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。

共收录 22615 信号源:cs.CV, cs.LG, q-bio, eess.IV, eess.SP

1. 医学影像 22615 篇

1602.07049 2026-06-04 math.NA cs.NA 86%

Limited Tomography Reconstruction via Tight Frame and Sinogram Extrapolation

有限数据CT重建 via 紧密框架与sinogram外推

Jae Kyu Choi, Bin Dong, Xiaoqun Zhang

专题命中 医学影像 :CT(title_cn,summary_cn)

AI总结 本文提出利用紧密框架正则化和同时sinogram外推方法,从有限sinogram数据中重建完整CT图像,优于传统稀疏模型方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.02156 2026-06-02 eess.IV cs.AI cs.CV cs.IR cs.LG 86%

Predicting the risk of colorectal anastomotic leak based on preoperative mapping of the blood supply of the bowel

基于术前肠道血供映射预测结直肠吻合口漏风险

Zahra Tabatabaei, Jon Sporring, Mark Bremholm Ellebæk, Alaa El-Hussuna

机构 * Computer Science Department, Københavns Universitet (KU)(哥本哈根大学计算机科学系) University of Southern Denmark(南部丹麦大学) Odense University Hospital(奥登塞大学医院) OpenSourceResearch Collaboration(开源研究协作)

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

AI总结 提出一种基于术前CT影像的AI驱动系统,通过分析血管和组织特征量化吻合口漏风险,并结合内容检索支持临床决策。

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.09234 2024-10-15 cs.CL 86%

Fine-Tuning In-House Large Language Models to Infer Differential Diagnosis from Radiology Reports

Luoyao Chen, Revant Teotia, Antonio Verdone, Aidan Cardall, Lakshay Tyagi, Yiqiu Shen, Sumit Chopra

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

Comments 10 pages, 2 figures, 4 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.13038 2024-09-23 cs.AI 86%

HeadCT-ONE: Enabling Granular and Controllable Automated Evaluation of Head CT Radiology Report Generation

Julián N. Acosta, Xiaoman Zhang, Siddhant Dogra, Hong-Yu Zhou, Seyedmehdi Payabvash, Guido J. Falcone, Eric K. Oermann, Pranav Rajpurkar

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2008.07588 2024-08-19 eess.IV cs.CV cs.LG stat.ML 86%

Uncertainty Quantification using Variational Inference for Biomedical Image Segmentation

Abhinav Sagar

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2311.07234 2023-11-14 eess.IV cs.CV cs.LG 86%

Multi-task learning for joint weakly-supervised segmentation and aortic arch anomaly classification in fetal cardiac MRI

Paula Ramirez, Alena Uus, Milou P. M. van Poppel, Irina Grigorescu, Johannes K. Steinweg, David F. A. Lloyd, Kuberan Pushparajah, Andrew P. King, Maria Deprez

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

Comments Accepted for publication at the Journal of Machine Learning for Biomedical Imaging (MELBA) https://melba-journal.org/2023:015

Journal ref Machine.Learning.for.Biomedical.Imaging. 2 (2023)

详情

展开后加载摘要…

URL PDF HTML 收藏
2307.15872 2023-08-01 eess.IV cs.CV cs.LG 86%

Cross-dimensional transfer learning in medical image segmentation with deep learning

Hicham Messaoudi, Ahror Belaid, Douraied Ben Salem, Pierre-Henri Conze

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

Comments 30 pages, 12 figures, 6 tables, Accepted for publication in the Journal of Medical Image Analysis

Journal ref In Medical Image Analysis (Vol. 88, p. 102868). Elsevier BV (2023)

详情

展开后加载摘要…

URL PDF HTML 收藏
1910.02923 2021-05-06 cs.LG cs.CV cs.HC eess.IV 86%

A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis

Samuel Budd, Emma C Robinson, Bernhard Kainz

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

Comments Medical Image Analysis Volume 71 2021 https://doi.org/10.1016/j.media.2021.102062

Journal ref Medical Image Analysis, Volume 71, 2021, 102062, ISSN 1361-8415

详情

展开后加载摘要…

URL PDF HTML 收藏
2004.10734 2021-03-30 eess.IV cs.CV cs.LG 86%

Red-GAN: Attacking class imbalance via conditioned generation. Yet another perspective on medical image synthesis for skin lesion dermoscopy and brain tumor MRI

Ahmad B Qasim, Ivan Ezhov, Suprosanna Shit, Oliver Schoppe, Johannes C Paetzold, Anjany Sekuboyina, Florian Kofler, Jana Lipkova, Hongwei Li, Bjoern Menze

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

Journal ref Published in Proceedings of the 3rd edition of Medical Imaging with Deep Learning, Montréal, Canada, PMLR 121, 2020

详情

展开后加载摘要…

URL PDF HTML 收藏
2001.01279 2020-08-24 eess.IV cs.CV cs.LG 86%

Deep Transfer Convolutional Neural Network and Extreme Learning Machine for Lung Nodule Diagnosis on CT images

Xufeng Huang, Qiang Lei, Tingli Xie, Yahui Zhang, Zhen Hu, Qi Zhou

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

Comments Some content of the article needs to be kept secret

Journal ref Knowledge-Based Systems (2020) 106230

详情

展开后加载摘要…

URL PDF HTML 收藏
2008.02708 2020-08-07 cs.AI 86%

Deep reinforcement learning to detect brain lesions on MRI: a proof-of-concept application of reinforcement learning to medical images

Joseph Stember, Hrithwik Shalu

专题命中 医学影像 :medical image(title);MRI(title);radiology(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2005.03347 2020-05-08 physics.med-ph 86%

Evaluation of Ultra Low Dose chest CT imaging for Covid 19 diagnosis and follow up

Fariba Zarei, Reza Jalli, Sabyasachi Chatterjee, Mehrzad Lotfi, Pooya Iranpour, Vani VC, Sedigheh Emadi, Rezvan Ravanfar Haghighi

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

Comments this manuscript contains 13 pages, 2 figures, I am the Corresponding author this pre-print paper

详情

展开后加载摘要…

URL PDF HTML 收藏
1803.00131 2019-08-06 physics.med-ph 86%

Male pelvic synthetic CT generation from T1-weighted MRI using 2D and 3D convolutional neural networks

Jie Fu, Yingli Yang, Kamal Singhrao, Dan Ruan, Daniel A. Low, John H. Lewis

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

Comments Medical Physics 2019

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.24160 2026-06-23 eess.IV cs.CV 版本更新 86%

Beyond the LUMIR challenge: The pathway to foundational registration models

超越LUMIR挑战:走向基础配准模型

Junyu Chen, Shuwen Wei, Joel Honkamaa, Pekka Marttinen, Hang Zhang, Min Liu, Yichao Zhou, Zuopeng Tan, Zhuoyuan Wang, Yi Wang, Hongchao Zhou, Shunbo Hu, Yi Zhang, Qian Tao, Lukas Förner, Thomas Wendler, Bailiang Jian, Benedikt Wiestler, Tim Hable, Jin Kim, Dan Ruan, Frederic Madesta, Thilo Sentker, Wiebke Heyer, Lianrui Zuo, Yuwei Dai, Jing Wu, Jerry L. Prince, Harrison Bai, Yong Du, Yihao Liu, Alessa Hering, Reuben Dorent, Lasse Hansen, Mattias P. Heinrich, Aaron Carass

机构 * The Russell H. Morgan Department of Radiology(Russell H. Morgan放射科) Radiological Science, Johns Hopkins Medical School(约翰霍普金斯医学院放射科学) Department of Computer Science, Aalto University(阿尔托大学计算机科学系) Cornell University(康奈尔大学) Canon Medical Systems (China) Co. Ltd.(佳能医疗系统(中国)有限公司) School of Biomedical Engineering, Shenzhen University Medical School(深圳大学医学院生物医学工程学院) Department of Imaging Physics, Delft University of Technology(代尔夫特理工大学成像物理系) Technical University of Munich(慕尼黑技术大学) Radboud University Medical Center(拉德伯德大学医学中心) Inria, Paris, France(法国巴黎Inria)

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

AI总结 提出LUMIR挑战,通过大规模无监督脑MRI配准任务,验证深度学习方法在生成解剖合理变形场和跨域鲁棒性上的优势,推动通用医学图像配准基础模型的发展。

Comments Accepted to Medical Image Analysis ((c) MedIA). Code available at https://github.com/JHU-MedImage-Reg/LUMIR_L2R

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.17425 2026-08-19 cs.CV 新提交 85%

GSToken: Geometry-Structured Gaussian Tokens for Compact 3D Medical Image Representation

GSToken:用于紧凑三维医学图像表示的几何结构化高斯令牌

Xiaoduo Li, Quan Gu

机构 * Taiyuan University of Technology(太原理工大学)

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

AI总结 本文提出GSToken,一种带显式几何信息的高斯令牌,通过冻结令牌生成器的评估协议验证其在多模态脑肿瘤分割中,比容量匹配基线更优,可提升三维医学图像表示的信息密度。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.09953 2026-08-17 cs.CV 版本更新 85%

J-RAS: Mutual Adaptation for Medical Image Segmentation via Contrastive Retrieval-Augmented Joint Optimization

J-RAS:基于对比检索增强联合优化的医学图像分割互适应方法

Salma J. Ahmed, Emad A. Mohammed, Azam Asilian Bidgoli

机构 * Laurier University(劳里尔大学)

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

AI总结 提出J-RAS框架,通过交替对比学习和监督学习联合优化分割与检索模型,实现检索与分割的互适应,提升医学图像分割的边界描绘、鲁棒性和跨数据集泛化能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.08713 2026-08-11 cs.CV cs.AI 新提交 85%

Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation

分辨率与压缩结合:面向3D放射报告生成的高效视觉上下文

Jonathan Suprijadi, Raphael Stock, Moritz Langenberg, David Zimmerer, Kim-Celine Kahl, Stefan Denner, Yannick Kirchhoff, Karol Gotkowski, Maximilian Rokuss, Jeremias Traub, Tassilo Wald, Constantin Ulrich, Klaus Maier-Hein

机构 * German Cancer Research Center (DKFZ)(德国癌症研究中心)

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

AI总结 该研究针对3D放射报告生成中视觉序列的计算瓶颈,通过实验评估不同视觉编码器、投影器和LLM,提出解剖学引导的ROI裁剪等策略,在两个数据集上取得最先进的临床macro F1结果。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.01808 2026-08-04 cs.CV 新提交 85%

SecondOpinion: Anatomy-Aware Gated Reasoning for Efficient Medical Image Analysis

SecondOpinion:面向高效医学图像分析的解剖感知门控推理

Siam Tahsin Bhuiyan, Rashedur Rahman, Sefatul Wasi, Riyadul Islam, Syoji Kobashi, Ashraful Islam, Saadia Binte Alam

机构 * Center for Computational & Data Sciences, Independent University, Bangladesh(孟加拉国独立大学计算与数据科学中心) Department of Computer Science and Engineering, Independent University, Bangladesh(孟加拉国独立大学计算机科学与工程系) Graduate School of Engineering, University of Hyogo(兵库大学工程研究生院)

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

AI总结 SecondOpinion是一种医学图像分析框架,通过训练为二元正确性分类器的门控机制按需调用解剖引导流,在保持性能的同时降低计算量,激活率与任务难度直接相关。

Comments Accepted at EMA4MICCAI 2026 (MICCAI Workshop)

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.29253 2026-08-03 physics.med-ph cs.CV 新提交 85%

CBCT-IQ: A Publicly Available Annotated Cone-Beam CT Dataset for Image Quality Assessment and Benchmarking

CBCT-IQ:用于图像质量评估与基准测试的公开标注锥形束CT数据集

Sepideh Hatamikia, Anna Breger, Clemens Karner, Birgit Pohn, Poorya MohammadiNasab, Martin Buschmann, Stephanie Nougaret, Laura Haddad, Ali Abbasian Ardakani, Afshin Mohammadi, Paul Apfaltrer, Wolfgang Birkfellner, Alfred Pohl, Ander Biguri, Gernot Kronreif, Carola-Bibiane Schönlieb, Tess Reynolds

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

AI总结 本研究构建首个公开标注的CBCT-IQ数据集,含1764张经专家评分的CBCT图像,对26种IQA指标基准测试并提出排名方法,为CBCT IQA研究提供标准化资源。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.09893 2026-08-03 cs.CV cs.CL 85%

Regional Attention-Enhanced Swin Transformer for Clinically Relevant Medical Image Captioning

Zubia Naz, Farhan Asghar, Muhammad Ishfaq Hussain, Yahya Hadadi, Muhammad Aasim Rafique, Wookjin Choi, Moongu Jeon

机构 * Electrical Engineering and Computer Science(电子工程与计算机科学) Gwangju Institute of Science and Technology(全州科学技术研究院) Electrical and Computer Engineering Department(电子与计算机工程系) Chonnam National University(全南国立大学) AI Convergence Department(人工智能融合部门) Department of Information Systems, CCSIT(信息系统系,CCSIT) King Faisal University(国王费萨尔大学) Thomas Jefferson University, Philadelphia(费城托马斯杰斐逊大学)

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

Journal ref 2026 IEEE 5th International Conference on Computing and Machine Intelligence (ICMI), 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.28565 2026-07-31 cs.CV 新提交 85%

MIND: Multimodal Intent-Driven Network via Diffusion Transformers for Medical Image Fusion

MIND:基于扩散Transformer的多模态意图驱动网络用于医学图像融合

Yunzhan Fu, Xiangyu Shen, Yifei Sun, Yuhan Chen, Jian Wu, Hongxia Xu

机构 * Transvascular Implantation Devices Research Institute, Zhejiang University(浙江大学血管内植入器械研究院) Zhejiang University(浙江大学) Hangzhou Institute of Technology, Xidian University(西安电子科技大学杭州研究院) Hangzhou Dianzi University(杭州电子科技大学)

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

AI总结 该研究针对现有医学图像融合方法缺乏对诊断意图深度理解的问题,提出基于DiTs的MIND网络,通过BioMedGPT、多尺度潜在适配器和医学语义一致性损失优化,在多数据集上取得优异效果,可提升脑肿瘤分割精度并支持交互式融合。

Comments 14pages, 14 figures, accepted by ACM MM2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.22293 2026-07-27 cs.CV 新提交 85%

RadSight: Towards Perceptually Reliable Multimodal Radiology Image Understanding

RadSight:迈向感知可靠的多模态放射学图像理解

Jianqin Liu, Weiwei Cao, Wanxing Chang, Ruifeng Yuan, Bowen Shi, Zhilin Zheng, Xianjie Zhang, Ling Zhang, Peng Wang, Jianpeng Zhang

机构 * DAMO Academy, Alibaba Group(达摩院,阿里巴巴集团) Hupan Lab(湖畔实验室) University of Electronic Science and Technology of China(电子科技大学)

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

AI总结 该研究针对医学多模态大语言模型视觉解释可靠性低的问题,引入Perception-Bench基准分析问题。提出基于双2D/3D编码器架构的RadSight模型,经渐进课程学习训练,在多维度评估中优于现有模型,凸显低级视觉感知对可靠临床理解的关键作用。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.16291 2026-07-21 cs.CV 新提交 85%

Beyond Target Scores: Measuring Off-Target Drift in Diffusion-Based Medical Image Editing

超越目标分数:测量基于扩散的医学图像编辑中的偏离目标漂移

Todd Zhou

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

AI总结 研究基于扩散的医学图像编辑中偏离目标漂移问题,引入CIB-Med-1基准及受约束扩散引导基线,通过多指标评估编辑效果,实验显示能保留目标进展并减少偏离目标漂移,强调应从轨迹级语义控制角度评估医学图像编辑。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.13300 2026-07-16 cs.CV 新提交 85%

Improving Medical Image Generative Models with Fréchet Distance Loss

用弗雷歇距离损失改进医学图像生成模型

Andrew Marshall, Xuanang Xu, Xiaoran Zhang, Rui Wang, Lawrence Staib, James Duncan

机构 * Yale University(耶鲁大学)

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

AI总结 研究针对扩散生成模型难以捕捉异质性肿瘤复杂形态特征的问题,提出用弗雷歇距离损失微调模型,通过在多数据集上集成该损失,提升了下游分割网络性能,证明其是改进医学图像生成模型临床工作流程的有效正则化方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.13544 2026-07-03 cs.CV 版本更新 85%

CA-GCL: Cross-Anatomy Global-Local Contrastive Learning for Robust 3D Medical Image Understanding

CA-GCL:跨解剖全局-局部对比学习用于稳健的3D医学图像理解

Hanwen Zhang, Yao Liu, Die Dai, Jiaye Yang, Qiao Liu, Yutong Xie, Peng Wang

机构 * University of Electronic Science and Technology of China(电子科技大学) Mohamed bin Zayed University of Artificial Intelligence(莫扎德人工智能大学)

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

AI总结 本文提出CA-GCL框架,通过全局对比学习和临床感知文本增强,解决3D医学图像理解中文本嵌入空间退化问题,提升零样本异常检测性能和跨数据集泛化能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.16650 2026-06-24 eess.IV cs.CV q-bio.QM 版本更新 85%

Predicting brain tumour enhancement from non-contrast MR imaging with artificial intelligence: a multi-cohort retrospective diagnostic accuracy study

基于人工智能从非对比MR成像预测脑肿瘤强化:一项多队列回顾性诊断准确性研究

James K Ruffle, Samia Mohinta, Guilherme Pombo, Asthik Biswas, Alan Campbell, Indran Davagnanam, David Doig, Ahmed Hammam, Harpreet Hyare, Farrah Jabeen, Emma Lim, Dermot Mallon, Stephanie Owen, Sophie Wilkinson, Sebastian Brandner, Parashkev Nachev

机构 * Queen Square Institute of Neurology, University College London, London, UK(伦敦大学学院医院神经科学研究所) National Hospital for Neurology and Neurosurgery, London, UK(伦敦神经病学与神经外科医院) NVIDIA, UK(英国NVIDIA公司) Great Ormond Street Hospital for Children, London, UK(伦敦儿童医院) Royal National Orthopaedic Hospital, Stanmore, Middlesex, UK(斯坦莫尔皇家骨科医院,中西敏,英国) University College Hospitals NHS Foundation Trust, London, UK(伦敦大学学院医院 NHS 基础信托) Royal Free Hospital, London, UK(伦敦皇家自由医院) Imperial College Healthcare NHS Trust, London, UK(伦敦帝国学院医疗信托) Imperial College London, London, UK(伦敦帝国学院)

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

AI总结 本研究开发并验证了深度学习模型,仅从非对比MRI预测肿瘤对比增强,在多个数据集上达到83.0%的平衡准确率,有望减少神经肿瘤成像中对钆的依赖。

Comments 44 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.15323 2026-06-16 cs.CV 新提交 85%

PPDM: Pixel Puzzling Diffusion Model for Speed and Memory Efficient Volumetric Medical Image Translation

PPDM: 像素拼图扩散模型用于速度和内存高效的体积医学图像翻译

Tianqi Chen, Jun Hou, Yinchi Zhou, James S. Duncan, Chi Liu, Bo Zhou

机构 * Department of Radiology, Northwestern University(西北大学放射学系) Department of Biomedical Engineering, Yale University(耶鲁大学生物医学工程系) Department of Radiology and Biomedical Imaging, Yale School of Medicine(耶鲁医学院放射学与生物医学影像系)

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

AI总结 提出像素拼图扩散模型(PPDM),通过可逆像素拼图操作和直接桥接扩散公式,在降低内存和加速推理的同时保持全局一致性,用于3D医学图像翻译。

Comments 12 pages, 5 figures, 5 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.04301 2026-06-04 cs.CV 85%

XSSR: Cross-Domain Self-Supervised Representative Selection for Efficient Annotation in Medical Image Segmentation

XSSR: 跨域自监督代表性选择用于医学图像分割中的高效标注

Byunghyun Ko, Aleksei Anisimov, Kobe Ke, Suhas Bharthepude, Jeongkyu Lee

机构 * Northeastern University, San Jose, CA 95113, USA(东北大学,旧金山,CA 95113,美国) Northeastern University, New York, NY 10021, USA(东北大学,纽约,NY 10021,美国)

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

AI总结 提出XSSR框架,通过自监督学习在目标域中自动选择代表性样本进行标注,在仅使用5%标注预算时达到接近全数据性能。

Comments Accepted to the Third International Conference on AI in Healthcare (AIiH 2026). This is the preprint version of the paper

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.25144 2026-06-02 cs.CV 85%

SpikeReg: Energy-Efficient 3D Deformable Medical Image Registration with Spiking Neural Networks

SpikeReg: 基于脉冲神经网络的高能效3D可变形医学图像配准

Ali Mikaeili Barzili, Behzad Moshiri, Hamid Azadegan, Mohammad-Reza A. Dehaqani

机构 * School of Electrical and Computer Engineering, College of Engineering, University of Tehran(德黑兰大学电气与计算机工程学院) Max Planck Institute for Brain Research(马克斯·普朗克脑科学研究所) 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) Department of Electrical and Computer Engineering, University of Waterloo(滑铁卢大学电气与计算机工程系)

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

AI总结 提出SpikeReg,一种脉冲U-Net,通过层间权重迁移和激活百分位阈值校准从模拟ANN教师初始化,结合局部互相关、扩散正则化和脉冲率稀疏性的代理梯度微调,在OASIS Learn2Reg验证集上达到Dice 0.7474,与ANN教师无显著差异,同时实现12.8%平均脉冲率和55.5倍算术能量降低。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.30972 2026-06-01 cs.CV 85%

BiSegMamba: Efficient Bidirectional Tri-Oriented Mamba for 3D Medical Image Segmentation

BiSegMamba: 用于3D医学图像分割的高效双向三向Mamba

Bakht Zada, Chao Tong, Qile Su, Shuai Zhang

机构 * School of Computer Science and Engineering, Beihang University(北航计算机科学与工程学院) State Key Laboratory of Virtual Reality Technology and Systems, Beihang University(北航虚拟现实技术与系统国家重点实验室)

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

AI总结 提出BiSegMamba,一种基于双向三向Mamba的高效3D医学图像分割网络,通过渐进压缩主干、多尺度空间混合器、双向正交Mamba块和自适应方向融合,在降低计算成本的同时提升分割精度。

Comments 10 pages, 7 figures, 5 tables. Code is available at: https://github.com/bakhtzadaabshare/BiSegMamba

详情

展开后加载摘要…

URL PDF HTML 收藏