DC-Net:超声图像病变分割的显著性图分解与耦合

IF 8 2区 计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS
Zhenyuan Ning , Yixiao Mao , Xiaotong Xu, Qianjin Feng, Shengzhou Zhong, Yu Zhang
{"title":"DC-Net:超声图像病变分割的显著性图分解与耦合","authors":"Zhenyuan Ning ,&nbsp;Yixiao Mao ,&nbsp;Xiaotong Xu,&nbsp;Qianjin Feng,&nbsp;Shengzhou Zhong,&nbsp;Yu Zhang","doi":"10.1016/j.engappai.2025.110355","DOIUrl":null,"url":null,"abstract":"<div><div>Accurate lesion segmentation in ultrasound images faces the unique challenge that adjacent tissues (<em>i.e.</em>, background) share similar intensity and often exhibit richer texture patterns than the lesion region (<em>i.e.</em>, foreground). This work presents a decomposition-coupling network, called DC-Net, to deal with this challenge in a (foreground-background) saliency map disentanglement-fusion manner. The DC-Net consists of decomposition and coupling subnets, and the former preliminarily disentangles original image into foreground and background saliency maps, followed by the latter for accurate segmentation under the assistance of saliency prior fusion. The coupling subnet involves three aspects of fusion strategies, including: (1) regional feature aggregation (via differentiable context pooling operator in the encoder) to adaptively preserve local contextual details with the larger receptive field during dimension reduction; (2) relation-aware representation fusion (via cross-correlation fusion module in the decoder) to efficiently fuse low-level visual characteristics and high-level semantic features during resolution restoration; (3) dependency-aware prior incorporation (via coupler) to reinforce foreground-salient representation with the complementary information derived from background representation. Furthermore, a harmonic loss function is introduced to encourage the network to focus more attention on low-confidence and hard pixels. The proposed method is evaluated on two ultrasound lesion segmentation tasks, achieving better performance than second best methods (<em>i.e.</em>, dice similarity coefficient: 73.96 ± 0.36 (+4.18%)/76.25 ± 1.89 (+3.88%), mean intersection over union/jaccard index: 64.26 ± 0.48 (+5.07%)/65.28 ± 2.24 (+6.46%), precision: 75.82 ± 1.16 (+8.07%)/79.35 ± 1.92 (+3.07%), 95% hausdorff distance: 5.44 ± 0.10 (+5.39%)/6.22 ± 0.26 (+5.18%) on breast/thyroid ultrasound). Our proposed DC-Net can adapt to multiple ultrasound segmentation tasks and achieve remarkable performance improvement. Our code is available at <span><span>https://github.com/smu-myx/DC-Net</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"148 ","pages":"Article 110355"},"PeriodicalIF":8.0000,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"DC-Net: Decomposing and coupling saliency map for lesion segmentation in ultrasound images\",\"authors\":\"Zhenyuan Ning ,&nbsp;Yixiao Mao ,&nbsp;Xiaotong Xu,&nbsp;Qianjin Feng,&nbsp;Shengzhou Zhong,&nbsp;Yu Zhang\",\"doi\":\"10.1016/j.engappai.2025.110355\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Accurate lesion segmentation in ultrasound images faces the unique challenge that adjacent tissues (<em>i.e.</em>, background) share similar intensity and often exhibit richer texture patterns than the lesion region (<em>i.e.</em>, foreground). This work presents a decomposition-coupling network, called DC-Net, to deal with this challenge in a (foreground-background) saliency map disentanglement-fusion manner. The DC-Net consists of decomposition and coupling subnets, and the former preliminarily disentangles original image into foreground and background saliency maps, followed by the latter for accurate segmentation under the assistance of saliency prior fusion. The coupling subnet involves three aspects of fusion strategies, including: (1) regional feature aggregation (via differentiable context pooling operator in the encoder) to adaptively preserve local contextual details with the larger receptive field during dimension reduction; (2) relation-aware representation fusion (via cross-correlation fusion module in the decoder) to efficiently fuse low-level visual characteristics and high-level semantic features during resolution restoration; (3) dependency-aware prior incorporation (via coupler) to reinforce foreground-salient representation with the complementary information derived from background representation. Furthermore, a harmonic loss function is introduced to encourage the network to focus more attention on low-confidence and hard pixels. The proposed method is evaluated on two ultrasound lesion segmentation tasks, achieving better performance than second best methods (<em>i.e.</em>, dice similarity coefficient: 73.96 ± 0.36 (+4.18%)/76.25 ± 1.89 (+3.88%), mean intersection over union/jaccard index: 64.26 ± 0.48 (+5.07%)/65.28 ± 2.24 (+6.46%), precision: 75.82 ± 1.16 (+8.07%)/79.35 ± 1.92 (+3.07%), 95% hausdorff distance: 5.44 ± 0.10 (+5.39%)/6.22 ± 0.26 (+5.18%) on breast/thyroid ultrasound). Our proposed DC-Net can adapt to multiple ultrasound segmentation tasks and achieve remarkable performance improvement. Our code is available at <span><span>https://github.com/smu-myx/DC-Net</span><svg><path></path></svg></span>.</div></div>\",\"PeriodicalId\":50523,\"journal\":{\"name\":\"Engineering Applications of Artificial Intelligence\",\"volume\":\"148 \",\"pages\":\"Article 110355\"},\"PeriodicalIF\":8.0000,\"publicationDate\":\"2025-03-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Engineering Applications of Artificial Intelligence\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0952197625003550\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"AUTOMATION & CONTROL SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Engineering Applications of Artificial Intelligence","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0952197625003550","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AUTOMATION & CONTROL SYSTEMS","Score":null,"Total":0}
引用次数: 0

摘要

超声图像中病灶的准确分割面临着一个独特的挑战,即相邻组织(即背景)具有相似的强度,并且通常比病变区域(即前景)具有更丰富的纹理模式。这项工作提出了一个分解耦合网络,称为DC-Net,以(前景-背景)显著性图解纠缠-融合的方式处理这一挑战。DC-Net由分解子网和耦合子网组成,前者将原始图像初步分解为前景和背景显著性图,后者在显著性先验融合的辅助下进行精确分割。耦合子网涉及三个方面的融合策略,包括:(1)区域特征聚合(通过编码器中的可微分上下文池算子),在降维过程中自适应地保留更大接受场的局部上下文细节;(2)关系感知表示融合(通过解码器中的互相关融合模块),在分辨率恢复过程中有效融合低层次视觉特征和高层次语义特征;(3)依赖感知先验合并(通过耦合器),利用背景表示的互补信息增强前景显著表示。此外,引入了谐波损失函数,以鼓励网络更多地关注低置信度和硬像素。对两种超声病灶分割任务进行了评价,结果表明,该方法的分割效果优于第二优方法(即:dice similarity coefficient: 73.96±0.36(+4.18%)/76.25±1.89(+3.88%),平均相交比union/jaccard指数:64.26±0.48(+5.07%)/65.28±2.24(+6.46%),精密度:75.82±1.16(+8.07%)/79.35±1.92 (+3.07%),95% hausdorff distance: 5.44±0.10(+5.39%)/6.22±0.26(+5.18%))。我们提出的DC-Net可以适应多种超声分割任务,并取得显著的性能提升。我们的代码可在https://github.com/smu-myx/DC-Net上获得。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
DC-Net: Decomposing and coupling saliency map for lesion segmentation in ultrasound images
Accurate lesion segmentation in ultrasound images faces the unique challenge that adjacent tissues (i.e., background) share similar intensity and often exhibit richer texture patterns than the lesion region (i.e., foreground). This work presents a decomposition-coupling network, called DC-Net, to deal with this challenge in a (foreground-background) saliency map disentanglement-fusion manner. The DC-Net consists of decomposition and coupling subnets, and the former preliminarily disentangles original image into foreground and background saliency maps, followed by the latter for accurate segmentation under the assistance of saliency prior fusion. The coupling subnet involves three aspects of fusion strategies, including: (1) regional feature aggregation (via differentiable context pooling operator in the encoder) to adaptively preserve local contextual details with the larger receptive field during dimension reduction; (2) relation-aware representation fusion (via cross-correlation fusion module in the decoder) to efficiently fuse low-level visual characteristics and high-level semantic features during resolution restoration; (3) dependency-aware prior incorporation (via coupler) to reinforce foreground-salient representation with the complementary information derived from background representation. Furthermore, a harmonic loss function is introduced to encourage the network to focus more attention on low-confidence and hard pixels. The proposed method is evaluated on two ultrasound lesion segmentation tasks, achieving better performance than second best methods (i.e., dice similarity coefficient: 73.96 ± 0.36 (+4.18%)/76.25 ± 1.89 (+3.88%), mean intersection over union/jaccard index: 64.26 ± 0.48 (+5.07%)/65.28 ± 2.24 (+6.46%), precision: 75.82 ± 1.16 (+8.07%)/79.35 ± 1.92 (+3.07%), 95% hausdorff distance: 5.44 ± 0.10 (+5.39%)/6.22 ± 0.26 (+5.18%) on breast/thyroid ultrasound). Our proposed DC-Net can adapt to multiple ultrasound segmentation tasks and achieve remarkable performance improvement. Our code is available at https://github.com/smu-myx/DC-Net.
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
Engineering Applications of Artificial Intelligence
Engineering Applications of Artificial Intelligence 工程技术-工程:电子与电气
CiteScore
9.60
自引率
10.00%
发文量
505
审稿时长
68 days
期刊介绍: Artificial Intelligence (AI) is pivotal in driving the fourth industrial revolution, witnessing remarkable advancements across various machine learning methodologies. AI techniques have become indispensable tools for practicing engineers, enabling them to tackle previously insurmountable challenges. Engineering Applications of Artificial Intelligence serves as a global platform for the swift dissemination of research elucidating the practical application of AI methods across all engineering disciplines. Submitted papers are expected to present novel aspects of AI utilized in real-world engineering applications, validated using publicly available datasets to ensure the replicability of research outcomes. Join us in exploring the transformative potential of AI in engineering.
×
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