Multi-scale adversarial learning with difficult region supervision learning models for primary tumor segmentation

作者全名："Zheng, Shenhai; Sun, Qiuyu; Ye, Xin; Li, Weisheng; Yu, Lei; Yang, Chaohui"

作者地址："[Zheng, Shenhai; Sun, Qiuyu; Ye, Xin; Li, Weisheng] Chongqing Univ Posts & Telecommun, Coll Comp Sci & Technol, Chongqing, Peoples R China; [Zheng, Shenhai; Li, Weisheng] Chongqing Univ Posts & Telecommun, Chongqing, Peoples R China; [Yu, Lei] Second Affiliated Hosp Chongqing Med Univ, Chongqing, Peoples R China; [Yang, Chaohui] NanPeng Artificial Intelligence Res Inst Ltd, Chongqing, Peoples R China"

通信作者："Zheng, SH (通讯作者)，Chongqing Univ Posts & Telecommun, Coll Comp Sci & Technol, Chongqing, Peoples R China.; Zheng, SH (通讯作者)，Chongqing Univ Posts & Telecommun, Chongqing, Peoples R China."

来源：PHYSICS IN MEDICINE AND BIOLOGY

ESI学科分类：MOLECULAR BIOLOGY & GENETICS

WOS号：WOS:001196321000001

JCR分区：Q2

影响因子：3.5

年份：2024

卷号：69

期号：8

开始页：　

结束页：　

文献类型：Article

关键词：adversarial learning; difficult supervision; cascade; tumor segmentation

摘要："Objective. Recently, deep learning techniques have found extensive application in accurate and automated segmentation of tumor regions. However, owing to the variety of tumor shapes, complex types, and unpredictability of spatial distribution, tumor segmentation still faces major challenges. Taking cues from the deep supervision and adversarial learning, we have devised a cascade-based methodology incorporating multi-scale adversarial learning and difficult-region supervision learning in this study to tackle these challenges. Approach. Overall, the method adheres to a coarse-to-fine strategy, first roughly locating the target region, and then refining the target object with multi-stage cascaded binary segmentation which converts complex multi-class segmentation problems into multiple simpler binary segmentation problems. In addition, a multi-scale adversarial learning difficult supervised UNet (MSALDS-UNet) is proposed as our model for fine-segmentation, which applies multiple discriminators along the decoding path of the segmentation network to implement multi-scale adversarial learning, thereby enhancing the accuracy of network segmentation. Meanwhile, in MSALDS-UNet, we introduce a difficult region supervision loss to effectively utilize structural information for segmenting difficult-to-distinguish areas, such as blurry boundary areas. Main results. A thorough validation of three independent public databases (KiTS21, MSD's Brain and Pancreas datasets) shows that our model achieves satisfactory results for tumor segmentation in terms of key evaluation metrics including dice similarity coefficient, Jaccard similarity coefficient, and HD95. Significance. This paper introduces a cascade approach that combines multi-scale adversarial learning and difficult supervision to achieve precise tumor segmentation. It confirms that the combination can improve the segmentation performance, especially for small objects (our codes are publicly availabled on https://zhengshenhai.github.io/)."

基金机构："National Natural Science Foundation of Chinahttps://doi.org/10.13039/501100001809 [61902046, 61901074, 62076044]; National Natural Science Foundation of China [KJZDK202200606]; Science and Technology Research Program of Chongqing Municipal Education Commission [2022NSCQ-MSX3746, cstc2019jcyj-zdxm0011]; Natural Science Foundation of Chongqing"

基金资助正文："We thank the anonymous reviewers for their careful reading of our manuscript and their many insightful comments and suggestions to improve the quality of this paper. This work was supported in part by the National Natural Science Foundation of China (Nos. 61902046, 61901074 and 62076044) and the Science and Technology Research Program of Chongqing Municipal Education Commission (No. KJZDK202200606) and the Natural Science Foundation of Chongqing (Nos. 2022NSCQ-MSX3746 and cstc2019jcyj-zdxm0011)."