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。

2026-02-06 至 2026-02-06 共收录 35 信号源:cs.CV, cs.LG, q-bio, eess.IV, eess.SP

1. 医学影像 15 篇

2407.18967 2026-02-06 eess.IV eess.SP 81%

GroupCDL: Interpretable Denoising and Compressed Sensing MRI via Learned Group-Sparsity and Circulant Attention

GroupCDL: 通过学习的组稀疏性和循环注意力实现可解释的去噪和压缩感知MRI

Nikola Janjusevic, Amirhossein Khalilian-Gourtani, Adeen Flinker, Li Feng, Yao Wang

专题命中 医学影像 :MRI(title,abstract);分类 eess.IV、eess.SP

AI总结 本文提出了一种基于学习组稀疏性和循环注意力的可解释卷积网络,用于实现高效的图像去噪和压缩感知MRI重建。

Comments 13 pages, 8 figures. arXiv admin note: substantial text overlap with arXiv:2306.01950

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.05937 2026-02-06 cs.CV 79%

Multi-Scale Global-Instance Prompt Tuning for Continual Test-time Adaptation in Medical Image Segmentation

多尺度全局-实例提示微调用于医学图像分割中的持续测试时适应

Lingrui Li, Yanfeng Zhou, Nan Pu, Xin Chen, Zhun Zhong

机构 * School of Computer Science, University of Nottingham, UK(诺丁汉大学计算机科学学院) School of Artificial Intelligence, Shenzhen University, China(深圳大学人工智能学院) Department of Information Engineering and Computer Science, University of Trento, Italy(特伦托大学信息工程与计算机科学系) School of Computer Science and Information Engineering, Hefei University of Technology, China(合肥工业大学计算机科学与信息工程学院)

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

AI总结 本文提出多尺度全局-实例提示微调方法,通过增强提示多样性并结合全局和实例级知识,提升医学图像分割中的持续测试时适应性能。

Comments 8 pages, BIBM2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.11963 2026-02-06 eess.IV 79%

Noisy MRI Reconstruction via MAP Estimation with an Implicit Deep-Denoiser Prior

通过隐式深度去噪先验进行噪声MRI重建

Nikola Janjušević, Amirhossein Khalilian-Gourtani, Yao Wang, Li Feng

专题命中 医学影像 :MRI(title,abstract);分类 eess.IV

AI总结 本文提出ImMAP框架,通过整合噪声模型到MAP中,提升MRI在现实噪声下的重建可靠性与可解释性。

Comments 6 pages, 5 figures, conference paper

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.05426 2026-02-06 cs.CV 77%

Multi-AD: Cross-Domain Unsupervised Anomaly Detection for Medical and Industrial Applications

多域无监督异常检测:医疗和工业应用中的Multi-AD

Wahyu Rahmaniar, Kenji Suzuki

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

AI总结 Multi-AD通过结合SE块、知识蒸馏和判别器网络,实现跨域医疗和工业图像的高效异常检测,取得最佳AUROC表现。

Comments 28 pages, 8 figures

Journal ref Pattern Recognition 172 (Part B) (April 2026) 112486

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.01031 2026-02-06 cs.CV 70%

Pediatric Wrist Fracture Detection Using Feature Context Excitation Modules in X-ray Images

儿童腕部骨折检测:基于X射线图像的特征上下文激发模块

Rui-Yang Ju, Chun-Tse Chien, Enkaer Xieerke, Jen-Shiun Chiang

机构 * Graduate Institute of Networking and Multimedia(网络与多媒体研究生院) National Taiwan University(台湾大学) Department of Electrical and Computer Engineering(电子工程系) Tamkang University(Tamkang大学) College of Energy and Mechanical Engineering(能源与机械工程学院) Shanghai University of Electric Power(上海电力大学)

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

AI总结 本研究提出FCE-YOLOv8模型,通过不同特征上下文激发模块提升X射线图像中儿童腕部骨折检测性能,取得更高准确率和更优推理效率。

Comments arXiv admin note: text overlap with arXiv:2407.03163

Journal ref IET Image Process. 20 (2026) e70269

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.00160 2026-02-06 q-bio.QM stat.AP 68%

How reproducible are data-driven subtypes of Alzheimer's disease atrophy?

阿尔茨海默病萎缩数据驱动亚型的可重复性如何?

Emma Prevot, Cameron Shand, Neil Oxtoby, for Alzheimer's Disease Neuroimaging Initiative

专题命中 医学影像 :MRI(abstract);diagnosis(abstract);分类 q-bio

AI总结 本研究评估了SuStaIn算法在不同数据集中的亚型一致性,发现三种主要亚型及罕见变种,强调算法的可靠性并指出需提升数据集多样性以增强应用。

Journal ref Journal of Alzheimer's Disease (2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.05738 2026-02-06 eess.IV cs.CV 62%

Disc-Centric Contrastive Learning for Lumbar Spine Severity Grading

以椎间盘为中心的对比学习用于腰椎严重程度分级

Sajjan Acharya, Pralisha Kansakar

机构 * Independent Researchers(独立研究者)

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

AI总结 本文提出以椎间盘为中心的对比学习方法,通过对比预训练和椎间盘级微调,提升腰椎管狭窄严重程度分级的准确率和鲁棒性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.11249 2026-02-06 eess.IV cs.CV 62%

YOLOv9 for Fracture Detection in Pediatric Wrist Trauma X-ray Images

YOLOv9在儿童手腕创伤X光图像骨折检测中的应用

Chun-Tse Chien, Rui-Yang Ju, Kuang-Yi Chou, Jen-Shiun Chiang

机构 * Department of Electrical and Computer Engineering, Tamkang University(潭府大学电气与计算机工程系) Graduate Institute of Networking and Multimedia, National Taiwan University(台湾大学网络与多媒体研究所) School of Nursing, National Taipei University of Nursing and Health Sciences(台北护理大学护理学院)

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

AI总结 本文提出使用YOLOv9算法在儿童手腕创伤X光图像中检测骨折,通过数据增强提升模型性能,实验结果显示mAP值提升3.7%。

Comments Accepted by Electronics Letters

Journal ref Electron. Lett. 60 (2024) e13248

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.05812 2026-02-06 cs.LG stat.ML 57%

Principled Confidence Estimation for Deep Computed Tomography

深度计算层析成像的原理性置信度估计

Matteo Gätzner, Johannes Kirschner

机构 * ETH Zürich(苏黎世联邦理工学院) Swiss Data Science Center(瑞士数据科学中心)

专题命中 医学影像 :CT(abstract);分类 cs.LG

AI总结 本文提出了一种原理性的置信度估计框架,用于深度学习CT重建,通过理论覆盖保证和更紧的置信区域,提高医学影像的不确定性感知能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.05420 2026-02-06 cs.CV cs.AI 57%

Disco: Densely-overlapping Cell Instance Segmentation via Adjacency-aware Collaborative Coloring

Disco:通过邻接感知的协作着色实现密集重叠细胞实例分割

Rui Sun, Yiwen Yang, Kaiyu Guo, Chen Jiang, Dongli Xu, Zhaonan Liu, Tan Pan, Limei Han, Xue Jiang, Wu Wei, Yuan Cheng

机构 * Shanghai Academy of Artificial Intelligence for Science(上海人工智能科学研究院) Fudan University(复旦大学) Shanghai Innovation Institute(上海创新研究院) School of Life Sciences and Biotechnology, Shanghai Jiao Tong University(上海交通大学生命科学与生物技术学院) Lingang Laboratory(临港实验室) Renji Hospital, School of Medicine, Shanghai Jiao Tong University(仁济医院,上海交通大学医学院)

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

AI总结 Disco通过邻接感知协作着色解决复杂细胞实例分割问题,结合拓扑标注与深度学习解决冲突。

Comments 17 pages, 10 figures; ICLR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.13901 2026-02-06 physics.med-ph eess.IV physics.app-ph 57%

Self-Portrait of the Focusing Process in Speckle: II. Gouy Phase Shift for Defocus Correction and Pixel Depth Reassignment

点散射过程的自我画像:II. 用于失焦校正的Gouy相移与像素深度重新分配

Flavien Bureau, Emma Brenner, Naiara Korta Martiartu, Elsa Giraudat, Arthur Le Ber, William Lambert, Louis Carmier, Aymeric Guibal, Mathias Fink, Alexandre Aubry

专题命中 医学影像 :diagnosis(abstract);分类 eess.IV

AI总结 本文提出通过优化声速模型和Gouy相移来校正失焦和像差,提升超声成像的深度和精度。

Comments 43 pages, 8 figures, 3 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.09329 2026-02-06 cs.CV 57%

YOLOv8-AM: YOLOv8 Based on Effective Attention Mechanisms for Pediatric Wrist Fracture Detection

YOLOv8-AM:基于有效注意力机制的YOLOv8用于儿童腕骨骨折检测

Chun-Tse Chien, Rui-Yang Ju, Kuang-Yi Chou, Enkaer Xieerke, Jen-Shiun Chiang

机构 * Department of Electrical and Computer Engineering, Tamkang University, New Taipei City, 251301, Taiwan(电子工程系,潭南大学,新北市) Graduate Institute of Networking and Multimedia, National Taiwan University, Taipei City 106335, Taiwan(网络与多媒体研究所,台湾大学,台北市) School of Nursing, National Taipei University of Nursing and Health Sciences, Taipei City, 112303, Taiwan(护理学院,台北护理及健康科学大学,台北市) College of Energy and Mechanical Engineering, Shanghai University of Electric Power, Shanghai, 201306, China(能源与机械工程学院,上海电力大学,上海)

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

AI总结 YOLOv8-AM通过引入有效注意力机制提升儿童腕骨骨折检测的准确率,达到最先进的性能水平。

Journal ref IEEE Access 13 (2025) 52461-52477

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.16838 2026-02-06 eess.AS cs.AI cs.CL 50%

Segmentation-free Goodness of Pronunciation

无分段的发音质量评估

Xinwei Cao, Zijian Fan, Torbjørn Svendsen, Giampiero Salvi

机构 * Department of Electronic Systems, Norwegian University of Science and Technology (NTNU)(电子系统系,挪威科学技术大学)

专题命中 医学影像 :diagnosis(abstract)

AI总结 本文提出无分段发音质量评估方法,利用CTC训练的ASR模型提升发音错误检测与诊断的准确性,并在多个数据集上验证了其在发音评估中的优越性能。

Comments The article has been accepted for publication by IEEE TASLPRO

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.05256 2026-02-06 physics.app-ph 50%

Topological Metamaterial for Magnetic Resonance Imaging

拓扑超材料用于磁共振成像

Siyong Zheng, Maopeng Wu, Zhonghai Chi, Xinxin Li, Mingze Weng, Fubei Liu, Yingyi Qi, Yi Yi, Yakui Wang, Jie Gao, Guoxiang Zhan, Zewen Chen, Shuojun Ling, Yucheng Wei, Zhuozhao Zheng, Qian Zhao, Ji Zhou

专题命中 医学影像 :MRI(abstract)

AI总结 本研究利用拓扑超材料提升MRI信号接收性能,通过准二维双拓扑边界态实现低损耗信号传输和增强局部磁场,展现出优于商用线圈的性能与潜力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.05077 2026-02-06 physics.med-ph 50%

Laterally Oscillating Trajectory for Undersampling Slices: LOTUS

横向振荡轨迹用于欠采样切片:LOTUS

Mayuri Sothynathan, Paul I. Dubovan, Corey. A. Baron

专题命中 医学影像 :MRI(abstract)

AI总结 LOTUS通过受控非相干混叠降低g因子,提升扩散MRI的重建精度和扫描效率。

Comments 31 pages, 8 figures, 3 supplementary figures, submitted to Magnetic Resonance in Medicine

详情

展开后加载摘要…

URL PDF HTML 收藏

2. 临床大模型 1 篇

2504.20741 2026-02-06 cs.HC cs.AI cs.CY cs.LG 79%

In defence of post-hoc explanations in medical AI

为医疗AI中的事后解释辩护

Joshua Hatherley, Lauritz Munch, Jens Christian Bjerring

机构 * Center for the Philosophy of AI(哲学人工智能中心) University of Copenhagen(哥本哈根大学) Department of Philosophy and History of Ideas(哲学与思想史系) Aarhus University(奥胡斯大学)

专题命中 临床大模型 :medical AI(title,abstract);分类 cs.LG

AI总结 本文为医疗AI中的事后解释辩护,指出其虽无法完全复制黑盒推理过程,但能提升用户理解、提高临床团队准确性并辅助医生决策。

Journal ref 2026. Hastings Center Report 56(1): 40-46

详情

展开后加载摘要…

URL PDF HTML 收藏

3. 诊断辅助 4 篇

2602.04944 2026-02-06 eess.IV cs.AI cs.LG 81%

Smart Diagnosis and Early Intervention in PCOS: A Deep Learning Approach to Women's Reproductive Health

PCOS的智能诊断与早期干预:一种深度学习方法用于女性生殖健康

Shayan Abrar, Samura Rahman, Ishrat Jahan Momo, Mahjabin Tasnim Samiha, B. M. Shahria Alam, Mohammad Tahmid Noor, Nishat Tasnim Niloy

专题命中 诊断辅助 :diagnosis(title,abstract);分类 cs.LG、eess.IV

AI总结 本文提出基于深度学习的PCOS卵巢超声图像分类系统,利用迁移学习和增强策略实现高准确率的自动诊断,提升医疗图像分析的透明度和实用性。

Comments 6 pages, 12 figures. This is the author's accepted manuscript of a paper accepted for publication in the Proceedings of the 16th International IEEE Conference on Computing, Communication and Networking Technologies (ICCCNT 2025). The final published version will be available via IEEE Xplore

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.05446 2026-02-06 cs.HC 71%

DiLLS: Interactive Diagnosis of LLM-based Multi-agent Systems via Layered Summary of Agent Behaviors

通过代理行为分层总结实现基于大语言模型的多代理系统交互诊断:DiLLS

Rui Sheng, Yukun Yang, Chuhan Shi, Yanna Lin, Zixin Chen, Huamin Qu, Furui Cheng

专题命中 诊断辅助 :diagnosis(title)

AI总结 DiLLS通过多层行为总结,帮助开发者更高效地诊断和理解基于LLM的多代理系统故障。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.03951 2026-02-06 cs.LG cs.CV math.DG math.GN 62%

Representation Geometry as a Diagnostic for Out-of-Distribution Robustness

表示几何作为分布外鲁棒性的诊断

Ali Zia, Farid Hazratian

机构 * School of Mathematics, Computer Science Statistics, University of Tehran, Tehran, Iran School of Computing, Engineering \& Mathematical Sciences, La Trobe University , Melbourne, Australia

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

AI总结 本文提出基于几何的诊断框架,通过分析嵌入的谱复杂度和曲率来预测分布外鲁棒性,支持无监督的检查点选择。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.05455 2026-02-06 hep-ex physics.chem-ph 50%

A waveguide kinetics framework for electrochemical polarization

一种用于电化学极化现象的波导动力学框架

Bishuang Chen, Huayang Cai

专题命中 诊断辅助 :diagnosis(abstract)

AI总结 本文提出了一种理论中立的波导动力学框架,用于定量分析和预测氢电催化中的极化现象,并提供可转移的界面效率指标。

详情

展开后加载摘要…

URL PDF HTML 收藏

4. 病理影像 6 篇

2312.00992 2026-02-06 cs.LG 65%

Improving Normative Modeling for Multi-modal Neuroimaging Data using mixture-of-product-of-experts variational autoencoders

利用混合专家积变分自编码器改进多模态神经影像数据的规范建模

Sayantan Kumar, Philip Payne, Aristeidis Sotiras

机构 * Department of Computer Science and Engineering, Washington University in St. Louis, USA(计算机科学与工程系,华盛顿大学圣路易斯分校) Institute for Informatics, Data Science and Biostatistics, Washington University in St.Louis, USA(信息学、数据科学与生物统计研究所,华盛顿大学圣路易斯分校) Department of Radiology, Washington University in St.Louis, USA(放射学系,华盛顿大学圣路易斯分校)

专题命中 病理影像 :pathology(abstract);biomedical(comments,journal_ref);分类 cs.LG

AI总结 本文提出利用混合专家积变分自编码器改进多模态神经影像数据的规范建模,以更准确地识别异常个体及异常脑区。

Comments IEEE Internattional Symposium in Biomedical Imaging 2024

Journal ref 2024 IEEE International Symposium on Biomedical Imaging (ISBI)

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.04672 2026-02-06 cs.CV q-bio.QM 60%

Histo-Miner: Deep learning based tissue features extraction pipeline from H&E whole slide images of cutaneous squamous cell carcinoma

Histo-Miner:基于深度学习的H&E全切片图像皮肤鳞状细胞癌组织特征提取流程

Lucas Sancéré, Carina Lorenz, Doris Helbig, Oana-Diana Persa, Sonja Dengler, Alexander Kreuter, Martim Laimer, Roland Lang, Anne Fröhlich, Jennifer Landsberg, Johannes Brägelmann, Katarzyna Bozek

机构 * Faculty of Mathematics and Natural Sciences, University of Cologne(数学与自然科学学院,科隆大学) Excellence Cluster on Cellular Stress Responses in Aging-Associated Diseases (CECAD), University of Cologne(细胞应激反应与年龄相关疾病卓越集群(CECAD),科隆大学) Department for Dermatology, University Hospital Cologne(皮肤科部门,科隆大学医院) Department of Dermatology and Allergy, School of Medicine, Technical University of Munich(皮肤科与过敏科部门,医学院,慕尼黑技术大学) Department of Dermatology, Dortmund Hospital gGmbH, University Witten/Herdecke(皮肤科部门,多特蒙德医院gGmbH,乌尔姆/赫尔德克大学) Department of Dermatology, Venereology and Allergology, Helios St. Elisabeth Hospital Oberhausen, University Witten/Herdecke(皮肤科、性病科与过敏科部门,Helios圣埃利莎医院奥伯豪森,乌尔姆/赫尔德克大学) Department of Dermatology and Allergology, University Hospital of the Paracelsus Medical University Salzburg(皮肤科与过敏科部门,帕拉塞尔医学大学萨尔茨堡大学医院) Department of Dermatology and Allergology, University Hospital Bonn(皮肤科与过敏科部门,波恩大学医院) Medical Clinic III for Oncology, Hematology, Immune-Oncology and Rheumatology, University Hospital Bonn (UKB)(肿瘤科、血液科、免疫肿瘤科和风湿科第三医疗部门,波恩大学医院(UKB))

专题命中 病理影像 :pathology(abstract);分类 cs.CV、q-bio

AI总结 Histo-Miner通过深度学习提取皮肤鳞状细胞癌全切片图像的组织特征,用于预测免疫治疗反应。

Comments 37 pages including supplement, 5 core figures. Version 2: change sections order, add new supplementary sections, minor text updates. Version 3: Author addition and update of author contributions, increase font on 2 figures, minor text updates

Journal ref PLoS Comput. Biol., vol. 22, no. 1, p. e1013907, Jan. 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.05397 2026-02-06 cs.CV 57%

Explainable Pathomics Feature Visualization via Correlation-aware Conditional Feature Editing

通过相关性感知的条件特征编辑实现可解释的病理科特征可视化

Yuechen Yang, Junlin Guo, Ruining Deng, Junchao Zhu, Zhengyi Lu, Chongyu Qu, Yanfan Zhu, Xingyi Guo, Yu Wang, Shilin Zhao, Haichun Yang, Yuankai Huo

机构 * Vanderbilt University(范德比尔特大学) Weill Cornell Medicine(韦尔医学院) Vanderbilt University Medical Center(范德比尔特大学医学中心)

专题命中 病理影像 :pathology(abstract);分类 cs.CV

AI总结 本文提出了一种Manifold-Aware Diffusion框架,通过正则化解耦潜在空间中的特征轨迹,实现可控且生物合理的细胞核编辑,提升病理科特征的可解释性与图像生成质量。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.00151 2026-02-06 cs.CV cs.AI 57%

Investigating the Impact of Histopathological Foundation Models on Regressive Prediction of Homologous Recombination Deficiency

探究病理基础模型对同源重组缺陷的回归预测影响

Alexander Blezinger, Wolfgang Nejdl, Ming Tang

机构 * Leibniz University Hannover(汉诺威莱布尼茨大学)

专题命中 病理影像 :pathology(abstract);分类 cs.CV

AI总结 本研究探讨了病理基础模型在预测同源重组缺陷评分中的影响,通过实验发现基于基础模型的模型在预测准确性方面优于基线,并提出了缓解数据不平衡的上采样策略。

Comments 9 pages, 7 figures and 5 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.05250 2026-02-06 cs.CV 57%

Active Label Cleaning for Reliable Detection of Electron Dense Deposits in Transmission Electron Microscopy Images

主动标签清洗用于透射电子显微镜图像中电子致密沉积物的可靠检测

Jieyun Tan, Shuo Liu, Guibin Zhang, Ziqi Li, Jian Geng, Lei Zhang, Lei Cao

机构 * School of Biomedical Engineering(生物医学工程学院) Southern Medical University(南方医科大学) College of Letters and Science(文理学院) University of Wisconsin-Madison(威斯康星大学麦迪逊分校) School of Basic Medical Sciences(基础医学学院) Department of Nephrology(肾内科) Nanfang Hospital, Southern Medical University(南方医科大学南芳医院)

专题命中 病理影像 :medical AI(abstract);分类 cs.CV

AI总结 本文提出主动标签清洗方法,通过主动学习和专家重新标注,提升透射电子显微镜图像中电子致密沉积物检测的准确性和效率,降低标注成本。

Comments 10 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.05717 2026-02-06 cs.AI 50%

Anchored Policy Optimization: Mitigating Exploration Collapse Via Support-Constrained Rectification

基于锚定策略优化:通过支持约束修正缓解探索崩溃

Tianyi Wang, Long Li, Hongcan Guo, Yibiao Chen, Yixia Li, Yong Wang, Yun Chen, Guanhua Chen

机构 * Beijing University of Posts and Telecommunications(北京邮电大学) Southern University of Science and Technology(南方科技大学) Alibaba Group(阿里巴巴集团) Shanghai University of Finance and Economics(上海财经大学)

专题命中 病理影像 :pathology(abstract)

AI总结 本文提出锚定策略优化方法,通过支持覆盖机制缓解强化学习中的探索崩溃问题,提升模型在准确性与多样性间的性能平衡。

Comments 17 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏

5. 医疗多模态 4 篇

2110.04903 2026-02-06 eess.IV cs.LG 66%

Normative Modeling using Multimodal Variational Autoencoders to Identify Abnormal Brain Structural Patterns in Alzheimer Disease

基于多模态变分自编码器的规范建模用于识别阿尔茨海默病异常脑结构模式

Sayantan Kumar, Philip Payne, Aristeidis Sotiras

专题命中 医疗多模态 :MRI(abstract);分类 cs.LG、eess.IV;diagnosis(journal_ref)

AI总结 本文提出基于多模态变分自编码器的规范建模框架,用于识别阿尔茨海默病中异常脑结构模式,通过联合分布建模提高疾病阶段检测的敏感性和准确性。

Comments Medical Imaging Meets NeurIPS workshop in NeurIPS 2022

Journal ref Proc. SPIE 12465, Medical Imaging 2023: Computer-Aided Diagnosis, 1246503 (7 April 2023)

详情

展开后加载摘要…

URL PDF HTML 收藏
2404.05748 2026-02-06 q-bio.NC cs.LG 60%

Analyzing heterogeneity in Alzheimer Disease using multimodal normative modeling on imaging-based ATN biomarkers

利用多模态规范建模分析阿尔茨海默病的异质性:基于影像学ATN生物标志物

Sayantan Kumar, Tom Earnest, Braden Yang, Deydeep Kothapalli, Andrew J. Aschenbrenner, Jason Hassenstab, Chengie Xiong, Beau Ances, John Morris, Tammie L. S. Benzinger, Brian A. Gordon, Philip Payne, Aristeidis Sotiras

专题命中 医疗多模态 :MRI(abstract);分类 cs.LG、q-bio

AI总结 本研究利用多模态规范建模分析阿尔茨海默病影像学ATN生物标志物的异质性,揭示了疾病严重程度与认知功能的关系。

Comments Under review in Alzheimer's & Dementia

Journal ref Alzheimer's Dement. 2025; 21:e70143

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.07163 2026-02-06 cs.CV 57%

Test-time Adaptive Hierarchical Co-enhanced Denoising Network for Reliable Multimodal Classification

测试时自适应层次联合增强去噪网络用于可靠的多模态分类

Shu Shen, C. L. Philip Chen, Tong Zhang

机构 * The Guangdong Provincial Key Laboratory of Computational Intelligence and Cyberspace Information, the School of Computer Science and Engineering, South China University of Technology(广东省计算智能与网络信息重点实验室、计算机科学与工程学院、华南理工大学) The Pazhou Laboratory(琶洲实验室)

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

AI总结 本文提出TAHCD网络,通过自适应稳定子空间对齐和样本自适应置信度对齐,有效去除多模态噪声,提升多模态分类的鲁棒性和泛化能力。

Comments 14 pages,9 figures, 8 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.00120 2026-02-06 stat.ME stat.ML 50%

AdapDISCOM: An Adaptive Sparse Regression Method for High-Dimensional Multimodal Data With Block-Wise Missingness and Measurement Errors

AdapDISCOM:一种用于高维多模态数据的自适应稀疏回归方法,具有块状缺失和测量误差

Maimouna Baldé, Abdoul O. Diakité, Claudia Moreau, Gleb Bezgin, Nikhil Bhagwat, Pedro Rosa-Neto, Jean-Baptiste Poline, Simon Girard, Amadou Barry

专题命中 医疗多模态 :biomedical(abstract)

AI总结 AdapDISCOM通过自适应稀疏回归方法,有效应对高维多模态数据中的块状缺失和测量误差问题,提升预测性能和生物标志物选择的可靠性。

Comments 49 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏