医学 AI - arXivDaily 专题

2206.00831 2022-06-03 eess.IV cs.CV cs.LG 83%

Dynamic Cardiac MRI Reconstruction Using Combined Tensor Nuclear Norm and Casorati Matrix Nuclear Norm Regularizations

Yinghao Zhang, Yue Hu

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

Comments 4 pages, 3 figures, 1 table, accepted in IEEE ISBI 2022

Journal ref [C]//2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI). IEEE, 2022: 1-4

2203.12454 2022-03-24 eess.IV cs.CV cs.LG 83%

MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels

Ziyuan Zhao, Kaixin Xu, Shumeng Li, Zeng Zeng, Cuntai Guan

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

Comments Accept by MICCAI 2021, code at: https://github.com/jacobzhaoziyuan/MT-UDA

Journal ref Medical Image Computing and Computer Assisted Intervention, MICCAI 2021. Lecture Notes in Computer Science, vol 12901. Springer, Cham

2110.03343 2021-10-08 eess.IV cs.CV cs.LG 83%

Uncertainty-aware GAN with Adaptive Loss for Robust MRI Image Enhancement

Uddeshya Upadhyay, Viswanath P. Sudarshan, Suyash P. Awate

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

Comments Accepted at IEEE ICCV-2021 workshop on Computer Vision for Automated Medical Diagnosis

2103.14955 2021-07-23 eess.IV cs.CV cs.LG 83%

Improving prostate whole gland segmentation in t2-weighted MRI with synthetically generated data

Alvaro Fernandez-Quilez, Steinar Valle Larsen, Morten Goodwin, Thor Ole Gulsurd, Svein Reidar Kjosavik, Ketil Oppedal

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

Comments 5 pages. Accepted as a full paper at the International Symposium on Biomedical Imaging (ISBI) 2021

2107.00283 2021-07-02 eess.IV cs.CV cs.LG 83%

DivergentNets: Medical Image Segmentation by Network Ensemble

Vajira Thambawita, Steven A. Hicks, Pål Halvorsen, Michael A. Riegler

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

Comments the winning model of the segmentation generalization challenge at EndoCV 2021

Journal ref Proceedings of the 3rd International Workshop and Challenge on Computer Vision in Endoscopy (EndoCV 2021) colocated with with the 17th IEEE International Symposium on Biomedical Imaging (ISBI 2021)

2103.12595 2021-03-24 eess.IV cs.CV cs.LG 83%

An augmentation strategy to mimic multi-scanner variability in MRI

Maria Ines Meyer, Ezequiel de la Rosa, Nuno Barros, Roberto Paolella, Koen Van Leemput, Diana M. Sima

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

Comments 5 pages, 2 figures. accepted for presentation at the International Symposium on Biomedical Imaging (ISBI) 2021. Code available at https://github.com/icometrix/gmm-augmentation

2103.02844 2021-03-05 eess.IV cs.CV cs.LG 83%

Learning With Context Feedback Loop for Robust Medical Image Segmentation

Kibrom Berihu Girum, Gilles Créhange, Alain Lalande

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

Comments 13 pages, accepted for publication in IEEE Transactions on Medical Imaging (TMI); Applied to Heart (Cardiac cine-MRI and Echocardiography), Prostate, and Inner ear image segmentation

1908.06337 2021-01-20 eess.IV cs.CV cs.LG stat.ML 83%

EigenRank by Committee: A Data Subset Selection and Failure Prediction paradigm for Robust Deep Learning based Medical Image Segmentation

Bilwaj Gaonkar, Joel Beckett, Mark Attiah, Christine Ahn, Matthew Edwards, Bayard Wilson, Azim Laiwalla, Banafsheh Salehi, Bryan Yoo, Alex Bui, Luke Macyszyn

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

Journal ref Medical Image Analysis, Volume 67, 2021, Medical Image Analysis, Volume 67,2021,101834,ISSN 1361-8415,

2009.06082 2020-09-15 cs.AI 83%

Receptivity of an AI Cognitive Assistant by the Radiology Community: A Report on Data Collected at RSNA

Karina Kanjaria, Anup Pillai, Chaitanya Shivade, Marina Bendersky, Ashutosh Jadhav, Vandana Mukherjee, Tanveer Syeda-Mahmood

专题命中医学影像：radiology(title,abstract)；medical image(abstract)；biomedical(journal_ref)

Journal ref Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 5: HEALTHINF, ISBN 978-989-758-398-8, pages 178-186. 2020

2007.04768 2020-07-10 eess.IV cs.CV cs.LG 83%

Low Dose CT Denoising via Joint Bilateral Filtering and Intelligent Parameter Optimization

Mayank Patwari, Ralf Gutjahr, Rainer Raupach, Andreas Maier

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

Comments 4 pages, 5 figures, 1 table. Accepted at CT Meeting 2020

1908.10454 2020-02-13 eess.IV cs.CV cs.LG 83%

Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation

Nima Tajbakhsh, Laura Jeyaseelan, Qian Li, Jeffrey Chiang, Zhihao Wu, Xiaowei Ding

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

Comments Accepted for publication in the journal of Medical Image Analysis

1909.08868 2019-09-20 eess.IV cs.CV cs.LG 83%

Learning to Avoid Poor Images: Towards Task-aware C-arm Cone-beam CT Trajectories

Jan-Nico Zaech, Cong Gao, Bastian Bier, Russell Taylor, Andreas Maier, Nassir Navab, Mathias Unberath

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

Comments Accepted for oral presentation at the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2019

1909.00548 2019-09-04 eess.IV cs.CV cs.LG 83%

Resource Optimized Neural Architecture Search for 3D Medical Image Segmentation

Woong Bae, Seungho Lee, Yeha Lee, Beomhee Park, Minki Chung, Kyu-Hwan Jung

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

Comments MICCAI(International Conference on Medical Image Computing and Computer Assisted Intervention) 2019 accepted

0707.3455 2009-12-01 physics.med-ph 83%

Posture-Dependent Human 3He Lung Imaging in an Open Access MRI System: Initial Results

L. L. Tsai, R. W. Mair, C. -H. Li, M. S. Rosen, S. Patz, R. L. Walsworth

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

Comments single pdf file in manuscript format, 35 pages, 5 figures Submitted to Academic Radiology

0706.3286 2009-12-01 physics.med-ph 83%

Intensity-Based Registration of Freehand 3D Ultrasound and CT-scan Images of the Kidney

Antoine Leroy, Pierre Mozer, Yohan Payan, Jocelyne Troccaz

专题命中医学影像：CT(title,abstract)；medical image(abstract)；radiology(journal_ref)

Journal ref International Journal of Computer Assisted Radiology and Surgery 2, 1 (2007) 31-41

2608.23882 2026-08-26 eess.IV cs.CV 新提交 82%

Native-Space 3D CarveMix for Multi-Site T1w Stroke Segmentation

用于多中心T1加权卒中分割的原生空间3D CarveMix方法

Dexter Wen Jie Teo, Kumaradevan Punithakumar

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

AI总结针对多中心未标准化T1w MRI的卒中分割难题，提出结合MedNeXt-L骨干与动态3D CarveMix增强的方法，在ISLES 2026数据集上实现0.648的5折交叉验证Dice分数，较原骨干提升0.018。

Comments Accepted at the SWITCH+ Workshop (ISLES 2026 Challenge), MICCAI 2026. Springer LNCS

2608.23745 2026-08-26 eess.IV cs.CV 新提交 82%

Multi-Stage Prompt-Guided Feature Modulation for Generalizable Brain Tumor Segmentation

用于通用脑肿瘤分割的多阶段提示引导特征调制

Mohammad Mahdi Danesh Pajouh, Sara Saeedi

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

AI总结本文提出多阶段动态提示nnU-Net，通过多阶段动态提示调制编码器特征，在BraTS GOAT数据集上较基线nnU-Net提升了脑肿瘤分割的Dice分数，增强了模型泛化性。

Comments Accepted to BraTS MICCAI 2026 Task 3 (Generalizability Across Tumors)

2505.21736 2026-08-03 cs.CV cs.LG 版本更新 82%

Moment kernels: a simple and scalable approach for equivariance to rotations and reflections in deep convolutional networks

矩核：深度卷积网络中应对旋转与反射等变的简单可扩展方法

Siqi Fang, Zachary Schlamowitz, Andrew Bennecke, Daniel J. Tward

机构 * Department of Computational Medicine University of California, Los Angeles（计算医学系加州大学洛杉矶分校）

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

AI总结本文提出矩核，一种简单可扩展的正交变换等变卷积核，在生物医学图像任务中提升方向一致性，避免群卷积的方向通道扩展，适配标准CNN工作流程。

2607.23343 2026-07-28 eess.IV cs.AI cs.CV 新提交 82%

Patient-Agnostic Synthetic Pretraining for Efficient Patient-Specific Intraoperative 2D/3D Registration

用于高效患者特异性术中二维/三维配准的患者无关合成预训练

Minheng Chen, Youyong Kong

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

AI总结研究术中二维/三维配准问题，提出基于患者无关合成预训练和球面相似性学习的框架，先预训练模型学习可转移表示，再用目标CT投影适应新患者，引入无分割域随机化策略，实验证明该方法能降低训练需求并保持配准精度。

2607.16888 2026-07-21 cs.CV cs.LG 新提交 82%

Transferable Low-Rank Convolutional Bases for Onboarding Unseen Medical Imaging Modalities

用于引入未见医学成像模态的可转移低秩卷积基

Ranat Das Prangon, Istiaque Ahmed, Shajid Hasan Naim, Waseem Mustak Zisan, Hossain Md Shakhawat

机构 * Bangladesh University of Engineering and Technology (BUET)（孟加拉国工程技术大学）； Osaka Metropolitan University（大阪都市大学）； Chittagong University of Engineering and Technology (CUET)（吉大港工程技术大学）； Kochi University of Technology（高知工科大学）

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

AI总结研究医学成像模型引入未见模态的问题，提出冻结源模态低秩卷积基并训练其向上投影的方法，该方法可转移，能以极少参数引入未见模态，保持源模态准确率不变，还能检测何时需引入。

2607.13826 2026-07-16 cs.CV cs.AI cs.IR cs.LG 新提交 82%

Multimodal Assessment of Pancreatic Cancer Resectability Using Deep Learning

使用深度学习对胰腺癌可切除性进行多模态评估

Vincent Ochs, Christoph Kuemmerli, Florentin Bieder, Julia Wolleb, Joel L. Lavanchy, Julia Ruppel, Jan Liechti, Stephanie Taha-Mehlitz, Christian Andreas Nebiker, Beat Mueller, Giuseppe Kito Fusai, Joerg-Matthias Pollok, Anas Taha, Philippe C. Cattin, Sebastian Staubli

机构 * University of Basel（巴塞尔大学）； Clarunis, University Digestive Health Centre（克拉鲁尼斯大学消化健康中心）； Kantonsspital Aarau（阿劳州立医院）； Royal Free Hospital（皇家自由医院）

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

AI总结研究利用深度学习框架联合分析CT与临床信息，对胰腺癌可切除性分类。通过Swin-UNETR主干获取图像特征，融合临床嵌入，经动态多任务目标训练，能将患者分入NCCN的三种可切除性类别，提高评估准确性。

2607.12586 2026-07-15 eess.IV cs.CV 新提交 82%

Medical Image Segmentation based on Deep Active Contour and Mean Curvature Loss Function

基于深度活动轮廓和平均曲率损失函数的医学图像分割

Xiao-qiang Zhai, Zhi-feng Pang, Peng Zheng, Ze-wen Li, Yan-zhe Hou

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

AI总结针对医学图像分割中像素级训练缺乏几何先验信息及分割区域表征不足的问题，提出深度活动轮廓和平均曲率（DACMC）损失函数，用卷积核近似平均曲率，在多数据集上验证性能，展现新最优表现。

Comments 15 pages, 4 figures. Keywords: medical image segmentation, curvature regularization, loss function, active contour model, mean curvature, deep learning. Under review at Biomedical Signal Processing and Control

2607.11533 2026-07-14 cs.CV cs.LG 新提交 82%

Adaptive Routing for Efficient Diffusion Transformer-Based PNI Prediction

基于高效扩散变压器的PNI预测的自适应路由

Youngung Han, Dohyun Kweon, Kyeonghun Kim, Hyunsu Go, Jina Jeong, Suah Park, Induk Um, Junga Kim, Anna Jung, Yului Jeong, Sungha Park, Jinyong Jun, Pa Hong, Woo Kyoung Jeong, Won Jae Lee, Ken Ying-Kai Liao, Hyuk-Jae Lee, Nam-Joon Kim

机构 * Seoul National University（首尔国立大学）； Kyung Hee University（庆熙大学）； OUTTA ； Chung-Ang University（Chung-Ang 大学）； Seoul National University School of Medicine（首尔国立大学医学院）； Samsung Changwon Hospital（三星昌原医院）； Samsung Medical Center（三星医疗中心）； NVIDIA AI Technology Center（NVIDIA AI 技术中心）

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

AI总结针对胆管癌PNI术前MRI预测难题，传统方法有局限。本文将PNI预测设为扩散分类问题，用基于Transformer的表示实现去噪网络，并引入自适应路由提高效率，实验取得了0.731的AUC及257.57 GFLOPs的结果。

2503.15414 2026-07-10 eess.IV cs.CV 版本更新 82%

Asynchronous Federated Continual Segmentation with Evolving Clients and Label Spaces

具有不断变化的客户端和标签空间的异步联邦持续分割

Can Peng, Qianhui Men, Pramit Saha, Qianye Yang, Yingyu Yang, Shuwei Xing, Cheng Ouyang, J. Alison Noble

机构 * University of Oxford（牛津大学）； University of Bristol（布里斯托大学）

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

AI总结研究现实中联邦学习客户端组成和标签空间会变化的问题，提出CA-MMDS框架，通过基于代理的蒸馏更新全局模型，减少通信和计算成本，以多类3D腹部CT分割任务验证其能有效整合客户端知识并获良好分割性能。

2606.26716 2026-06-29 eess.IV cs.CV 新提交 82%

Dual-Prior Guided Null-Space Learning with Mixture-of-Splines for Arbitrary Medical Slice Super-Resolution

双先验引导的零空间学习与样条混合用于任意医学切片超分辨率

Haofei Song, Siyuan Xu, Xintian Mao, Shaojie Guo, Qingli Li, Yan Wang

机构 * Shanghai Key Laboratory of Multidimensional Information Processing（上海多维信息处理重点实验室）； East China Normal University（华东师范大学）

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

AI总结提出DP-NSL框架，通过测量一致性投影和样条混合模块，在零空间内学习几何连续先验，实现任意尺度医学切片超分辨率，保持测量一致性并优于现有方法。

Comments Accepted to ECCV 2026! Project page: https://github.com/DeepMed-Lab-ECNU/Medical-Image-Reconstruction

2606.26991 2026-06-26 eess.IV cs.LG math.OC 新提交 82%

Enabling self-supervised learned primal dual with Noise2Inverse

利用 Noise2Inverse 实现自监督学习先验-对偶算法

Antti Sällinen, Siiri Rautio, Santeri Kaupinmäki, Andreas Hauptmann

机构 * Research Unit of Mathematical Sciences, University of Oulu, Finland（奥卢大学数学科学研究中心，芬兰）； Department of Mathematics and Information Science, Josai University, Japan（立命馆大学数学与信息科学系，日本）； Department of Computer Science, University College London, United Kingdom（伦敦大学学院计算机科学系，英国）

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

AI总结提出 Noise2Inverse 学习先验-对偶算法 (N2I-LPD)，利用 CT 扫描角度旋转下不同测量噪声的统计独立性，实现无真实图像的自监督训练，提升低剂量和稀疏角度 CT 重建质量。

2606.25579 2026-06-25 eess.IV cs.CV 交叉投稿 82%

Cross-Attention Multimodal Learning for Predicting Response to Neoadjuvant Imatinib in Gastrointestinal Stromal Tumors: A Multicenter Retrospective Study

跨注意力多模态学习预测胃肠道间质瘤新辅助伊马替尼治疗反应：一项多中心回顾性研究

Fariba Tohidinezhad, Douwe J. Spaanderman, Natalia Oviedo Acosta, Kaouther Mouheb, Karthik Prathaban, David F. Hanff, Dirk J. Grünhagen, Cornelis Verhoef, Joris M. van Sabben, Evelyne Roets, Jette J. Slettenhaar, Hans Gelderblom, Ingrid M. E. Desar, Anna K. L. Reyners, Neeltje Steeghs, Stefan Klein, Martijn P. A. Starmans

机构 * Department of Radiology and Nuclear Medicine, Erasmus MC Cancer Institute, University Medical Center Rotterdam（埃拉斯姆斯MC癌症研究所放射学与核医学部，埃因霍温医学院鲁特沃特分校）； Department of Surgical Oncology, Erasmus MC Cancer Institute, University Medical Center Rotterdam（埃拉斯姆斯MC癌症研究所外科肿瘤部，埃因霍温医学院鲁特沃特分校）； Department of Pathology, Erasmus MC Cancer Institute, University Medical Center Rotterdam（埃拉斯姆斯MC癌症研究所病理学部，埃因霍温医学院鲁特沃特分校）； Department of Medical Oncology, The Netherlands Cancer Institute, Amsterdam（荷兰癌症研究所医学肿瘤部，阿姆斯特丹）； Department of Medical Oncology, Leiden University Medical Center, Leiden（莱顿大学医学中心医学肿瘤部，莱顿）； Department of Medical Oncology, Radboud University Medical Centre, Nijmegen（拉德堡德大学医学中心医学肿瘤部，尼日梅根）； Department of Medical Oncology, University Medical Center Groningen, University of Groningen（格罗宁根大学医学中心医学肿瘤部，格罗宁根）； Department of Medical Oncology, Netherlands Cancer Institute, Antoni Van Leeuwenhoek（荷兰癌症研究所医学肿瘤部，安托万·弗莱明）

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

AI总结本研究开发了一种可解释的跨注意力多模态深度学习框架，整合CT影像和临床变量，用于预测胃肠道间质瘤对新辅助伊马替尼的治疗反应，在内部验证中达到高AUC但外部泛化性有限。

2606.12824 2026-06-24 eess.IV cs.AI cs.CV physics.med-ph 新提交 82%

Acquisition state behaves as a structured, measurable variable governing lung-nodule AI: kernel-driven measurement instability and noise-driven detection fragility, invisible to DICOM metadata

采集状态作为结构化、可测量变量影响肺结节AI：核驱动的测量不稳定性和噪声驱动的检测脆弱性，DICOM元数据不可见

Daniel Soliman

机构 * Daniel Soliman, M.S（丹尼尔·索利曼，硕士）

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

AI总结研究通过LUNA16训练的RetinaNet检测器，发现CT采集状态（重建核与噪声）独立影响AI的测量与检测性能，且无法从DICOM元数据恢复，提出采集感知的输入验证层。

2605.02230 2026-06-23 cs.CV cs.LG 版本更新 82%

InfiltrNet: Dual-Branch CNN-Transformer Architecture for Brain Tumor Infiltration Risk Prediction

InfiltrNet: 用于脑肿瘤浸润风险预测的双分支CNN-Transformer架构

S M Asif Hossain, Shruti Kshirsagar

机构 * School of Computing, Wichita State University（维斯科萨大学计算学院）

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

AI总结提出InfiltrNet，结合CNN和Swin Transformer编码器及交叉注意力融合模块，从多模态MRI预测三区浸润风险图，利用距离变换生成标签，在BraTS数据集上优于五个基线模型。

Comments This work will be extended for a future journal submission

2606.21414 2026-06-23 eess.IV cs.AI cs.CV 新提交 82%

2D Versus 3D Diffusion for In Silico Training of Interventional X-ray AI Models

二维与三维扩散在介入X射线AI模型模拟训练中的比较

Sampath Rapuri, Jeremy Ko, Benjamin D. Killeen, Russell H. Taylor, Mathias Unberath

机构 * Johns Hopkins University（约翰霍普金斯大学）

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

AI总结本文比较了基于3D条件潜在扩散模型生成CT体数据用于DRR合成与基于视图条件的2D扩散模型直接生成合成X射线两种方法，发现2D扩散生成的合成X射线可用于训练解剖标志检测模型，性能接近真实数据训练模型。

1. 医学影像 22694 篇

Dynamic Cardiac MRI Reconstruction Using Combined Tensor Nuclear Norm and Casorati Matrix Nuclear Norm Regularizations

MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels

Uncertainty-aware GAN with Adaptive Loss for Robust MRI Image Enhancement

Improving prostate whole gland segmentation in t2-weighted MRI with synthetically generated data

DivergentNets: Medical Image Segmentation by Network Ensemble

An augmentation strategy to mimic multi-scanner variability in MRI

Learning With Context Feedback Loop for Robust Medical Image Segmentation

EigenRank by Committee: A Data Subset Selection and Failure Prediction paradigm for Robust Deep Learning based Medical Image Segmentation

Receptivity of an AI Cognitive Assistant by the Radiology Community: A Report on Data Collected at RSNA

Low Dose CT Denoising via Joint Bilateral Filtering and Intelligent Parameter Optimization

Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation

Learning to Avoid Poor Images: Towards Task-aware C-arm Cone-beam CT Trajectories

Resource Optimized Neural Architecture Search for 3D Medical Image Segmentation

Posture-Dependent Human 3He Lung Imaging in an Open Access MRI System: Initial Results

Intensity-Based Registration of Freehand 3D Ultrasound and CT-scan Images of the Kidney

Native-Space 3D CarveMix for Multi-Site T1w Stroke Segmentation

Multi-Stage Prompt-Guided Feature Modulation for Generalizable Brain Tumor Segmentation

Moment kernels: a simple and scalable approach for equivariance to rotations and reflections in deep convolutional networks

Patient-Agnostic Synthetic Pretraining for Efficient Patient-Specific Intraoperative 2D/3D Registration

Transferable Low-Rank Convolutional Bases for Onboarding Unseen Medical Imaging Modalities

Multimodal Assessment of Pancreatic Cancer Resectability Using Deep Learning

Medical Image Segmentation based on Deep Active Contour and Mean Curvature Loss Function

Adaptive Routing for Efficient Diffusion Transformer-Based PNI Prediction

Asynchronous Federated Continual Segmentation with Evolving Clients and Label Spaces

Dual-Prior Guided Null-Space Learning with Mixture-of-Splines for Arbitrary Medical Slice Super-Resolution

Enabling self-supervised learned primal dual with Noise2Inverse

Cross-Attention Multimodal Learning for Predicting Response to Neoadjuvant Imatinib in Gastrointestinal Stromal Tumors: A Multicenter Retrospective Study

Acquisition state behaves as a structured, measurable variable governing lung-nodule AI: kernel-driven measurement instability and noise-driven detection fragility, invisible to DICOM metadata

InfiltrNet: Dual-Branch CNN-Transformer Architecture for Brain Tumor Infiltration Risk Prediction

2D Versus 3D Diffusion for In Silico Training of Interventional X-ray AI Models