摘要
目的以YOLOv8框架为基础,引入高效多尺度注意力(EMA)机制,构建子宫解剖结构检测与分割智能模型(IMSU),并评估其性能。方法回顾性收集2021年1月至2022年12月深圳市妇幼保健院共计4326张非妊娠子宫正中矢状切面超声图像,人工标注子宫宫体、宫颈及内膜3个关键解剖结构,建立图像数据库。按8∶1∶1比例划分为训练集(3460张)、验证集(433张)与测试集(424张),引入EMA机制对YOLOv8模型进行改进,构建IMSU。首先训练并验证原始YOLOv8标准模型及基于EMA模块改进的模型(IMSU),随后在测试集上对两种模型对子宫宫体、宫颈及内膜的自动结构检测与分割性能进行评估,评估指标包括精确率、召回率、平均精度(mAP)2个层级指标(mAP@50与mAP@50-95)。结果在3个关键结构自动检测任务中,IMSU的整体平均精确率(0.920 vs 0.905)、召回率(0.939 vs 0.917)及mAP@50(0.952 vs 0.933)均优于YOLOv8;尤其对宫颈的检测mAP@50值由0.858提升至0.919,召回率由0.778提升至0.842。在自动分割任务中,与YOLOv8相比,IMSU整体平均精确率由0.905提升至0.914,召回率由0.915提升至0.933,mAP@50由0.930提升至0.952,mAP@50-95亦从0.661提升至0.677;对宫颈的分割mAP@50-95由0.570提升至0.597。结论融合EMA机制的IMSU显著提升了非妊娠子宫正中矢状切面关键结构的自动检测性能与分割精度,为实现子宫结构的智能量化测量及超声辅助诊断提供了技术支持,具有良好的临床应用前景。
Objective To develop an intelligent model for uterine anatomical structure detection and segmentation(IMSU)by integrating the Efficient Multi-scale Attention(EMA)mechanism into the You Only Look Once version 8(YOLOv8)framework and evaluate its performance.Methods A total of 4326 non-pregnant mid-sagittal uterine ultrasound images were retrospectively collected from Shenzhen Maternity and Child Healthcare Hospital(January 2021-December 2022).Three key anatomical structures(uterine corpus,cervix,and endometrium)were manually annotated to establish an image database.The dataset was divided into training(3460 images),validation(433 images),and test sets(424 images)at an 8∶1∶1 ratio.An IMSU model was constructed by enhancing YOLOv8 with the EMA module.Both the baseline YOLOv8 and IMSU models were trained and validated,followed by performance evaluation on the test set for automated detection and segmentation of uterine structures.Metrics included precision,recall,and mean Average Precision(mAP)at two levels:mAP@50 and mAP@50-95.Results For detection tasks,IMSU outperformed YOLOv8 in overall precision(0.920 vs 0.905),recall(0.939 vs 0.917),and mAP@50(0.952 vs 0.933).Notably,cervical detection mAP@50 improved from 0.858 to 0.919 and recall increased from 0.778 to 0.842.In segmentation tasks,IMSU achieved higher precision(0.914 vs 0.905),recall(0.933 vs 0.915),mAP@50(0.952 vs 0.930),and mAP@50-95(0.677 vs 0.661).Cervical segmentation mAP@50-95 rose from 0.570 to 0.597.Conclusion The EMA-enhanced IMSU significantly improves automated detection and segmentation accuracy for key uterine structures in mid-sagittal ultrasound images,providing technical support for intelligent quantitative uterine measurements and ultrasound-assisted diagnosis with promising clinical applicability.
作者
江瑶
蒋程
余翔
谭莹
温昕
温慧莹
彭桂艳
李胜利
Jiang Yao;Jiang Cheng;Yu Xiang;Tan Ying;Wen Xin;Wen Huiying;Peng Guiyan;Li Shengli(Department of Ultrasonography,Shenzhen Maternal and Child Healthcare Hospital,Women and Children's Medical Center,Southern Medical University,Shenzhen 518028,China;College of Computer Science,Hunan University,Changsha 410082,China)
出处
《中华医学超声杂志(电子版)》
北大核心
2025年第8期703-710,共8页
Chinese Journal of Medical Ultrasound(Electronic Edition)
基金
深圳市自然科学基金基础研究面上项目(JCYJ20240813115114020)。
关键词
子宫
人工智能
深度学习
自动分割
超声成像
Uterus
Artificial intelligence
Deep learning
Automatic segmentation
Ultrasound imaging
