Evaluation of Unsupervised Deformable Image Registration Using CNN and ViT on 4D-CT.

IF 1.1 4区医学 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Current Medical Imaging Reviews Pub Date : 2025-10-22 DOI:10.2174/0115734056385097251010051841

Peizhi Chen, Jialan Wang, Yifan Guo, Yan Wang

{"title":"Evaluation of Unsupervised Deformable Image Registration Using CNN and ViT on 4D-CT.","authors":"Peizhi Chen, Jialan Wang, Yifan Guo, Yan Wang","doi":"10.2174/0115734056385097251010051841","DOIUrl":null,"url":null,"abstract":"Introduction: Deformable image registration is essential in medical image analysis. The state-of-the-art approaches are unsupervised methods based on convolutional neural networks (CNN) and vision transformers (ViT). While CNNs perform well in extracting local features, ViTs perform better in extracting global features.Objective: This study aimed to compare the performance of CNN and ViT in unsupervised deformable image registration.Method: We have proposed a unified registration framework and evaluated both architectures. Experiments have been conducted using 4D-CT.Results: The results have shown ViT-based registration to achieve superior performance compared to CNN-based methods.Conclusion: The findings have indicated vision transformer architectures to be more effective than convolutional networks for unsupervised deformable registration on 4D-CT data. Foundation Item: This work is supported by the National Natural Science Foundation of China (No.61801413).","PeriodicalId":54215,"journal":{"name":"Current Medical Imaging Reviews","volume":" ","pages":""},"PeriodicalIF":1.1000,"publicationDate":"2025-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Current Medical Imaging Reviews","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.2174/0115734056385097251010051841","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}

引用次数: 0

Abstract

Introduction: Deformable image registration is essential in medical image analysis. The state-of-the-art approaches are unsupervised methods based on convolutional neural networks (CNN) and vision transformers (ViT). While CNNs perform well in extracting local features, ViTs perform better in extracting global features.

Objective: This study aimed to compare the performance of CNN and ViT in unsupervised deformable image registration.

Method: We have proposed a unified registration framework and evaluated both architectures. Experiments have been conducted using 4D-CT.

Results: The results have shown ViT-based registration to achieve superior performance compared to CNN-based methods.

Conclusion: The findings have indicated vision transformer architectures to be more effective than convolutional networks for unsupervised deformable registration on 4D-CT data. Foundation Item: This work is supported by the National Natural Science Foundation of China (No.61801413).

查看原文本刊更多论文

基于CNN和ViT的4D-CT无监督形变图像配准评价。

变形图像配准在医学图像分析中是必不可少的。最先进的方法是基于卷积神经网络（CNN）和视觉变压器（ViT）的无监督方法。cnn在提取局部特征方面表现良好，而ViTs在提取全局特征方面表现更好。目的：比较CNN和ViT在无监督变形图像配准中的性能。方法：我们提出了一个统一的注册框架，并对两种架构进行了评估。利用4D-CT进行了实验。结果：结果表明，与基于cnn的配准方法相比，基于vitv的配准方法具有更优越的性能。结论：研究结果表明，对于4D-CT数据的无监督形变配准，视觉转换器架构比卷积网络更有效。基金项目：国家自然科学基金（No.61801413）资助。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Current Medical Imaging Reviews 医学-核医学

CiteScore

2.60

自引率

0.00%

发文量

246

审稿时长

1 months

期刊介绍： Current Medical Imaging Reviews publishes frontier review articles, original research articles, drug clinical trial studies and guest edited thematic issues on all the latest advances on medical imaging dedicated to clinical research. All relevant areas are covered by the journal, including advances in the diagnosis, instrumentation and therapeutic applications related to all modern medical imaging techniques. The journal is essential reading for all clinicians and researchers involved in medical imaging and diagnosis.