ES-UNet:高效的3D医学图像分割,在3D UNet中具有增强的跳过连接。

IF 3.2 3区 医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING
Minyoung Park, Seungtaek Oh, Junyoung Park, Taikyeong Jeong, Sungwook Yu
{"title":"ES-UNet:高效的3D医学图像分割,在3D UNet中具有增强的跳过连接。","authors":"Minyoung Park, Seungtaek Oh, Junyoung Park, Taikyeong Jeong, Sungwook Yu","doi":"10.1186/s12880-025-01857-0","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Deep learning has significantly advanced medical image analysis, particularly in semantic segmentation, which is essential for clinical decisions. However, existing 3D segmentation models, like the traditional 3D UNet, face challenges in balancing computational efficiency and accuracy when processing volumetric medical data. This study aims to develop an improved architecture for 3D medical image segmentation with enhanced learning strategies to improve accuracy and address challenges related to limited training data.</p><p><strong>Methods: </strong>We propose ES-UNet, a 3D segmentation architecture that achieves superior segmentation performance while offering competitive efficiency across multiple computational metrics, including memory usage, inference time, and parameter count. The model builds upon the full-scale skip connection design of UNet3+ by integrating channel attention modules into each encoder-to-decoder path and incorporating full-scale deep supervision to enhance multi-resolution feature learning. We further introduce Region Specific Scaling (RSS), a data augmentation method that adaptively applies geometric transformations to annotated regions, and a Dynamically Weighted Dice (DWD) loss to improve the balance between precision and recall. The model was evaluated on the MICCAI HECKTOR dataset, and additional validation was conducted on selected tasks from the Medical Segmentation Decathlon (MSD).</p><p><strong>Results: </strong>On the HECKTOR dataset, ES-UNet achieved a Dice Similarity Coefficient (DSC) of 76.87%, outperforming baseline models including 3D UNet, 3D UNet 3+, nnUNet, and Swin UNETR. Ablation studies showed that RSS and DWD contributed up to 1.22% and 1.06% improvement in DSC, respectively. A sensitivity analysis demonstrated that the chosen scaling range in RSS offered a favorable trade-off between deformation and anatomical plausibility. Cross-dataset evaluation on MSD Heart and Spleen tasks also indicated strong generalization. Computational analysis revealed that ES-UNet achieves superior segmentation performance with moderate computational demands. Specifically, the enhanced skip connection design with lightweight channel attention modules integrated throughout the network architecture enables this favorable balance between high segmentation accuracy and computational efficiency.</p><p><strong>Conclusion: </strong>ES-UNet integrates architectural and algorithmic improvements to achieve robust 3D medical image segmentation. While the framework incorporates established components, its core contributions lie in the optimized skip connection strategy and supporting techniques like RSS and DWD. Future work will explore adaptive scaling strategies and broader validation across diverse imaging modalities.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"327"},"PeriodicalIF":3.2000,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12351991/pdf/","citationCount":"0","resultStr":"{\"title\":\"ES-UNet: efficient 3D medical image segmentation with enhanced skip connections in 3D UNet.\",\"authors\":\"Minyoung Park, Seungtaek Oh, Junyoung Park, Taikyeong Jeong, Sungwook Yu\",\"doi\":\"10.1186/s12880-025-01857-0\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Deep learning has significantly advanced medical image analysis, particularly in semantic segmentation, which is essential for clinical decisions. However, existing 3D segmentation models, like the traditional 3D UNet, face challenges in balancing computational efficiency and accuracy when processing volumetric medical data. This study aims to develop an improved architecture for 3D medical image segmentation with enhanced learning strategies to improve accuracy and address challenges related to limited training data.</p><p><strong>Methods: </strong>We propose ES-UNet, a 3D segmentation architecture that achieves superior segmentation performance while offering competitive efficiency across multiple computational metrics, including memory usage, inference time, and parameter count. The model builds upon the full-scale skip connection design of UNet3+ by integrating channel attention modules into each encoder-to-decoder path and incorporating full-scale deep supervision to enhance multi-resolution feature learning. We further introduce Region Specific Scaling (RSS), a data augmentation method that adaptively applies geometric transformations to annotated regions, and a Dynamically Weighted Dice (DWD) loss to improve the balance between precision and recall. The model was evaluated on the MICCAI HECKTOR dataset, and additional validation was conducted on selected tasks from the Medical Segmentation Decathlon (MSD).</p><p><strong>Results: </strong>On the HECKTOR dataset, ES-UNet achieved a Dice Similarity Coefficient (DSC) of 76.87%, outperforming baseline models including 3D UNet, 3D UNet 3+, nnUNet, and Swin UNETR. Ablation studies showed that RSS and DWD contributed up to 1.22% and 1.06% improvement in DSC, respectively. A sensitivity analysis demonstrated that the chosen scaling range in RSS offered a favorable trade-off between deformation and anatomical plausibility. Cross-dataset evaluation on MSD Heart and Spleen tasks also indicated strong generalization. Computational analysis revealed that ES-UNet achieves superior segmentation performance with moderate computational demands. Specifically, the enhanced skip connection design with lightweight channel attention modules integrated throughout the network architecture enables this favorable balance between high segmentation accuracy and computational efficiency.</p><p><strong>Conclusion: </strong>ES-UNet integrates architectural and algorithmic improvements to achieve robust 3D medical image segmentation. While the framework incorporates established components, its core contributions lie in the optimized skip connection strategy and supporting techniques like RSS and DWD. Future work will explore adaptive scaling strategies and broader validation across diverse imaging modalities.</p>\",\"PeriodicalId\":9020,\"journal\":{\"name\":\"BMC Medical Imaging\",\"volume\":\"25 1\",\"pages\":\"327\"},\"PeriodicalIF\":3.2000,\"publicationDate\":\"2025-08-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12351991/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"BMC Medical Imaging\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1186/s12880-025-01857-0\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"BMC Medical Imaging","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s12880-025-01857-0","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0

摘要

背景:深度学习显著推进了医学图像分析,特别是在语义分割方面,这对临床决策至关重要。然而,现有的3D分割模型,如传统的3D UNet,在处理体积医学数据时,在平衡计算效率和准确性方面面临挑战。本研究旨在通过增强的学习策略开发一种改进的3D医学图像分割架构,以提高准确性并解决与有限训练数据相关的挑战。方法:我们提出ES-UNet,这是一种3D分割架构,在实现卓越的分割性能的同时,在多个计算指标(包括内存使用、推理时间和参数计数)上提供具有竞争力的效率。该模型基于UNet3+的全尺寸跳跃式连接设计,将信道关注模块集成到每个编码器到解码器路径中,并结合全尺寸深度监督,增强多分辨率特征学习。我们进一步介绍了区域特定缩放(RSS),一种自适应地对注释区域应用几何变换的数据增强方法,以及动态加权骰子(DWD)损失,以改善精度和召回率之间的平衡。该模型在MICCAI HECKTOR数据集上进行了评估,并在医学分割十项全能(MSD)的选定任务上进行了额外的验证。结果:在HECKTOR数据集上,ES-UNet的骰子相似系数(DSC)达到76.87%,优于3D UNet、3D UNet 3+、nnUNet和Swin UNETR等基准模型。消融研究表明,RSS和DWD分别对DSC的改善贡献高达1.22%和1.06%。敏感性分析表明,在RSS中选择的尺度范围提供了变形和解剖合理性之间的有利权衡。对MSD心脏和脾脏任务的跨数据集评估也显示出很强的泛化。计算分析表明,ES-UNet在计算量适中的情况下实现了优越的分割性能。具体来说,在整个网络架构中集成了轻量级信道关注模块的增强型跳过连接设计,实现了高分割精度和计算效率之间的良好平衡。结论:ES-UNet集成了架构和算法改进,实现了鲁棒的三维医学图像分割。虽然该框架包含了已建立的组件,但其核心贡献在于优化的跳过连接策略以及RSS和DWD等支持技术。未来的工作将探索自适应缩放策略和更广泛的验证在不同的成像模式。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
ES-UNet: efficient 3D medical image segmentation with enhanced skip connections in 3D UNet.

Background: Deep learning has significantly advanced medical image analysis, particularly in semantic segmentation, which is essential for clinical decisions. However, existing 3D segmentation models, like the traditional 3D UNet, face challenges in balancing computational efficiency and accuracy when processing volumetric medical data. This study aims to develop an improved architecture for 3D medical image segmentation with enhanced learning strategies to improve accuracy and address challenges related to limited training data.

Methods: We propose ES-UNet, a 3D segmentation architecture that achieves superior segmentation performance while offering competitive efficiency across multiple computational metrics, including memory usage, inference time, and parameter count. The model builds upon the full-scale skip connection design of UNet3+ by integrating channel attention modules into each encoder-to-decoder path and incorporating full-scale deep supervision to enhance multi-resolution feature learning. We further introduce Region Specific Scaling (RSS), a data augmentation method that adaptively applies geometric transformations to annotated regions, and a Dynamically Weighted Dice (DWD) loss to improve the balance between precision and recall. The model was evaluated on the MICCAI HECKTOR dataset, and additional validation was conducted on selected tasks from the Medical Segmentation Decathlon (MSD).

Results: On the HECKTOR dataset, ES-UNet achieved a Dice Similarity Coefficient (DSC) of 76.87%, outperforming baseline models including 3D UNet, 3D UNet 3+, nnUNet, and Swin UNETR. Ablation studies showed that RSS and DWD contributed up to 1.22% and 1.06% improvement in DSC, respectively. A sensitivity analysis demonstrated that the chosen scaling range in RSS offered a favorable trade-off between deformation and anatomical plausibility. Cross-dataset evaluation on MSD Heart and Spleen tasks also indicated strong generalization. Computational analysis revealed that ES-UNet achieves superior segmentation performance with moderate computational demands. Specifically, the enhanced skip connection design with lightweight channel attention modules integrated throughout the network architecture enables this favorable balance between high segmentation accuracy and computational efficiency.

Conclusion: ES-UNet integrates architectural and algorithmic improvements to achieve robust 3D medical image segmentation. While the framework incorporates established components, its core contributions lie in the optimized skip connection strategy and supporting techniques like RSS and DWD. Future work will explore adaptive scaling strategies and broader validation across diverse imaging modalities.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
BMC Medical Imaging
BMC Medical Imaging RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING-
CiteScore
4.60
自引率
3.70%
发文量
198
审稿时长
27 weeks
期刊介绍: BMC Medical Imaging is an open access journal publishing original peer-reviewed research articles in the development, evaluation, and use of imaging techniques and image processing tools to diagnose and manage disease.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信