摘要
In this paper, we propose a Dual-path Supplemental Information Learning Architecture (DSILA) for predicting breast cancer Ki-67 status based on T2-weighted (T2w) magnetic resonance imaging (MRI). DSILA consists of two components: 1) a transfer network with multi-scale feature selection strategy to obtain generic multi-scale features most relative to target, 2) a supplemental learning network with a large receptive field and channel-level attention to mine scenario-related semantic information. A regulation item - Aspect Overlap Loss (AOL), is further added to force the supplemental learning network to pay more attention to the regions overlooked by the transfer network. The experimental results tested on the collected T2w MRI breast cancer Ki-67 dataset show that DSILA outperforms state-of-the-art techniques among all adopted evaluation metrics, even achieving 0.85 in Area under the Receiver Operating Characteristic Curve (AUC).
学科与关键词
- Preoperative Prediction of Ki-67 Status in Breast Cancer with Multiparametric MRI Using Transfer LearningLiu, Weixiao; Cheng, Yulin; Liu, Zaiyi; Liu, Chunling; Cattell, Renee; Xie, Xinyan; Wang, Yingyi; Yang, Xiaojun; Ye, Weitao; Liang, Cuishan; Li, Jiao; Gao, Ying; Huang, Chuan; Liang, ChanghongACADEMIC RADIOLOGY, 2021, 28(2): E44-E53.被引 18
- Clinical applications of deep learning in breast MRIZhao, Xue; Bai, Jing-Wen; Guo, Qiu; Ren, Ke*; Zhang, Guo-Jun*Biochimica et Biophysica Acta - Reviews on Cancer, 2023, 1878(2): 188864.被引 16
- Deep computational pathology in breast cancerDuggento, Andrea*; Conti, Allegra*; Mauriello, Alessandro; Guerrisi, Maria; Toschi, NicolaSeminars in Cancer Biology, 2021, 72: 226-237.被引 40
