医学 AI - arXivDaily 专题

2303.02559 2023-03-07 cs.LG cs.CR cs.CV eess.IV 89%

Securing Biomedical Images from Unauthorized Training with Anti-Learning Perturbation

Yixin Liu, Haohui Ye, Kai Zhang, Lichao Sun

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

Comments This paper is accepted as a poster for NDSS 2023

2211.07966 2022-11-16 eess.IV cs.CV cs.LG 89%

Adaptive PromptNet For Auxiliary Glioma Diagnosis without Contrast-Enhanced MRI

Yeqi Wang, Weijian Huang, Cheng Li, Xiawu Zheng, Yusong Lin, Shanshan Wang

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

Comments 5 pages, 2 figures, 2 tables

2205.07568 2022-05-17 eess.IV cs.CV cs.LG 89%

Weakly-supervised Biomechanically-constrained CT/MRI Registration of the Spine

Bailiang Jian, Mohammad Farid Azampour, Francesca De Benetti, Johannes Oberreuter, Christina Bukas, Alexandra S. Gersing, Sarah C. Foreman, Anna-Sophia Dietrich, Jon Rischewski, Jan S. Kirschke, Nassir Navab, Thomas Wendler

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

Comments 10 pages, 3 figures

2109.03812 2021-09-15 eess.IV cs.CV cs.LG physics.med-ph 89%

fastMRI+: Clinical Pathology Annotations for Knee and Brain Fully Sampled Multi-Coil MRI Data

Ruiyang Zhao, Burhaneddin Yaman, Yuxin Zhang, Russell Stewart, Austin Dixon, Florian Knoll, Zhengnan Huang, Yvonne W. Lui, Michael S. Hansen, Matthew P. Lungren

专题命中医学影像：MRI(title,abstract)；pathology(title,abstract)；分类 cs.CV、cs.LG、eess.IV

2106.01915 2021-06-04 eess.IV cs.CV cs.LG 89%

Pathology-Aware Generative Adversarial Networks for Medical Image Augmentation

Changhee Han

专题命中医学影像：medical image(title,abstract)；pathology(title)；diagnosis(abstract)；分类 cs.CV、cs.LG、eess.IV

Comments Ph.D. Thesis (The University of Tokyo) defended in February, 2020. Based on GAN-based synthetic brain MR image generation (ISBI 2018), arXiv:1902.09856, arXiv:1903.12564, arXiv:1905.13456, arXiv:1906.04962, arXiv:2001.03923

2008.04396 2020-08-12 eess.IV cs.CV cs.LG 89%

GANDALF: Generative Adversarial Networks with Discriminator-Adaptive Loss Fine-tuning for Alzheimer's Disease Diagnosis from MRI

Hoo-Chang Shin, Alvin Ihsani, Ziyue Xu, Swetha Mandava, Sharath Turuvekere Sreenivas, Christopher Forster, Jiook Cha, Alzheimer's Disease Neuroimaging Initiative

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

Comments Accepted for publication at the MICCAI 2020 conference

2004.05698 2020-05-28 eess.IV cs.CV cs.LG 89%

Y-net: Biomedical Image Segmentation and Clustering

Sharmin Pathan, Anant Tripathi

专题命中医学影像：medical image(title,abstract)；biomedical(title)；diagnosis(abstract)；分类 cs.CV、cs.LG、eess.IV

2004.12204 2020-04-28 cs.LG cs.CV eess.IV stat.ML 89%

Explainable Deep CNNs for MRI-Based Diagnosis of Alzheimer's Disease

Eduardo Nigri, Nivio Ziviani, Fabio Cappabianco, Augusto Antunes, Adriano Veloso

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

Comments Accepted for the IEEE International Joint Conference on Neural Networks (IJCNN) 2020

1911.02521 2019-11-07 eess.IV cs.CV cs.LG 89%

Machine Learning Techniques for Biomedical Image Segmentation: An Overview of Technical Aspects and Introduction to State-of-Art Applications

Hyunseok Seo, Masoud Badiei Khuzani, Varun Vasudevan, Charles Huang, Hongyi Ren, Ruoxiu Xiao, Xiao Jia, Lei Xing

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

Comments Accept for publication at Medical Physics

1909.00617 2019-09-04 eess.IV cs.CV cs.LG 89%

Reinforcement Learning-based Automatic Diagnosis of Acute Appendicitis in Abdominal CT

Walid Abdullah Al, Il Dong Yun, Kyong Joon Lee

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

Comments 9 pages, 6 figures

1908.05663 2019-08-19 eess.IV cs.CV cs.LG 89%

Automatic detection and diagnosis of sacroiliitis in CT scans as incidental findings

Yigal Shenkman, Bilal Qutteineh, Leo Joskowicz, Adi Szeskin, Yusef Azraq, Arnaldo Mayer, Iris Eshed

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

1402.2647 2014-02-12 physics.med-ph 89%

First CT-MRI Scanner for Multi-dimensional Synchrony and Multi-physical Coupling

Ge Wang

专题命中医学影像：MRI(title,abstract)；CT(title,abstract)；biomedical(abstract)

Comments 2 pages, 5 references

2508.09919 2025-08-14 eess.IV cs.AI cs.CV 89%

T-CACE: A Time-Conditioned Autoregressive Contrast Enhancement Multi-Task Framework for Contrast-Free Liver MRI Synthesis, Segmentation, and Diagnosis

Xiaojiao Xiao, Jianfeng Zhao, Qinmin Vivian Hu, Guanghui Wang

机构 * Department of Computer Science, Toronto Metropolitan University（计算机科学系，多伦多 Metropolitan 大学）； School of Biomedical Engineering, Western University（生物医学工程学院，西部大学）

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

Comments IEEE Journal of Biomedical and Health Informatics, 2025

2405.16942 2024-10-24 eess.IV cs.CV 89%

PASTA: Pathology-Aware MRI to PET Cross-Modal Translation with Diffusion Models

Yitong Li, Igor Yakushev, Dennis M. Hedderich, Christian Wachinger

专题命中医学影像：MRI(title,abstract)；pathology(title,abstract)；分类 cs.CV、eess.IV；medical image(journal_ref)

Journal ref Medical Image Computing and Computer Assisted Intervention (MICCAI 2024)

2105.07451 2022-02-01 eess.IV cs.CV 89%

MSRF-Net: A Multi-Scale Residual Fusion Network for Biomedical Image Segmentation

Abhishek Srivastava, Debesh Jha, Sukalpa Chanda, Umapada Pal, Håvard D. Johansen, Dag Johansen, Michael A. Riegler, Sharib Ali, Pål Halvorsen

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

Journal ref IEEE Journal of Biomedical and Health Informatics, 2022

2511.05782 2026-08-25 cs.CV 版本更新 89%

TCSA-UDA: Text-Driven Cross-Semantic Alignment for Unsupervised Domain Adaptation in Medical Image Segmentation

TCSA-UDA：基于文本的跨语义对齐用于医学图像分割中的无监督域适应

Lalit Maurya, Honghai Liu, Reyer Zwiggelaar

机构 * School of Computing, University of Portsmouth（朴茨茅斯大学计算学院）； Department of Computer Science, Aberystwyth University（阿伯里斯特威斯大学计算机科学系）

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

AI总结本文提出TCSA-UDA框架，通过文本驱动的跨语义对齐方法，在医学图像分割中减少域偏移并提升跨模态一致性。

Comments Published in Neurocomputing

2608.16855 2026-08-18 cs.CV 新提交 89%

Can Unsupervised Methods Outperform Supervised Deep Learning When Ground Truth Is Sparse? A Case Study of Bronchovascular Bundle Segmentation in Low-Dose CT

当真实标注稀疏时，无监督方法能否优于监督深度学习？——基于低剂量CT中支气管血管束分割的案例研究

Anna Mrukwa, Marek Socha, Aleksandra Suwalska, Agata Durawa, Malgorzata Jelitto, Katarzyna Dziadziuszko, Edyta Szurowska, Pawel Bozek, Michal Marczyk, Witold Rzyman, Rafal Dziadziuszko, Joanna Polanska

专题命中医学影像：CT(title,title_cn)；分类 cs.CV

AI总结本研究以低剂量CT的支气管血管束分割为案例，构建RONALD无监督分割流程，在真实标注稀疏时，其结节保留率显著优于现有方法，可提升极早期肺癌的肺结节检测效果。

Comments 17 pages, 4 figures. Part of this research was submitted to the international conference European Molecular Imaging Meeting 2026

2509.22874 2026-08-06 cs.CV 版本更新 89%

Deformable Medical Image Registration with KAN-based Implicit Neural Representations

基于KAN的隐式神经表示的可变形医学图像配准

Nikita Drozdov, Marat Zinovev, Dmitry Sorokin

机构 * Lomonosov Moscow State University（罗蒙诺索夫莫斯科国立大学）

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

AI总结提出基于KAN的INR框架KAN-IDIR与RandKAN-IDIR，用于无需数据集级训练的逐对优化可变形医学图像配准，在多模态医学图像上实现高准确性、低开销与稳定性，适用于临床研究。

Comments Accepted at Machine Learning and Knowledge Extraction

2607.26196 2026-07-30 cs.CV 新提交 89%

Rad-JEPA 3D: Radiology Joint-Embedding Predictive Model for 3D Computed Tomography

Rad-JEPA 3D：用于三维计算机断层扫描的放射学联合嵌入预测模型

Quoc-Huy Trinh, Minh-Van Nguyen, Ulas Bagci

机构 * Northwestern University（西北大学）； Technical University of Denmark（丹麦技术大学）

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

AI总结 Rad-JEPA 3D是用于3D CT的自监督联合嵌入预测框架，采用混合H-Mamba编码器与HSOR正则化，在12万次CT扫描预训练后，在器官识别、空间推理等任务上达到最优性能。

2606.04705 2026-07-28 cs.CV cs.AI 版本更新 89%

Enhancing MedSAM with a Lightweight Box Predictor for Medical Image Segmentation

通过轻量级框预测器增强 MedSAM 用于医学图像分割

Amirhossein Movahedisefat, Amirreza Fateh, Mohammad Reza Mohammadi

机构 * School of Computer Engineering, Iran University of Science and Technology (IUST)（伊朗科学技术大学计算机工程学院）

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

AI总结提出一种集成轻量级框预测器的 MedSAM 增强框架，通过单次点击估计边界框以提升点提示的空间引导能力，在仅增加 1.6M 参数下显著提高多模态医学图像分割的准确性和鲁棒性。

2607.20993 2026-07-24 cs.CV cs.AI 新提交 89%

Sparse Concept Channels in Frozen 3D CT Vision Encoders

冻结的3D CT视觉编码器中的稀疏概念通道

Farhad Nooralahzadeh, Lea Bogensperger, Christian Bluethgen, Michael Krauthammer

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

AI总结研究3D医学图像解释中视觉语言模型内部单元对临床发现的编码，提出无训练概念通道探测（CCP）方法，通过实验证明该方法能清晰表征冻结医学编码器对发现的表示，在临床疗效和NLG指标上表现优且延迟低。

2607.20692 2026-07-24 cs.CV cs.AI 新提交 89%

DS@GT ARC at ImageCLEFmed GANs 2026: Geometric Filtering for Privacy-Preserving CT Slice Generation

图像CLEFmed GANs 2026竞赛中的DS@GT ARC：用于隐私保护CT切片生成的几何滤波

Eric Regina, Richard Arnaud, Samir Hadi Cisneros

机构 * Georgia Institute of Technology（佐治亚理工学院）

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

AI总结为Image-CLEFmed GANs 2026挑战赛开发隐私保护框架，结合最优传输条件流匹配等，在几何潜在空间过滤候选切片。官方结果显示有真实感与隐私权衡，虽减少泄漏，但防止直接图像复制仍不足以消除患者特定解剖特征，凸显未来隐私保护医学图像生成的重要前沿。

2607.15231 2026-07-17 cs.CV 新提交 89%

CRISP: Constrained Refinement via Iterative Squeezing Process for Robust Medical Image Segmentation under Domain Shift

CRISP：通过迭代挤压过程进行约束细化，以实现域转移下的稳健医学图像分割

Yizhou Fang, Pujin Cheng, Yixiang Liu, Xiaoying Tang, Longxi Zhou

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

AI总结针对医学成像域转移问题，提出CRISP模型无关框架，利用“正区域的秩稳定性”假设，通过潜在特征扰动获取双先验并递归细化，经迭代训练框架提升分割精度，在多中心实验中显著优于现有方法。

Comments X pages, 3 figures, 3 tables; submitted to AAAI 2027

2507.10881 2026-07-09 cs.CV 版本更新 89%

Trexplorer Super: Topologically Correct Centerline Tree Tracking of Tubular Objects in CT Volumes

Trexplorer Super：CT 体积中管状物体的拓扑正确中心线树跟踪

Roman Naeem, David Hagerman, Jennifer Alvén, Lennart Svensson, Fredrik Kahl

机构 * Chalmers University of Technology（查尔姆斯理工大学）

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

AI总结研究旨在改进 CT 体积中管状物体中心线跟踪。针对 Trexplorer 问题提出 Trexplorer Super，通过开发三个难度递增的中心线数据集，对现有 SOTA 模型全面评估，结果显示 Trexplorer Super 性能更优，且合成数据与真实数据表现有差异。

Comments Submitted Version. Accepted at MICCAI 2025

2607.00058 2026-07-02 cs.CV 新提交 89%

Joint Medical Image Enhancement and Segmentation with Diffusion-based Symbiotic Information Interaction

基于扩散的共生信息交互的联合医学图像增强与分割

Ying Chen, Jinyue Li, Qiankun Li

机构 * Shenzhen Research Institute, The Chinese University of Hong Kong（香港中文大学深圳研究院）； University of Science and Technology of China（中国科学技术大学）； Imperial Global Singapore, Imperial College London（伦敦帝国学院新加坡分校）

专题命中医学影像：medical image(title)；MRI(abstract,abstract_cn)；CT(abstract,abstract_cn)；diagnosis(abstract)

AI总结提出DiSIINet，利用扩散模型和共生信息交互模块，在统一框架中实现图像增强与分割的相互促进，在多模态医学图像上取得显著性能提升。

Comments Accepted by IJCAI 2026

2606.26894 2026-06-26 cs.CV 新提交 89%

Modeling Local, Global, and Cross-Modal Context in Multimodal 3D MRI

多模态3D MRI中的局部、全局和跨模态上下文建模

Minh Duc Do, Tillmann Rheude, Noel Kronenberg, Roland Eils, Benjamin Wild

机构 * Berlin Institute of Health at Charité - Universitätsmedizin Berlin（柏林健康研究所，柏林夏里特医学院）； Health Data Science Unit, Heidelberg University Hospital and BioQuant（海德堡大学医院与BioQuant健康数据科学部）； Intelligent Medicine Institute, Fudan University（复旦大学智能医学研究所）； Department of Mathematics and Computer Science, Freie Universität Berlin（柏林自由大学数学与计算机科学系）

专题命中医学影像：MRI(title,title_cn)；pathology(abstract)；分类 cs.CV

AI总结提出MICViT，一种3D视觉Transformer，通过四种注意力机制显式建模模态内和跨模态的局部与全局交互，在多数据集脑龄预测任务中优于现有方法。

2606.25390 2026-06-25 cs.CV cs.AI 新提交 89%

Anatomically-conditioned Latent Diffusion Model for Data-Efficient Few-Shot Cross-Domain 3D Glioma MRI Synthesis

解剖条件约束的潜在扩散模型用于数据高效的小样本跨域3D胶质瘤MRI合成

Salman Shaik, Truong Thanh Hung Nguyen, Hung Cao

机构 * Analytics Everywhere Lab, University of New Brunswick, Canada（新不伦瑞克大学分析无处不在实验室，加拿大）

专题命中医学影像：MRI(title,title_cn)；pathology(abstract)；分类 cs.CV

AI总结提出解剖条件约束的潜在扩散模型（ALDM），通过两阶段框架（3D变分自编码器学习解剖先验，ControlNet引导的潜在扩散生成结构一致体积）在仅16张目标图像的小样本设置下优于GAN基线，实现FID 85.40和分类AUC 0.987。

Comments Published in Canadian AI 2026

2606.18749 2026-06-18 cs.CV 新提交 89%

Toward Training-Free Zero-Shot Anomaly Detection in 3D Medical Images: A Batch-Based Approach Using 2D Foundation Models

迈向3D医学图像的无训练零样本异常检测：基于批次的方法使用2D基础模型

Tai Le-Gia

机构 * Chungnam National University（忠南大学）

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

AI总结提出CS3F框架，利用2D基础模型对3D医学图像进行零样本异常检测，通过沿多轴分解、切片编码和跨主体相似性计算异常分数，并引入粗到细的分词策略减少信号衰减。

2507.15777 2026-06-17 cs.CV 89%

Label tree semantic losses for rich multi-class medical image segmentation

用于丰富多类医学图像分割的标签树语义损失

Junwen Wang, Oscar MacCormac, William Rochford, Aaron Kujawa, Jonathan Shapey, Tom Vercauteren

机构 * School of Biomedical Engineering & Imaging Sciences（生物医学工程与成像科学学院）； Department of Neurosurgery（神经外科部门）

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

AI总结提出两种基于标签层次结构的树状语义损失函数，在脑MRI全监督分割和神经外科高光谱成像稀疏标注场景理解中取得一致改进。

2606.14072 2026-06-15 cs.CV cs.CL 新提交 89%

Diffusion-Refined Segmentation and Vision-Language Interpretation for Pediatric Brain Tumor MRI

扩散细化分割与视觉-语言解释用于儿童脑肿瘤MRI

Wentao Ke, Jianche Liu

机构 * Department of Mechanical Engineering, Stanford University（斯坦福大学机械工程系）； School of Medicine, Stanford University（斯坦福大学医学院）

专题命中医学影像：MRI(title,title_cn)；radiology(abstract)；分类 cs.CV

AI总结提出两阶段框架，先用Swin-UNETR粗分割，再用条件扩散模型细化边界，最后结合多模态语言模型生成结构化报告，提升儿童脑肿瘤分割精度和可解释性。

1. 医学影像 22681 篇

Securing Biomedical Images from Unauthorized Training with Anti-Learning Perturbation

Adaptive PromptNet For Auxiliary Glioma Diagnosis without Contrast-Enhanced MRI

Weakly-supervised Biomechanically-constrained CT/MRI Registration of the Spine

fastMRI+: Clinical Pathology Annotations for Knee and Brain Fully Sampled Multi-Coil MRI Data

Pathology-Aware Generative Adversarial Networks for Medical Image Augmentation

GANDALF: Generative Adversarial Networks with Discriminator-Adaptive Loss Fine-tuning for Alzheimer's Disease Diagnosis from MRI

Y-net: Biomedical Image Segmentation and Clustering

Explainable Deep CNNs for MRI-Based Diagnosis of Alzheimer's Disease

Machine Learning Techniques for Biomedical Image Segmentation: An Overview of Technical Aspects and Introduction to State-of-Art Applications

Reinforcement Learning-based Automatic Diagnosis of Acute Appendicitis in Abdominal CT

Automatic detection and diagnosis of sacroiliitis in CT scans as incidental findings

First CT-MRI Scanner for Multi-dimensional Synchrony and Multi-physical Coupling

T-CACE: A Time-Conditioned Autoregressive Contrast Enhancement Multi-Task Framework for Contrast-Free Liver MRI Synthesis, Segmentation, and Diagnosis

PASTA: Pathology-Aware MRI to PET Cross-Modal Translation with Diffusion Models

MSRF-Net: A Multi-Scale Residual Fusion Network for Biomedical Image Segmentation

TCSA-UDA: Text-Driven Cross-Semantic Alignment for Unsupervised Domain Adaptation in Medical Image Segmentation

Can Unsupervised Methods Outperform Supervised Deep Learning When Ground Truth Is Sparse? A Case Study of Bronchovascular Bundle Segmentation in Low-Dose CT

Deformable Medical Image Registration with KAN-based Implicit Neural Representations

Rad-JEPA 3D: Radiology Joint-Embedding Predictive Model for 3D Computed Tomography

Enhancing MedSAM with a Lightweight Box Predictor for Medical Image Segmentation

Sparse Concept Channels in Frozen 3D CT Vision Encoders

DS@GT ARC at ImageCLEFmed GANs 2026: Geometric Filtering for Privacy-Preserving CT Slice Generation

CRISP: Constrained Refinement via Iterative Squeezing Process for Robust Medical Image Segmentation under Domain Shift

Trexplorer Super: Topologically Correct Centerline Tree Tracking of Tubular Objects in CT Volumes

Joint Medical Image Enhancement and Segmentation with Diffusion-based Symbiotic Information Interaction

Modeling Local, Global, and Cross-Modal Context in Multimodal 3D MRI

Anatomically-conditioned Latent Diffusion Model for Data-Efficient Few-Shot Cross-Domain 3D Glioma MRI Synthesis

Toward Training-Free Zero-Shot Anomaly Detection in 3D Medical Images: A Batch-Based Approach Using 2D Foundation Models

Label tree semantic losses for rich multi-class medical image segmentation

Diffusion-Refined Segmentation and Vision-Language Interpretation for Pediatric Brain Tumor MRI