Region-based weighting-and-enhancement network with adaptive class weighting loss for postoperative inguinal hernia prediction

doi:10.1016/j.engappai.2025.112451

	Region-based weighting-and-enhancement network with adaptive class weighting loss for postoperative inguinal hernia prediction
	Zhang, Jiawei 1; Wu, Lisheng 2; Fang, Qiang 1; Yu, Weidong 3; Hua, Zhengyu 1; Zhang, Fengyun 4; Yang, Cheng 3; Zhang, Xiaoqing 1,5,6
	2025-12-22
发表期刊	ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
ISSN	0952-1976
卷号	162 页码:13
摘要	Postoperative inguinal hernia (PIH) is a common complication after radical prostatectomy, subsequently leading to multiple potential risks (e.g., cardiovascular and cerebrovascular accidents) and increased surgical costs due to re-surgical reparation. Magnetic resonance imaging (MRI) examination is a widely used procedure before radical prostatectomy, which can investigate the muscle structures of the abdominal wall (MSAW). Recently, clinical studies have indicated that clinical parameters (e.g., thickness and width of the external oblique muscle) of MSAW are strongly related to PIH. However, automated MRI-based PIH prediction based on deep neural networks has not been studied previously. Motivated by these observations, we propose a novel region-based weighting-and-enhancement network to predict PIH before radical prostatectomy based on MRI images automatically. Specifically, we employ the well-designed Region Weighting-and-Enhancement module to capture informative context representations through region weighting and regional context enhancement, by fully leveraging the potential of clinical MSAW priori. Additionally, this paper designs an effective adaptive class weighting loss to emphasize or suppress the samples with varying levels of significance to further boost the PIH prediction performance. The extensive experiments on a clinical MRI-PIH dataset and one publicly available MRI dataset manifest the superiority of our proposed methods over state-of-the-art deep neural networks and advanced loss methods.
关键词	Postoperative inguinal hernia prediction Magnetic resonance imaging Region-based weighting-and-enhancement network Adaptive class weighting loss
DOI	10.1016/j.engappai.2025.112451
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[82573191] ; Open Fund of Key Laboratory of Anti-inflammatory and Immune Medicine[KFJJ-2023-10] ; Ministry of Education, P.R. China (Anhui Medical University) ; Natural Science Foundation of Anhui Medical University[2022xkj146] ; Higher education quality project of Anhui Province[2023jyxm1095]
WOS研究方向	Automation & Control Systems ; Computer Science ; Engineering
WOS类目	Automation & Control Systems ; Computer Science, Artificial Intelligence ; Engineering, Multidisciplinary ; Engineering, Electrical & Electronic
WOS记录号	WOS:001589250000021
出版者	PERGAMON-ELSEVIER SCIENCE LTD
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/41671
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Yang, Cheng; Zhang, Xiaoqing
作者单位	1.Anhui Med Univ, Dept Gen Surg, Affiliated Hosp 1, Hefei, Anhui, Peoples R China 2.Univ Sci & Technol China, affiliated Hosp USTC 1, Dept Hernia & Bariatr Surg, Hefei, Anhui, Peoples R China 3.Anhui Med Univ, Dept Urol, Affiliated Hosp 1, Hefei, Anhui, Peoples R China 4.Southwest Univ, Coll Artificial Intelligence, Chongqing, Peoples R China 5.Chinese Acad Sci, Shenzhen Inst Adv Technol, Ctr High Performance Comp, Shenzhen, Peoples R China 6.Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen Key Lab Intelligent Bioinformat, Shenzhen, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Jiawei,Wu, Lisheng,Fang, Qiang,et al. Region-based weighting-and-enhancement network with adaptive class weighting loss for postoperative inguinal hernia prediction[J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE,2025,162:13.
APA	Zhang, Jiawei.,Wu, Lisheng.,Fang, Qiang.,Yu, Weidong.,Hua, Zhengyu.,...&Zhang, Xiaoqing.(2025).Region-based weighting-and-enhancement network with adaptive class weighting loss for postoperative inguinal hernia prediction.ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE,162,13.
MLA	Zhang, Jiawei,et al."Region-based weighting-and-enhancement network with adaptive class weighting loss for postoperative inguinal hernia prediction".ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 162(2025):13.