摘要
本研究回顾性分析了198例女性患者的乳腺动态增强磁共振成像(DCE-MRI)图像序列,年龄21~79(45.5±13.7)岁。以病理检查为金标准,采用深度学习方法建立CBAM-ResNet自动分类模型,统计图像级别的分类结果,同时结合集成学习思想得到患者个体的分类结果。基于残差网络的CBAM-ResNet分类模型在单张图像层面对乳腺肿瘤的分类准确率达到82.69%,灵敏度为85.67%。采用投票机制后,在患者层面的分类准确率为88.24%,灵敏度为87.50%。试验结果表明该分类算法具有较高的诊断准确率。
This retrospective analysis was conducted on clinical obtained DCE-MR images of 198 patients,age from 21 to 79 years(45.5±13.7).The CBAM-ResNet model was developed to perform the classification automatically at the image-level based on deep learning method using the pathological examination as the reference standard,then the classification result of each individual patient was obtained by ensemble learning.The proposed method can have an accuracy of 82.69%for correctly distinguishing between benign and malignant breast tumors at the slice-level based on CBAM-ResNet model and with a sensitivity of 85.67%..After the voting mechanism is applied,the classification accuracy can reach up to 88.24%at the patient-level with a sensitivity of 87.50%.Our experimental results demonstrated the proposed approach have a high classification accuracy.
作者
陈兴
刘璟
李鹏
王金铭
赵凌霄
韩小伟
陈悦
于洪伟
马国林
Chen Xing;Liu Jing;Li Peng;Wang Jinming;Zhao Lingxiao;Han Xiaowei;Chen Yue;Yu Hongwei;Ma Guolin(School of Biomedical Engineering,University of Science and Technology of China,Hefei 230000,China;Department of Radiology,China-Japan Friendship Hospital,Beijing 100029,China;Suzhou Institute of Biomedical Engineering and Technology,Chinese Academy of Science,Suzhou 215000,China)
出处
《中华医学杂志》
CAS
CSCD
北大核心
2021年第37期3029-3032,共4页
National Medical Journal of China
基金
江苏省级重点研发计划项目(BE2019710)
苏州市科技计划项目(SYS2019008)
常州市科技计划项目(CE20195001)。