医学 AI - arXivDaily 专题

2302.12533 2023-10-03 cs.LG cs.AI eess.SP 76%

HUST bearing: a practical dataset for ball bearing fault diagnosis

Nguyen Duc Thuan, Hoang Si Hong

专题命中医学数据与评测：diagnosis(title)；分类 cs.LG、eess.SP

Comments We are considering some issues in the paper

2307.14959 2023-07-28 cs.CV cs.LG 76%

Federated Model Aggregation via Self-Supervised Priors for Highly Imbalanced Medical Image Classification

Marawan Elbatel, Hualiang Wang, Robert Martí, Huazhu Fu, Xiaomeng Li

专题命中医学数据与评测：medical image(title)；分类 cs.CV、cs.LG

2301.02390 2023-01-09 eess.IV cs.CV 76%

Deep-learning models in medical image analysis: Detection of esophagitis from the Kvasir Dataset

Kyoka Yoshiok, Kensuke Tanioka, Satoru Hiwa, Tomoyuki Hiroyasu

专题命中医学数据与评测：medical image(title)；分类 cs.CV、eess.IV

2212.01577 2022-12-06 eess.IV cs.CV cs.MM 76%

A Domain-specific Perceptual Metric via Contrastive Self-supervised Representation: Applications on Natural and Medical Images

Hongwei Bran Li, Chinmay Prabhakar, Suprosanna Shit, Johannes Paetzold, Tamaz Amiranashvili, Jianguo Zhang, Daniel Rueckert, Juan Eugenio Iglesias, Benedikt Wiestler, Bjoern Menze

专题命中医学数据与评测：medical image(title)；分类 cs.CV、eess.IV

Comments under review

2112.06194 2021-12-30 eess.IV cs.AI cs.CV 76%

Improving Performance of Federated Learning based Medical Image Analysis in Non-IID Settings using Image Augmentation

Alper Emin Cetinkaya, Murat Akin, Seref Sagiroglu

专题命中医学数据与评测：medical image(title)；分类 cs.CV、eess.IV

Journal ref IEEE 14th International Conference on Information Security and Cryptology, 2021, pp. 69-74

2607.24878 2026-07-29 q-bio.QM cs.AI cs.LG 新提交 75%

GraphRareBench: An Auditable Graph-Evidence Benchmark for Phenotype-Driven Rare-Disease Diagnosis

GraphRareBench：用于表型驱动罕见病诊断的可审计图证据基准测试

Guiling Guo, Jia Yang, Jiahao Xu, Shuyuan Zheng, Zhonghai Sun, Qiyuan Li

专题命中医学数据与评测：diagnosis(title)；分类 cs.LG、q-bio

AI总结研究针对表型驱动罕见病诊断基准测试不透明问题，引入GraphRareBench基准测试，含病例与目标-混杂因素对。通过共享特征接口监督排名器及特定智能体测试，发现不同方法互补，为更透明的诊断系统评估提供基础。

2601.16529 2026-07-09 cs.AI cs.HC 版本更新 75%

SycoEval-EM: Sycophancy Evaluation of Large Language Models in Simulated Clinical Encounters for Emergency Care

SycoEval-EM：急诊护理模拟临床场景中大语言模型的谄媚评估

Dongshen Peng, Yi Wang, Austin Schoeffler, Sun-ha Hong, Brian Suffoletto, David Kim, Carl Preiksaitis, Christian Rose

机构 * UNC Chapel Hill（UNC夏洛特山分校）； University of Waterloo（滑铁卢大学）； Stanford University（斯坦福大学）

专题命中医学数据与评测：CT(abstract,abstract_cn)；clinical AI(abstract)

AI总结提出SycoEval-EM多智能体模拟框架，评估19个LLM在急诊医学中对患者说服的鲁棒性，发现谄媚率呈双峰分布，静态医学基准无法预测安全表现。

Comments 19 pages, 10 figures

2603.14644 2026-05-29 eess.IV cs.CV cs.DB cs.LG 75%

LUMINA: A Multi-Vendor Mammography Benchmark with Energy Harmonization Protocol

LUMINA：采用能量协调协议的多供应商乳腺X线摄影基准

Hongyi Pan, Gorkem Durak, Halil Ertugrul Aktas, Andrea M. Bejar, Baver Tutun, Emre Uysal, Ezgi Bulbul, Mehmet Fatih Dogan, Berrin Erok, Berna Akkus Yildirim, Sukru Mehmet Erturk, Ulas Bagci

机构 * Department of Radiology, Northwestern University（北western大学放射科）； Department of Radiation Oncology, University of Health Sciences Prof. Dr. Cemil Tascioglu City Hospital（健康科学大学教授Dr. Cemil Tascioglu医院放射肿瘤科）； Department of Radiology, Istanbul University（伊斯坦布尔大学放射科）

专题命中医学数据与评测：pathology(abstract)；diagnosis(abstract)；分类 cs.CV、cs.LG、eess.IV

AI总结为解决现有FFDM数据集规模小、标注少和供应商多样性不足的问题，提出LUMINA多供应商数据集及能量协调方法，通过前景像素对齐减少域偏移，在诊断、BI-RADS分类和密度估计任务上验证了模型性能提升。

Comments This paper was accepted to CVPR 2026

2512.06575 2025-12-09 eess.IV cs.CV cs.LG 75%

Proof of Concept for Mammography Classification with Enhanced Compactness and Separability Modules

乳腺分类的证明概念：增强的紧凑性和可分离性模块

Fariza Dahes

机构 * Fariza Dahes (December 2025)（Fariza Dahes（2025年12月））

专题命中医学数据与评测：medical image(abstract)；MRI(abstract)；分类 cs.CV、cs.LG、eess.IV

AI总结本研究验证了改进的ConvNeXt Tiny架构在乳腺分类中的有效性，通过多指标评估和特征可解释性分析，探讨了增强紧凑性和可分离性的方法。

Comments 26 pages, 16 figures, 2 tables; proof of concept on mammography classification with compactness/separability modules and interactive dashboard; preprint submitted to arXiv cs.LG

2505.04230 2025-05-08 eess.IV q-bio.TO 75%

HYAMD High-Resolution Fundus Image Dataset for age related macular degeneration (AMD) Diagnosis

Meishar Meisel, Benjamin A. Cohen, Meital Baskin, Beatrice Tiosano, Joachim A. Behar, Eran Berkowitz

专题命中医学数据与评测：diagnosis(title)；分类 q-bio、eess.IV

2412.17041 2025-04-21 cs.CV cs.AI cs.LG eess.IV 75%

An OpenMind for 3D medical vision self-supervised learning

Tassilo Wald, Constantin Ulrich, Jonathan Suprijadi, Sebastian Ziegler, Michal Nohel, Robin Peretzke, Gregor Köhler, Klaus H. Maier-Hein

专题命中医学数据与评测：medical image(abstract)；MRI(abstract)；分类 cs.CV、cs.LG、eess.IV

Comments Pre-Print; Dataset, Benchmark and Codebase available through https://github.com/MIC-DKFZ/nnssl

2502.12180 2025-02-19 eess.IV cs.AI cs.CV cs.LG 75%

ClusMFL: A Cluster-Enhanced Framework for Modality-Incomplete Multimodal Federated Learning in Brain Imaging Analysis

Xinpeng Wang, Rong Zhou, Han Xie, Xiaoying Tang, Lifang He, Carl Yang

专题命中医学数据与评测：MRI(abstract)；CT(abstract)；分类 cs.CV、cs.LG、eess.IV

2409.19945 2024-10-01 eess.IV cs.CV cs.LG 75%

One Shot GANs for Long Tail Problem in Skin Lesion Dataset using novel content space assessment metric

Kunal Deo, Deval Mehta, Kshitij Jadhav

专题命中医学数据与评测：medical image(abstract)；diagnosis(abstract)；分类 cs.CV、cs.LG、eess.IV

Comments 15 pages, 6 Figures, 9 Tables and additional 6 Tables in Ancillary Data

2406.15392 2024-08-31 physics.med-ph 75%

Quantitative Evaluation of Microstrip, Dipole, and L/C Loop pTx Arrays for UHF MR Imaging

Debolina De, Aditya A. Bhosale, Xiaoliang Zhang

专题命中医学数据与评测：MRI(abstract)；pathology(abstract)；diagnosis(abstract)

2407.02356 2024-07-03 eess.IV cs.CV cs.LG 75%

Enable the Right to be Forgotten with Federated Client Unlearning in Medical Imaging

Zhipeng Deng, Luyang Luo, Hao Chen

专题命中医学数据与评测：medical image(abstract)；diagnosis(abstract)；分类 cs.CV、cs.LG、eess.IV

2206.05288 2024-05-07 eess.IV cs.AI cs.CV cs.LG 75%

From Labels to Priors in Capsule Endoscopy: A Prior Guided Approach for Improving Generalization with Few Labels

Anuja Vats, Ahmed Mohammed, Marius Pedersen

专题命中医学数据与评测：pathology(abstract)；diagnosis(abstract)；分类 cs.CV、cs.LG、eess.IV

2402.10066 2024-02-16 cs.CV cs.LG cs.NE eess.IV 75%

NYCTALE: Neuro-Evidence Transformer for Adaptive and Personalized Lung Nodule Invasiveness Prediction

Sadaf Khademi, Anastasia Oikonomou, Konstantinos N. Plataniotis, Arash Mohammadi

专题命中医学数据与评测：CT(abstract)；diagnosis(abstract)；分类 cs.CV、cs.LG、eess.IV

2310.08165 2023-11-29 eess.IV cs.CV cs.LG 75%

COVID-19 detection using ViT transformer-based approach from Computed Tomography Images

Kenan Morani

专题命中医学数据与评测：CT(abstract)；diagnosis(abstract)；分类 cs.CV、cs.LG、eess.IV

2206.06448 2023-11-02 eess.IV cs.CR cs.CV cs.LG 75%

Assessing Privacy Leakage in Synthetic 3-D PET Imaging using Transversal GAN

Robert V. Bergen, Jean-Francois Rajotte, Fereshteh Yousefirizi, Arman Rahmim, Raymond T. Ng

专题命中医学数据与评测：medical image(abstract)；diagnosis(abstract)；分类 cs.CV、cs.LG、eess.IV

Comments arXiv admin note: text overlap with arXiv:2111.01866

2310.11577 2023-10-19 eess.IV cs.CV cs.LG 75%

Studying the Effects of Sex-related Differences on Brain Age Prediction using brain MR Imaging

Mahsa Dibaji, Neha Gianchandani, Akhil Nair, Mansi Singhal, Roberto Souza, Mariana Bento

专题命中医学数据与评测：MRI(abstract)；diagnosis(abstract)；分类 cs.CV、cs.LG、eess.IV

2209.11195 2022-09-23 eess.IV cs.CV cs.LG 75%

OLIVES Dataset: Ophthalmic Labels for Investigating Visual Eye Semantics

Mohit Prabhushankar, Kiran Kokilepersaud, Yash-yee Logan, Stephanie Trejo Corona, Ghassan AlRegib, Charles Wykoff

专题命中医学数据与评测：medical image(abstract)；diagnosis(abstract)；分类 cs.CV、cs.LG、eess.IV

Comments Accepted at 36th Conference on Neural Information Processing Systems (NeurIPS 2022) Track on Datasets and Benchmarks

2004.12314 2020-05-08 cs.CV cs.LG eess.IV stat.ML 75%

A Global Benchmark of Algorithms for Segmenting Late Gadolinium-Enhanced Cardiac Magnetic Resonance Imaging

Zhaohan Xiong, Qing Xia, Zhiqiang Hu, Ning Huang, Cheng Bian, Yefeng Zheng, Sulaiman Vesal, Nishant Ravikumar, Andreas Maier, Xin Yang, Pheng-Ann Heng, Dong Ni, Caizi Li, Qianqian Tong, Weixin Si, Elodie Puybareau, Younes Khoudli, Thierry Geraud, Chen Chen, Wenjia Bai, Daniel Rueckert, Lingchao Xu, Xiahai Zhuang, Xinzhe Luo, Shuman Jia, Maxime Sermesant, Yashu Liu, Kuanquan Wang, Davide Borra, Alessandro Masci, Cristiana Corsi, Coen de Vente, Mitko Veta, Rashed Karim, Chandrakanth Jayachandran Preetha, Sandy Engelhardt, Menyun Qiao, Yuanyuan Wang, Qian Tao, Marta Nunez-Garcia, Oscar Camara, Nicolo Savioli, Pablo Lamata, Jichao Zhao

专题命中医学数据与评测：MRI(abstract)；diagnosis(abstract)；分类 cs.CV、cs.LG、eess.IV

1807.06081 2020-09-22 cs.CV cs.LG 74%

A Dataset of Laryngeal Endoscopic Images with Comparative Study on Convolution Neural Network Based Semantic Segmentation

Max-Heinrich Laves, Jens Bicker, Lüder A. Kahrs, Tobias Ortmaier

专题命中医学数据与评测：medical image(abstract)；diagnosis(abstract)；分类 cs.CV、cs.LG；radiology(comments)

Comments Accepted for publication in International Journal of Computer Assisted Radiology and Surgery

2606.20919 2026-07-31 cs.CV 版本更新 74%

GIM-ENDO: A Multimodal Endoscopic Image and Video Dataset for Gastric Intestinal Metaplasia Morphology and Pathology

GIM-ENDO：用于胃肠化生形态与病理的多模态内镜图像和视频数据集

Mojgan Forootan, Mahziar Setayeshfar, Ali Darvishi, Mohammad Tashakoripour, Hamidreza Bolhasani

机构 * Gastroenterology and Liver Disease Research Center, Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences（沙希德·贝赫什提医科大学胃肠病与肝病研究中心，胃肠病与肝病研究所）； Iran University of Medical Sciences（伊朗医科大学）； Shiraz University of Medical Sciences（设拉子医科大学）； Gastroenterology Department, Amiralam Hospital, Tehran University of Medical Sciences（德黑兰医科大学阿米拉拉姆医院胃肠病科）； Department of Computer Engineering, Science and Research Branch, Islamic Azad University（伊斯兰阿扎德大学科学与研究分校计算机工程系）

专题命中医学数据与评测：pathology(title)；分类 cs.CV

AI总结针对胃黏膜肠化生（GIM）公开数据集缺失的问题，构建了包含多模态内镜图像、视频及病理标注的数据集GIM-ENDO，涵盖六种主要内镜征象和亚型分级，以促进AI辅助诊断。

2607.16493 2026-07-21 cs.LG 新提交 74%

Leakage-Robust Evaluation and Data-Scale Sensitivity of Attention-Enhanced Multi-Task Learning for Joint Fault Diagnosis and Remaining Useful Life Estimation

用于联合故障诊断和剩余使用寿命估计的注意力增强多任务学习的泄漏鲁棒评估和数据规模敏感性

Md Mahamudur Rahaman Shamim, Md. Nuruzzaman, Zannatul Ferdus, Md Rajib Ahmed, Abieer Nwshad Anward, Mohammad Tooneer, Johir Uddin Khan, Khalid Hossen

机构 * Western Illinois University（西伊利诺伊大学）； Ahsanullah University of Science and Technology（阿山努拉科技大学）； Trine University（特莱恩大学）； Sapienza University of Rome（罗马第一大学）； Bangladesh University of Engineering and Technology（孟加拉工程技术大学）； Chittagong University of Engineering and Technology（吉大港工程技术大学）； Rajshahi University of Engineering & Technology (RUET)（拉杰沙希工程技术大学）

专题命中医学数据与评测：diagnosis(title)；分类 cs.LG

AI总结研究联合故障诊断和剩余使用寿命估计的多任务深度学习模型中，滑动窗口序列划分对性能的影响。采用AMTLNet架构，引入基于块的泄漏审核划分协议，通过实验得出任务稳定性与标签来源有关，贡献了评估协议和相关证据。

Comments Submitted in Next Research (Elsevier)

2604.26324 2026-04-30 cs.CV 74%

Federated Medical Image Classification under Class and Domain Imbalance exploiting Synthetic Sample Generation

联邦学习在类别和领域不平衡下的医学图像分类中利用合成样本生成

Martina Pavan, Matteo Caligiuri, Francesco Barbato, Pietro Zanuttigh

机构 * University of Padova（帕多瓦大学）； NIDEK Technologies Srl（NIDEK技术公司）

专题命中医学数据与评测：medical image(title)；分类 cs.CV

AI总结本文提出FedSSG框架，通过生成合成样本解决医学图像分类中的类别和领域不平衡问题，提升模型性能和泛化能力。

Comments Accepted at ICPR 2026, 13 pages, 3 figures, 5 tables

2604.03806 2026-04-07 cs.CV 74%

Bridging Restoration and Diagnosis: A Comprehensive Benchmark for Retinal Fundus Enhancement

弥合修复与诊断：一个全面的视网膜视网膜图像增强基准

Xuanzhao Dong, Wenhui Zhu, Xiwen Chen, Hao Wang, Xin Li, Yujian Xiong, Jiajun Cheng, Zhipeng Wang, Shao Tang, Oana Dumitrascu, Yalin Wang

机构 * Arizona State University（亚利桑那州立大学）； Clemson University（克莱姆森大学）； LinkedIn Corporation（领英公司）； Mayo Clinic（梅奥诊所）

专题命中医学数据与评测：diagnosis(title)；分类 cs.CV

AI总结本文提出EyeBench-V2基准，通过多维度临床对齐、专家指导评估和可操作见解，解决视网膜图像增强模型评估中的关键问题。

2603.22379 2026-03-25 cs.LG cs.AI cs.CL 74%

Instruction-Tuned, but Not More Verifiable Instruction-Following: A Cross-Task Diagnosis for LoRA Adapters

经过指令调优，但并非更可验证的指令遵循：LoRA适配器的跨任务诊断

Junyi Zou

机构 * Zjydiary Group（Zjydiary小组）

专题命中医学数据与评测：diagnosis(title)；分类 cs.LG

AI总结研究通过评估LoRA适配器在不同任务中的表现，发现名义上的训练目标与实际能力提升不一致，指出能力漂移现象，强调需进行跨任务评估以避免依赖名义标签。

Comments 12 pages, 5 figures, 6 tables

2603.20148 2026-03-23 cs.CV 74%

Can Large Multimodal Models Inspect Buildings? A Hierarchical Benchmark for Structural Pathology Reasoning

大型多模态模型能否检查建筑？一种用于结构病理推理的分层基准

Hui Zhong, Yichun Gao, Luyan Liu, Hai Yang, Wang Wang, Haowei Zhang, Xinhu Zheng

机构 * Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））； Hong Kong University（香港大学）

专题命中医学数据与评测：pathology(title)；分类 cs.CV

AI总结本文提出DefectBench基准，评估大型多模态模型在建筑表面检测中的能力，发现其在拓扑理解和语义理解方面表现优异，但在精确定位方面存在不足，并验证了零样本生成分割的可行性。

2406.15189 2026-03-23 cs.LG 74%

Causal Learning in Biomedical Applications: Krebs Cycle as a Benchmark

生物医学应用中的因果学习：柠檬酸循环作为基准

Xiaoyu He, Petr Ryšavý, Jakub Mareček

机构 * AI Center（人工智能中心）； Department of Computer Science（计算机科学系）； Czech Technical University in Prague（布拉格捷克技术大学）

专题命中医学数据与评测：biomedical(title)；分类 cs.LG

AI总结本文提出基于柠檬酸循环模拟的新基准数据集，用于评估因果发现方法在时间序列数据上的性能，包含真实因果图和多种评估指标。

1. 医学数据与评测 2119 篇

HUST bearing: a practical dataset for ball bearing fault diagnosis

Federated Model Aggregation via Self-Supervised Priors for Highly Imbalanced Medical Image Classification

Deep-learning models in medical image analysis: Detection of esophagitis from the Kvasir Dataset

A Domain-specific Perceptual Metric via Contrastive Self-supervised Representation: Applications on Natural and Medical Images

Improving Performance of Federated Learning based Medical Image Analysis in Non-IID Settings using Image Augmentation

GraphRareBench: An Auditable Graph-Evidence Benchmark for Phenotype-Driven Rare-Disease Diagnosis

SycoEval-EM: Sycophancy Evaluation of Large Language Models in Simulated Clinical Encounters for Emergency Care

LUMINA: A Multi-Vendor Mammography Benchmark with Energy Harmonization Protocol

Proof of Concept for Mammography Classification with Enhanced Compactness and Separability Modules

HYAMD High-Resolution Fundus Image Dataset for age related macular degeneration (AMD) Diagnosis

An OpenMind for 3D medical vision self-supervised learning

ClusMFL: A Cluster-Enhanced Framework for Modality-Incomplete Multimodal Federated Learning in Brain Imaging Analysis

One Shot GANs for Long Tail Problem in Skin Lesion Dataset using novel content space assessment metric

Quantitative Evaluation of Microstrip, Dipole, and L/C Loop pTx Arrays for UHF MR Imaging

Enable the Right to be Forgotten with Federated Client Unlearning in Medical Imaging

From Labels to Priors in Capsule Endoscopy: A Prior Guided Approach for Improving Generalization with Few Labels

NYCTALE: Neuro-Evidence Transformer for Adaptive and Personalized Lung Nodule Invasiveness Prediction

COVID-19 detection using ViT transformer-based approach from Computed Tomography Images

Assessing Privacy Leakage in Synthetic 3-D PET Imaging using Transversal GAN

Studying the Effects of Sex-related Differences on Brain Age Prediction using brain MR Imaging

OLIVES Dataset: Ophthalmic Labels for Investigating Visual Eye Semantics

A Global Benchmark of Algorithms for Segmenting Late Gadolinium-Enhanced Cardiac Magnetic Resonance Imaging

A Dataset of Laryngeal Endoscopic Images with Comparative Study on Convolution Neural Network Based Semantic Segmentation

GIM-ENDO: A Multimodal Endoscopic Image and Video Dataset for Gastric Intestinal Metaplasia Morphology and Pathology

Leakage-Robust Evaluation and Data-Scale Sensitivity of Attention-Enhanced Multi-Task Learning for Joint Fault Diagnosis and Remaining Useful Life Estimation

Federated Medical Image Classification under Class and Domain Imbalance exploiting Synthetic Sample Generation

Bridging Restoration and Diagnosis: A Comprehensive Benchmark for Retinal Fundus Enhancement

Instruction-Tuned, but Not More Verifiable Instruction-Following: A Cross-Task Diagnosis for LoRA Adapters

Can Large Multimodal Models Inspect Buildings? A Hierarchical Benchmark for Structural Pathology Reasoning

Causal Learning in Biomedical Applications: Krebs Cycle as a Benchmark