SW-Net: A novel few-shot learning approach for disease subtype prediction
作者机构：Faculty of Innovation EngineeringSchool of Computer Science and EngineeringMacao University of Science and TechnologyMacao999078China Tencent Quantum LabShenzhen518000China
出 版 物：《BIOCELL》 (生物细胞（英文）)
年 卷 期：2023年第47卷第3期
页 面：569-579页
核心收录：
学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）]
主 题：Few-shot learning Disease sub-type classification Feature selection Deep learning Meta-learning
摘 要：Few-shot learning is becoming more and more popular in many fields,especially in the computer vision *** inspires us to introduce few-shot learning to the genomic field,which faces a typical few-shot problem because some tasks only have a limited number of samples with *** goal of this study was to investigate the few-shot disease sub-type prediction problem and identify patient subgroups through training on small *** disease subtype classification allows clinicians to efficiently deliver investigations and interventions in clinical *** propose the SW-Net,which simulates the clinical process of extracting the shared knowledge from a range of interrelated tasks and generalizes it to unseen *** model is built upon a simple baseline,and we modified it for genomic *** initialization for the classifier and transductive fine-tuning techniques were applied in our model to improve prediction accuracy,and an Entropy regularization term on the query set was appended to reduce ***,to address the high dimension and high noise issue,we future extended a feature selection module to adaptively select important features and a sample weighting module to prioritize high-confidence *** on simulated data and The Cancer Genome Atlas meta-dataset show that our new baseline model gets higher prediction accuracy compared to other competing algorithms.
维普期刊数据库