Traditional radiation omics models,including radiomics,dosiomics,and contouromics,typically adopt fea-ture splicing,which tends to ignore the specific statistical attributes of different omics and therefore leads to overfitting.A multi-omics collaborative learning(MOCL)algorithm focused on consistency constraints and adaptive weights was proposed in the study to address this problem.The MOCL algorithm employs consistency constraints to explore comple-mentary patterns among heterogeneous omics features and adaptively learns their weights using Shannon entropy while avoiding overfitting through compactness mapping.An experiment was conducted on the clinical imaging data of 311 patients with nasopharyngeal carcinoma using MOCL.The experimental result is compared with three traditional ma-chine learning algorithms and two multiperspective algorithms.The results demonstrate that MOCL has certain advant-ages in collaborative learning of multi-omics and can provide a valuable prediction basis for adaptive radiotherapy quali-fication in the case of nasopharyngeal carcinoma.
关键词
数据融合/机器学习/特征提取/特征选择/预测/图像分析/自适应算法/鼻咽癌/多组学
Key words
data fusion/machine learning/feature extraction/feature selection/forecasting/image analysis/adaptive al-gorithms/nasopharyngeal carcinoma/multi-omic
维普
万方数据