly deployed in real-world scenarios with important outcomes, the impact of their mistakes often extends far beyond what correctness can capture. In domains like medicine, a single error can lead to serious consequences and put patient safety at risk. However, mainstream evaluation protocols still treat all errors as equal, overlooking the spectrum of real-world costs. To address this, we propose a utility-based evaluation paradigm that explicitly incorporates the varying consequences of errors. Guided by this principle, we develop UtilityBench, a large-scale benchmark of 15,000 instances with verifiable answers, quantifying error severity using Best-Worst Scaling to elicit meaningful, data-driven cost estimates. These quantified utilities shape when a model should answer or abstain, guiding it to make decisions that align with the true importance of each scenario. As another merit, we introduce UtilityAUC, a metric that measures the area under the utility curve determined by a model's response ordering, thereby enabling utility preference alignment beyond error frequency. Our theoretical analysis demonstrates that UtilityAUC can distinguish…
PDF arXiv
arXiv cs.CVOct 19
Multi-scale Fusion of Fast Vision Mamba and Foundation Model Features for Patch-Level Gleason Grading in Computational Pathology
Zihe Zhang, Weimiao Yu, Piumi Don Simonge
Automated Gleason grading of prostate whole slide images (WSIs) enables faster and more consistent cancer risk stratification. However, it remains a challenging task due to the subtle morphological differences between grades, the severe class imbalance arising from rare patterns, and the diagnostic features that span multiple spatial scales. Pathology foundation models (FMs) extract strong patch representations but often operate at a single-scale, which limits spatial context and disproportionately affects classes that depend on broader context. The challenge of fusing multiple scales and complementary models, with minimal data and computational resources, remains unresolved. We propose a multi-scale classifier built on state-space models. Our method combines two complementary feature sources: a frozen foundation model, and a lightweight FastVim, pre-trained on ImageNet and distilled from the foundation model, that reads the raw image crops. At each scale, a Mamba model encodes the features from both sources with linear-time spatial context, and a jointly trained head fuses the encoded representations into one prediction. On the PANDA dataset, our method reaches macro F1 of 0.894…
PDF arXiv

Activity · 12 weeks

Coming with more sources: repos

Fields · AI · updated 53m ago

Image segmentation

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

164papers this week−21.5% vs last week

All papers · 1.1k With code · 4

Newest Most relevant

1k papers this month

Open problems in Image segmentation

Lack of benchmarks for agentic evidence-seeking in medical imaging1 paper raises it · 1 addresses it
Current benchmarks assess reasoning over preselected evidence rather than the ability to autonomously seek and use longitudinal imaging and clinical records.
- 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 histopathology models operate at patch scale, but clinical supervision and diagnoses require whole-slide level coherence and fidelity.
- BigCell: Generating Gigapixel Whole-Slide Imagesraises · addresses
Anatomically unsupported detail in generative super-resolution for CT1 paper raises it · 1 addresses it
Generative SR can produce visually plausible but anatomically incorrect vascular structures, leading to unreliable clinical interpretations.
- VascuSR: Iterative Anatomy-Aware Diffusion for CT Super-Resolutionraises · addresses
Mismatch between clinical use and evaluation benchmarks1 paper raises it · 1 addresses it
Benchmarks often fail to reflect real-world clinical queries, leading to poor generalization of model performance in deployment.
- Clinician use of language models diverges from how the models are evaluatedraises · addresses
Parameter-efficient fine-tuning for large-scale medical models1 paper raises it · 1 addresses it
Training or fully fine-tuning large models on limited neural or medical data is computationally expensive and often impractical.
- Scaling Parameter-Efficient Fine-Tuning for Brain Encodingraises · addresses

Named by an AI from these papers' abstracts.