Ultrasound-based deep learning in the establishment of a breast lesion risk stratification system: a multicenter study.
Yang GuWen XuTing LiuXing AnJiawei TianHaitao RanWeidong RenCai ChangJianjun YuanChunsong KangYoubin DengHui WangBaoming LuoShenglan GuoQi ZhouEnsheng XueWeiwei ZhanQing ZhouJie LiPing ZhouMan ChenYing GuWu ChenYuhong ZhangJianchu LiLongfei CongLei ZhuHongyan WangYuxin JiangPublished in: European radiology (2022)
• The DL model can achieve binary categorization for benign and malignant breast lesions and six-way BI-RADS categorizations for categories 2, 3, 4a, 4b, 4c, and 5, simultaneously. • The DL model showed acceptable agreement with radiologists for the classification of breast lesions. • The DL model performed well in distinguishing benign from malignant breast lesions and had promise in helping reduce unnecessary biopsies of BI-RADS 4a lesions.