arXivDaily arXiv每日学术速递 周一至周五更新

科学与医疗

医学 AI

医学智能、临床 AI、医学影像、病理、诊断和医疗健康大模型。

2026-05-14 至 2026-05-14 共收录 40 信号源:cs.CV, cs.LG, q-bio, eess.IV, eess.SP

1. 医学影像 18 篇

2605.12560 2026-05-14 eess.IV cs.CV cs.LG 91%

Brain Tumor Classification in MRI Images: A Computationally Efficient Convolutional Neural Network

脑MRI图像中的肿瘤分类:一种计算高效的卷积神经网络

Md Fahimul Kabir Chowdhury, Jannatul Ferdous

机构 * Department of Computer Science and Engineering, University of North Texas, USA(北卡罗来纳州立大学计算机科学与工程系) Department of Electrical and Electronic Engineering, International Islamic University Chittagong, Bangladesh(伊斯兰国际大学查塔格昂分校电子与电气工程系)

专题命中 医学影像 :MRI(title,title_cn);diagnosis(abstract);分类 cs.CV、cs.LG、eess.IV;biomedical(journal_ref)

AI总结 本文提出一种轻量高效的卷积神经网络,用于多类脑肿瘤分类,利用MRI图像实现胶质瘤、脑膜瘤、垂体瘤和健康样本的准确分类,取得高准确率和ROC分数,同时参数更少。

Journal ref 2025 IEEE International Conference on Biomedical Engineering, Computer and Information Technology for Health (BECITHCON), pp. 633-638, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.06527 2026-05-14 physics.med-ph 90%

Low-dose, high-resolution CT of infant-sized lungs via propagation-based phase contrast

通过传播基相位对比技术实现婴儿肺部低剂量高分辨率CT

James A. Pollock, Kaye Morgan, Linda C. P. Croton, Emily J. Pryor, Kelly J. Crossley, Christopher J. Hall, Daniel Hausermann, Anton Maksimenko, Stuart B. Hooper, Marcus J. Kitchen

专题命中 医学影像 :CT(title,title_cn);diagnosis(abstract)

AI总结 利用传播基相位对比成像技术,优化了婴儿肺部CT成像的分辨率与辐射剂量,实现了比现有高分辨率CT更优的图像质量,符合澳大利亚婴儿胸部CT辐射标准。

Comments Updated to match published version

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.12562 2026-05-14 eess.IV cs.AI cs.CV 90%

Uncovering Latent Pathological Signatures in Pulmonary CT via Cross-Window Knowledge Distillation

通过跨窗口知识蒸馏揭示肺部CT中的潜在病理特征

Bo Peng, Wujian Xu, Kun Wang, Ximing Liao, Na Wang, Daqian Shi, Tian Li, Jing Gao, Johan Thygesen, Yingqun Ji, Honghan Wu

机构 * Institute of Health Informatics, University College London(伦敦大学学院健康信息学研究所) Department of Pulmonary and Critical Care Medicine, Shanghai East Hospital, School of Medicine, Tongji University(同济大学医学院 pulmonary and critical care medicine 部门,上海东方医院) Queen Mary University of London(伦敦女王玛丽大学) School of Health and Wellbeing, University of Glasgow(格拉斯哥大学健康与福祉学院)

专题命中 医学影像 :CT(title,title_cn);分类 cs.CV、eess.IV

AI总结 本文提出跨窗口知识蒸馏框架,通过教师模型学习最信息丰富的窗口,提升多窗口肺部CT分析的AUC,显著提高诊断性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.13813 2026-05-14 cs.CV 90%

JANUS: Anatomy-Conditioned Gating for Robust CT Triage Under Distribution Shift

JANUS:基于解剖的门控用于在分布偏移下鲁棒的CT分诊

Lavsen Dahal, Yubraj Bhandari, Geoffrey Rubin, Joseph Y. Lo

机构 * Center for Virtual Imaging Trials, RAI Labs, Department of Radiology, Duke University, Durham NC 27708, USA Electrical Computer Engineering, Pratt School of Engineering, Duke University, Durham, NC 27708, USA Department of Mathematics, Trinity College of Arts \& Sciences, Duke University, Durham, NC 27708, USA Department of Radiology

专题命中 医学影像 :CT(title,title_cn);分类 cs.CV

AI总结 JANUS通过解剖引导门控将视觉嵌入与宏放射组学先验条件相结合,提升CT分诊在不同病理和机构偏移下的鲁棒性,实现更高的AUROC和AUPRC。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.13560 2026-05-14 cs.LG 90%

Uncertainty-Aware Prediction of Lung Tumor Growth from Sparse Longitudinal CT Data via Bayesian Physics-Informed Neural Networks

基于贝叶斯物理信息神经网络的稀疏纵向CT数据肺癌肿瘤生长不确定性的预测

Lingfei Kong, Haoran Ma

机构 * Department of Mathematics, Vanderbilt University(范德比大学数学系) John A. Paulson School of Engineering and Applied Science, Harvard University(哈佛大学约翰·A·保罗森工程与应用科学学院)

专题命中 医学影像 :CT(title,title_cn);分类 cs.LG

AI总结 本文提出一种结合Gompertz生长动力学与低维贝叶斯推断的贝叶斯物理信息神经网络,用于从稀疏不规则纵向CT数据中预测肺癌肿瘤生长,通过两阶段推断策略估计后验预测分布和不确定性区间,实验显示模型能捕捉异质性肿瘤生长模式并保持合理预测精度。

Comments 8 pages, 15 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.15034 2026-05-14 q-bio.QM 90%

An MRI Atlas of the Human Fetal Brain: Reference and Segmentation Tools for Fetal Brain MRI Analysis

人类胎儿大脑的MRI图谱:用于胎儿大脑MRI分析的参考和分割工具

Mahdi Bagheri, Clemente Velasco-Annis, Jian Wang, Razieh Faghihpirayesh, Shadab Khan, Camilo Calixto, Camilo Jaimes, Lana Vasung, Abdelhakim Ouaalam, Onur Afacan, Simon K. Warfield, Caitlin K. Rollins, Ali Gholipour

专题命中 医学影像 :MRI(title,title_cn);分类 q-bio

AI总结 本文介绍了CRL-2025胎儿大脑图谱,提供了更详细的解剖信息和分割工具,用于胎儿大脑MRI分析和神经发育研究。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.13555 2026-05-14 physics.med-ph cs.AI 89%

Generating synthetic computed tomography for radiotherapy: SynthRAD2025 challenge report

生成放射治疗用合成计算机断层扫描:SynthRAD2025挑战报告

Viktor Rogowski, Maarten L. Terpstra, Niklas Wahl, Florian Kamp, Erik van der Bijl, Arthur Jr. Galapon, Christopher Kurz, Bowen Xin, Zhengxiang Sun, Hollie Min, Gregg Belous, Jason Dowling, Yan Xia, Siyuan Mei, Fuxin Fan, Arthur Longuefosse, Javier Sequeiro Gonzalez, Miguel Diaz Benito, Alvaro Garcia Martin, Fabien Baldacci, Valentin Boussot, Cédric Hémon, Jean-Claude Nunes, Jean-Louis Dillenseger, Zhiyuan Zhang, Jinghua Cai, Han Bing, Tan Zuopeng, Ricardo Brioso, Daniele Loiacono, Guillaume Landry, Adrian Thummerer, Matteo Maspero

机构 * Radiation Physics, Department of Hematology, Oncology Radiation Physics, Skåne University Hospital, Lund, Sweden Medical Radiation Physics, Department of Clinical Sciences Lund, Lund University, Lund, Sweden Radiotherapy Department, University Medical Center Utrecht, Utrecht, The Netherlands Computational Imaging Group for MR Diagnostics \& Therapy, University Medical Center Utrecht, Utrecht, The Netherlands Division of Medical Physics in Radiation Oncology, Deutsches Krebsforschungszentrum (DKFZ), Heidelberg, Germany Heidelberg Institute for Radiation Oncology (HIRO) National Center for Radiation Research in Oncology (NCRO), Heidelberg, Germany Department of Radiation Oncology Cyberknife Center, University Hospital of Cologne, Cologne, Germany Department of Radiation Oncology, Radboud University Medical Center, Nijmegen, The Netherlands Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands Department of Radiation Oncology, LMU University Hospital, LMU Munich, Munich, Germany Bavarian Cancer Research Center (BZKF), Munich, Germany Australian eHealth Research Center, CSIRO, Brisbane, Australia School of Computer Science, University of Sydney, Sydney, Australia Department of Orthodontics Pattern Recognition Lab, FAU Erlangen-Nuremberg, Germany RIKEN Center for Integrative Medical Sciences, Tokyo, Japan Erasmus Mundus Joint Master's Degree IPCVai, University of Bordeaux, France Computer Science, Huazhong University of Science Huazhong University of Science Canon Medical Systems (China) CO., LTD., Beijing, China Department of Radiation Oncology, Inselspital, Bern University Hospital University of Bern, Bern, Switzerland

专题命中 医学影像 :MRI(summary_cn,abstract);CT(summary_cn,abstract);medical image(comments)

AI总结 SynthRAD2025挑战赛评估了合成CT生成方法在头颈、胸腔和腹部2362名患者中的性能,通过图像相似性、分割和剂量学指标验证了深度学习在生成CT中的有效性,揭示了MRI到CT转换的持续挑战。

Comments 59 pages total: 26 pages main article + supplementary material; 8 figures in the main manuscript and 3 supplementary figures. Currently under review at the journal Medical Image Analysis (MIA)

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.12753 2026-05-14 eess.IV cs.CV cs.LG 89%

Optimization in Sparse 2D to Dense 3D Weakly Supervised Learning: Application to Multi-Label Segmentation of Large ex vivo MRI Data

稀疏2D到密集3D弱监督学习的优化:应用于大体积体外MRI数据的多标签分割

Paul Hoareau, Kuan Yi Wang, Brandon Bujak, Roy Sun, Govind Nair, Irene Cortese, Charidimos Tsagkas, Daniel Reich, Julien Cohen-Adad

机构 * NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal(神经多极实验室,生物医学工程学院,蒙特利尔理工学院) École Centrale de Lyon(里昂中央理工学院) Mila - Quebec AI Institute(魁北克人工智能研究所) Functional Neuroimaging Unit, CRIUGM, University of Montreal(功能神经影像单元,CRIUGM,蒙特利尔大学) Translational Neuroradiology Section, National Institute of Neurological Disorders and Stroke, National Institutes of Health(转化神经放射学部门,国家神经疾病与中风研究所,国家卫生研究院) Translational Imaging in Neurology (ThINk) Basel, Department of Biomedical Engineering, Faculty of Medicine, University Hospital Basel and University of Basel(神经学转化成像(ThINk)巴塞尔,生物医学工程系,医学院,巴塞尔大学医院和巴塞尔大学) Neurologic Clinic and Policlinic, Departments of Medicine, University Hospital Basel, Switzerland(神经科诊所和多科诊所,医学院,巴塞尔大学医院,瑞士) Research Center for Clinical Neuroimmunology and Neuroscience Basel (RC2NB), University Hospital Basel and University of Basel, Switzerland(临床神经免疫学和神经科学巴塞尔研究中心(RC2NB),巴塞尔大学医院和巴塞尔大学,瑞士) National Institute of Neurological Disorders and Stroke, National Institutes of Health(国家神经疾病与中风研究所,国家卫生研究院) Centre de recherche du CHU Sainte-Justine, Université de Montréal, Montreal, QC, Canada(圣朱斯特医院研究中心,蒙特利尔大学,蒙特利尔,魁北克,加拿大) Quantitative MRI core facility, NINDS, NIH(定量MRI核心设施,NINDS,NIH) Experimental Immunotherapeutics Unit, Division of Neuroimmunology and Neurovirology, NINDS, NIH(实验免疫治疗单元,神经免疫学和神经病毒学部门,NINDS,NIH)

专题命中 医学影像 :MRI(title,title_cn);分类 cs.CV、cs.LG、eess.IV;biomedical(comments)

AI总结 本文研究了稀疏2D到密集3D弱监督学习中多类分割的正则化需求差异,通过2D教师网络生成伪标签训练3D学生网络,发现2D教师需强空间增强和软标签正则化以克服数据稀缺,但传播至3D学生网络会降低性能。

Comments 19 pages. Submitted to Machine Learning for Biomedical Imaging (MELBA). Code and models: https://github.com/ivadomed/model_seg_sc-gm-lesion_human_ms_exvivo_t2star

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.12917 2026-05-14 cs.CV cs.LG 88%

Adaptive Conformal Prediction for Reliable and Explainable Medical Image Classification

自适应置信区间用于可靠且可解释的医学图像分类

One Octadion, Novanto Yudistira, Lailil Muflikhah

机构 * Faculty of Computer Science, Universitas Brawijaya(博雅大学计算机科学学院)

专题命中 医学影像 :medical image(title);CT(abstract,abstract_cn);medical AI(abstract);pathology(abstract)

AI总结 本文提出自适应Lambda准则改进RAPS,提升医学图像分类的可靠性与可解释性,实验表明其在跨域验证中表现优异。

Comments To appear in IEA/AIE 2026 (Springer LNAI)

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.13686 2026-05-14 cs.CV cs.AI 84%

Cross Modality Image Translation In Medical Imaging Using Generative Frameworks

利用生成框架在医学影像中实现跨模态图像翻译

Giulia Romoli, Alessia Capoccia, Filippo Ruffini, Francesco Di Feola, Luca Boldrini, Arturo Chiti, Renato Cuocolo, Tugba Akinci D'Antonoli, Fatemeh Darvizeh, Marcello Di Pumpo, Bradley J. Erickson, Liu Fang, Deborah Fazzini, Paola Feraco, Fabrizia Gelardi, Francesco Gossetti, Ana Isabel Hernáiz Ferrer, Michail E. Klontzas, Seyedmehdi Payabvash, Katrine Riklund, Sara N. Strandberg, Valerio Guarrasi, Paolo Soda

机构 * Department of Diagnostics and Intervention, Radiation Physics, Biomedical Engineering, Umeå University(诊断与介入部门、放射物理、生物医学工程,乌梅大学) Unit of Artificial Intelligence and Computer Systems, Department of Engineering, Università Campus Bio-Medico di Roma(人工智能与计算机系统单位,工程部门,罗马生物医学学院) Vita-Salute San Raffaele University(维塔-萨拉特·桑拉法埃莱大学) Department of Medicine, Surgery and Dentistry, University of Salerno(医学、外科和牙科部门,萨勒诺大学) Division of Diagnostic and Interventional Neuroradiology, Department of Radiology, University Hospital Basel(诊断和介入神经放射学部门,放射学部门,巴塞尔大学医院) Department of Pediatric Radiology, University Children’s Hospital Basel(儿科放射学部门,巴塞尔儿童医院) Department of Life Science and Public Health, Università Cattolica del Sacro Cuore(生命科学与公共健康部门,圣心大学) Athinoula A. Martinos Center for Biomedical Imaging(阿提诺拉A·马里诺斯生物医学成像中心) Artificial Intelligence and Translational Imaging (ATI) Lab, Department of Radiology, School of Medicine, University of Crete(人工智能与转化成像(ATI)实验室,放射学部门,医学院,克里特大学) Division of Radiology, Department of Clinical Science, Intervention and Technology (CLINTEC), Karolinska Institute(放射学部门,临床科学、介入和科技(CLINTEC)部门,卡罗林斯卡研究所) Columbia University Medical Center(哥伦比亚大学医学中心) Department of Diagnostics and intervention, Diagnostic radiology, Umeå University(诊断与介入部门,诊断放射学,乌梅大学)

专题命中 医学影像 :MRI(abstract,abstract_cn);CT(abstract,abstract_cn);medical image(abstract);分类 cs.CV

AI总结 本文提出了一种标准化的3D医学图像跨模态翻译评估框架,比较了七种生成模型在不同数据集上的性能,揭示了GANs在不同任务中优于潜在生成模型,并发现合成影像在临床应用中难以区分。

详情

展开后加载摘要…

URL PDF HTML 收藏
2301.12647 2026-05-14 physics.med-ph 82%

3DMPR -- A robust morphological approach for applying phase retrieval in proximity to highly-attenuating objects in CT

3DMPR -- 一种稳健的形态学方法,用于在接近高衰减物体时应用相位检索

J. A. Pollock, L. C. P. Croton, K. S. Morgan, K. J. Crossley, M. J. Wallace, G. A. Buckley, S. B. Hooper, M. J. Kitchen

专题命中 医学影像 :CT(title,summary_cn)

AI总结 本文提出3DMPR方法,结合形态学操作和相位检索,提升CT图像质量,减少辐射暴露,实现高精度3D成像。

Comments Updated to match published version

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.13798 2026-05-14 cs.CV 81%

VoxCor: Training-Free Volumetric Features for Multimodal Voxel Correspondence

VoxCor:无需训练的体积分量用于多模态体素对应

Guney Tombak, Ertunc Erdil, Ender Konukoglu

机构 * Biomedical Image Computing Group, ETH Zurich(生物医学图像计算组,苏黎世联邦理工学院) The LOOP Zurich – Medical Research Center(苏黎世医疗研究中心)

专题命中 医学影像 :CT(abstract,abstract_cn);medical image(abstract);MRI(abstract_cn);分类 cs.CV

AI总结 VoxCor通过冻结的2D Vision Transformer基础模型生成可重用的体积分量表示,无需训练即可实现跨模态和跨主体的体素对应,提升跨模态和跨主体的转换性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.13059 2026-05-14 cs.CV 81%

BrainAnytime: Anatomy-Aware Cross-Modal Pretraining for Brain Image Analysis with Arbitrary Modality Availability

BrainAnytime: 基于解剖结构的跨模态预训练用于脑图像分析,支持任意模态可用性

Guangqian Yang, Tong Ding, Wenlong Hou, Yue Xun, Ye Du, Qian Niu, Shujun Wang

机构 * Department of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China(生物医学工程系,香港理工大学,香港特别行政区,中国) Department of Technology Management for Innovation, The University of Tokyo, Japan(创新技术管理系,东京大学,日本) Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong SAR, China(数据科学与人工智能系,香港理工大学,香港特别行政区,中国)

专题命中 医学影像 :MRI(summary_cn,abstract);分类 cs.CV

AI总结 BrainAnytime通过跨模态蒸馏和解剖引导课程掩码,在共享的3D掩码自动编码器中学习MRI与PET的结构-分子对应关系,实现对任意模态可用性的统一预训练,提升多任务性能。

Comments Early accepted by MICCAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.12650 2026-05-14 cs.CV 79%

CRAFT: Clinical Reward-Aligned Finetuning for Medical Image Synthesis

CRAFT:面向医学图像合成的临床对齐微调

Yunsung Chung, Alex El Darzi, Carlo El Khoury, Han Feng, Nassir Marrouche, Jihun Hamm

机构 * Department of Computer Science, Tulane University(路易斯安那大学计算机科学系) School of Medicine, Tulane University(路易斯安那大学医学院)

专题命中 医学影像 :medical image(title);pathology(abstract);分类 cs.CV

AI总结 本文提出CRAFT框架,通过临床对齐评分和奖励优化提升医学图像生成质量,减少幻觉生成,提升分类性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.09020 2026-05-14 cs.CV 77%

The Direct Integration Theorem: A Rigorous Framework for Consistent Discrete Solutions of the Inverse Radon Problem

直接积分定理:逆Radon问题一致离散解的严格框架

Mikhail G. Mozerov

机构 * Institute for Information Transmission Problems, Russian Academy of Sciences(信息传输问题研究所,俄罗斯科学院)

专题命中 医学影像 :CT(summary_cn,abstract_cn);分类 cs.CV

AI总结 本文提出直接积分定理,通过经典中心切片定理推导,为CT中连续到离散转换提供数学一致方法,避免频域插值和常规梯度滤波,解决零频奇点和频域插值误差问题,实现高精度图像重建。

Comments Submitted to IEEE TPAMI. Code and data available at https://github.com/Mozerov-iitp/radon-dit/

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.12544 2026-05-14 physics.med-ph 75%

Dual-Correction Physics-Informed Neural Networks for Hemodynamic Reconstruction from Sparse Data

双校正物理信息神经网络用于从稀疏数据重建脑血管血流

Jingtai Song, Qinsheng Zhu, Xiaodong Xing, Yufeng Tang, Zhiyun Zhang, Xianwen Zhang, Hao Wu

专题命中 医学影像 :MRI(abstract,abstract_cn);CT(abstract_cn)

AI总结 本文提出双校正物理信息神经网络,用于解决曲颈内动脉弯曲段血流重建难题,通过因果解耦策略和高阶物理损失函数提升稀疏数据下的重建精度与鲁棒性。

Comments 10 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.24649 2026-05-14 cs.CV 70%

MedOpenClaw and MedFlowBench: Auditing Medical Agents in Full-Study Workflows

MedOpenClaw 和 MedFlowBench:在完整研究流程中审计医疗代理

Weixiang Shen, Chengzhi Shen, Yanzhu Hu, Che Liu, Junde Wu, Jiayuan Zhu, Xiao Han, Zongyue Li, Jingpei Wu, Min Xu, Daguang Xu, Yueming Jin, Benedikt Wiestler, Daniel Rueckert, Jiazhen Pan

机构 * Technical University of Munich(慕尼黑技术大学) TUM University Hospital(TUM大学医院) LMU Munich(慕尼黑大学) Imperial College London(伦敦帝国理工学院) University of Oxford(牛津大学) Carnegie Mellon University(卡内基梅隆大学) NVIDIA(NVIDIA公司) National University of Singapore(新加坡国立大学) Munich Center for Machine Learning(慕尼黑机器学习中心)

专题命中 医学影像 :pathology(abstract);radiology(abstract);分类 cs.CV

AI总结 本文提出 MedFlowBench 和 MedOpenClaw,用于评估医疗影像代理在完整研究流程中生成可审计证据的能力,发现仅依赖答案评分不够,需结合正确证据验证。

Comments 33 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.14244 2026-05-14 eess.IV cs.AI cs.CV 62%

Reinforcement Learning for Unsupervised Domain Adaptation in Spatio-Temporal Echocardiography Segmentation

强化学习用于空间时间超声分割的无监督领域适应

Arnaud Judge, Nicolas Duchateau, Thierry Judge, Roman A. Sandler, Joseph Z. Sokol, Christian Desrosiers, Olivier Bernard, Pierre-Marc Jodoin

机构 * Department of Computer Science, University of Sherbrooke(谢布鲁克大学计算机科学系) INSA, Universite Claude Bernard Lyon 1, CNRS UMR 5220, Inserm U1206, CREATIS(里昂1大学INSA、CNRS UMR 5220、Inserm U1206、CREATIS) Dep. of Software and Information Technology Engineering, École de technologie supérieure(蒙特利尔工程学院软件与信息技术工程系) Institut Universitaire de France (IUF)(法国国家科学院(IUF))

专题命中 医学影像 :medical image(abstract);分类 cs.CV、eess.IV

AI总结 本文提出RL4Seg3D框架,通过强化学习提升空间时间超声分割的准确性、解剖有效性与时间一致性,并提供鲁棒的不确定性估计器。

Comments 13 pages, accepted for publication in IEEE TMI

详情

展开后加载摘要…

URL PDF HTML 收藏

2. 临床大模型 1 篇

2605.12204 2026-05-14 cs.DB cs.NE 50%

Graph-Grounded Optimization: Rao-Family Metaheuristics, Classical OR, and SLM-Driven Formulation over Knowledge Graphs

图引导优化:Rao家族元启发式算法、经典运筹学和SLM驱动的公式在知识图谱上的应用

Madhulatha Mandarapu, Sandeep Kunkunuru

专题命中 临床大模型 :biomedical(abstract)

AI总结 本文提出图引导优化方法,通过Cypher查询从属性知识图谱中获取优化问题的变量、约束和目标系数,对比Rao家族元启发式算法与OR-tools在不同场景下的表现,揭示图引导公式在数据质量上的挑战。

Comments 14 pages, 8 figures, 7 public-domain KG-backed problems

详情

展开后加载摘要…

URL PDF HTML 收藏

3. 诊断辅助 7 篇

2605.13730 2026-05-14 cs.LG cs.AI cs.CV 76%

Robust and Explainable Bicuspid Aortic Valve Diagnosis Using Stacked Ensembles on Echocardiography

基于超声心动图的稳健且可解释的二叶式主动脉瓣诊断方法:使用堆叠集成

Christos Chrysanthos Nikolaidis, Vasileios Sachpekidis, Nikolas Moustakidis, Theofilos Moustakidis, Pavlos S. Efraimidis

机构 * Department of Electrical and Computer Engineering, Democritus University of Thrace(电气与计算机工程系,德莫克里特大学)

专题命中 诊断辅助 :diagnosis(title);分类 cs.CV、cs.LG

AI总结 本文提出了一种基于超声心动图的稳健且可解释的二叶式主动脉瓣诊断方法,利用堆叠集成技术对常规获取的胸骨旁长轴 cine 循环进行分类,实现了高精度的二叶式与三叶式主动脉瓣区分。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.02560 2026-05-14 cs.LG cs.AI cs.CV 73%

Auditing Sybil: Explaining Deep Lung Cancer Risk Prediction Through Generative Interventional Attributions

审计Sybil:通过生成干预性归因解释深度肺癌风险预测

Bartlomiej Sobieski, Jakub Grzywaczewski, Karol Dobiczek, Mateusz Wójcik, Tomasz Bartczak, Patryk Szatkowski, Przemysław Bombiński, Matthew Tivnan, Przemyslaw Biecek

机构 * National Lung Screening Trial Research Team(国家肺癌筛查试验研究组)

专题命中 诊断辅助 :CT(abstract,abstract_cn);分类 cs.CV、cs.LG

AI总结 本文提出S(H)NAP框架,通过专家放射科医生验证的生成干预性归因,揭示Sybil模型在区分恶性肺结节与良性病变时的失效模式,包括对不合理伪影的敏感性和径向偏差。

Comments ICML 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.12570 2026-05-14 cs.CV 70%

M3Net: A Macro-to-Meso-to-Micro Clinical-inspired Hierarchical 3D Network for Pulmonary Nodule Classification

M3Net:一种受临床诊断流程启发的宏-中-微三级层次3D网络用于肺结节分类

Jinyue Li, Yuzhou Yu, Jingjing Yang, Meng Fu, Yani Zhang, Shuyao He, Dianlong Ge, Xin Ning, Yannan Chu, Qiankun Li

机构 * Hefei Cancer Hospital of CAS, Institute of Health and Medical Technology, Hefei Institutes of Physical Science, Chinese Academy of Sciences(中国科学院合肥医疗健康研究院、健康与医疗技术研究所、物理研究所) University of Science and Technology of China(中国科学技术大学) Graduate School, Bengbu Medical College(蚌埠医疗学院研究生院) Department of Pulmonary and Critical Care Medicine, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China (USTC)(中国科学技术大学附属第一医院呼吸与危重症医学科、生命科学与医学学院) Northeastern University(东北大学) Institute of Semiconductors, Chinese Academy of Sciences(中国科学院半导体研究所) College of Computing and Data Science (CCDS), Nanyang Technological University(南洋理工大学计算与数据科学学院)

专题命中 诊断辅助 :CT(abstract);diagnosis(abstract);分类 cs.CV

AI总结 本文提出M3Net,通过多尺度上下文信息整合,提升肺结节分类的准确性和可解释性,在LIDC-IDRI和USTC-FHLN数据集上取得最佳性能。

Comments Published in Information Fusion (2026), 15 pages, 5 figures

Journal ref Information Fusion, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.13148 2026-05-14 cs.LG cs.CV 62%

Understanding Generalization through Decision Pattern Shift

通过决策模式偏移理解泛化

Huiqi Deng, Yibo Li, Quanshi Zhang, Peng Zhang, Hongbin Pei, Xia Hu

机构 * Xi’an Jiaotong University(西安交通大学) Shanghai Jiao Tong University(上海交通大学) Shanghai Artificial Intelligence Laboratory(上海人工智能实验室)

专题命中 诊断辅助 :diagnosis(abstract);分类 cs.CV、cs.LG

AI总结 本文提出决策模式偏移(DPS)作为泛化的新视角,通过分析模型内部决策模式的稳定性评估泛化能力,揭示泛化是内部决策机制系统性偏移的过程,并展示DPS在不同泛化退化场景中的统一解释。

Comments 14pages, 12figures, computer vision and pattern recognition

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.22966 2026-05-14 cs.CY cs.AI 50%

Institutions for the Post-Scarcity of Judgment

判断后稀缺性的机构

Lauri Lovén

机构 * Future Computing Group, University of Oulu(奥卢大学未来计算组)

专题命中 诊断辅助 :diagnosis(abstract)

AI总结 本文探讨AI革命中判断能力的扩张及其对机构体系的影响,指出判断能力的边际成本接近零,而验证信号、合法性、真实来源和整合能力成为稀缺资源,提出重新设计机构体系的政策议程。

Comments 5 pages, 9 references. Submitted to Communications of the ACM (Opinion section). Comments welcome

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.13177 2026-05-14 physics.optics 50%

Volumetric Optical Scattering Neural Networks

体积分散神经网络

Xuhao Luo, Qiang Song, Weiwei Cai, Lei Chen, Enbo Yang, Hao Wang, Zhipei Sun, Yueqiang Hu, Joel K. W. Yang, Huigao Duan

专题命中 诊断辅助 :diagnosis(abstract)

AI总结 本文提出体积分散神经网络,利用密集排列的弱散射体实现三维局部连接的光计算介质,实现高密度、高紧凑性和高效光学计算,应用于嵌入式光学智能和AI领域。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.12807 2026-05-14 stat.CO cs.IT math.IT 50%

Multi-Marginal Couplings for Metropolis-Hastings

多边缘耦合用于Metropolis-Hastings

Buu Phan, Gergely Flamich, Ashish Khisti, Shahab Asoodeh

专题命中 诊断辅助 :diagnosis(abstract)

AI总结 本文提出多边缘耦合方法用于改进Metropolis-Hastings链的收敛诊断,通过引入自然目标函数和分布耦合分析,提升高维设置下的共聚速率和效率。

详情

展开后加载摘要…

URL PDF HTML 收藏

4. 医疗多模态 1 篇

2601.22853 2026-05-14 cs.CV 57%

Inference-Time Dynamic Modality Selection for Incomplete Multimodal Classification

推理时动态模态选择用于不完整多模态分类

Siyi Du, Xinzhe Luo, Declan P. O'Regan, Chen Qin

机构 * Department of Electrical and Electronic Engineering & I-X(电气与电子工程系及I-X)

专题命中 医疗多模态 :medical image(abstract);分类 cs.CV

AI总结 本文提出DyMo框架,通过动态选择并融合可靠恢复的模态,解决不完整多模态学习中的丢弃或填补困境,实验显示其在多种缺失数据场景下优于现有方法。

Comments 27 pages (including appendix), accepted by ICLR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏

5. 生物医学文本 6 篇

2605.13451 2026-05-14 cs.CL 85%

LongBEL: Long-Context and Document-Consistent Biomedical Entity Linking

LongBEL:长上下文和文档一致的生物医学实体链接

Adam Remaki, Xavier Tannier, Christel Gérardin

机构 * Sorbonne Université, Inserm, Université Sorbonne Paris Nord, Limics(索邦大学、国家医学研究院、巴黎索邦大学北校区、Limics) Service de médecine interne, Hôpital Tenon, Assistance Publique - Hôpitaux de Paris(内科服务,Tenon医院,巴黎公共医院)

专题命中 生物医学文本 :biomedical(title,abstract);CT(abstract,abstract_cn)

AI总结 LongBEL通过结合全文上下文和预测记忆,提升生物医学实体链接的文档一致性,尤其在概念频繁重复的文档中表现突出。

Comments 9 pages, 2 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.00586 2026-05-14 q-bio.MN cs.AI cs.LG 60%

RAG-GNN: Integrating Retrieved Knowledge with Graph Neural Networks for Precision Medicine

RAG-GNN:将检索到的知识与图神经网络结合用于精准医学

Hasi Hays, William J. Richardson

机构 * Department of Chemical Engineering, University of Arkansas(化学工程系,阿肯色大学)

专题命中 生物医学文本 :biomedical(abstract);分类 cs.LG、q-bio

AI总结 RAG-GNN通过整合图神经网络与动态检索的文献知识,提升了癌症信号功能聚类的精度,同时验证了检索增强对精准医学应用的互补性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.13088 2026-05-14 cs.LG 57%

Bayesian Nonparametric Mixed-Effect ODEs with Gaussian Processes

基于高斯过程的贝叶斯非参数混合效应微分方程

Julien Martinelli, Maksim Sinelnikov, Harri Lähdesmäki, Quentin Clairon, Mélanie Prague

机构 * Aalto University(阿alto大学) Univ. Bordeaux, INSERM BPH, U1219, Inria SISTM team, VRI, France(波尔多大学,INSERM BPH,U1219,Inria SISTM团队,VRI,法国) Inria SISTM team(Inria SISTM团队)

专题命中 生物医学文本 :biomedical(abstract);分类 cs.LG

AI总结 本文提出MEGPODE模型,通过高斯过程先验分解每个主体的动力学场,实现对异质性动态系统的非参数混合效应建模,提升群体动力学恢复和个体轨迹预测性能。

详情

展开后加载摘要…

URL PDF HTML 收藏