Predicting pathological complete response based on weakly and semi-supervised joint learning in breast cancer multi-parametric MRI
Release Time:2024-12-24 Hits:
Date of Publication: 2024-12-20
Journal: Biomedical Signal Processing and Control
Volume: 93
ISSN: 1746-8094
Key Words: Article; Attention mechanisms; breast cancer; Breast Cancer; cancer patient; cancer staging; Chemotherapy; cohort analysis; Complete response; controlled study; cross validation; deep learning; diffusion weighted imaging; Diseases; dynamic contrast-enhanced magnetic resonance imaging; epidermal growth factor receptor 2; estrogen receptor; feature selection; Forecasting; human; image segmentation; Joint learning; Ki 67 antigen; Learning systems; major clinical study; Medical imaging; MR-images; multimodal imaging; multiparametric magnetic resonance imaging; Neoadjuvant chemotherapies; neoadjuvant chemotherapy; nuclear magnetic resonance imaging; pathological complete response; Pathological complete response; prediction; progesterone receptor; radiochemistry; radiomics; retrospective study; Semi-supervised; Semi-supervised learning; semi supervised machine learning; Supervised learning; support vector machine; T1 weighted imaging; T2 weighted imaging; treatment response; Tumors; Weakly supervised learning
Prev One:Comparative analysis of color emotional perception in art and non-art university students: hue, saturation, and brightness effects in the Munsell color system
Next One:Double-Tier Attention Based Multi-label Learning Network for Predicting Biomarkers from Whole Slide Images of Breast Cancer