Multi-Beholder: Biomarker Prediction for Low-Grade Glioma with Multiple Instance Learning and One-Class Classification
多视角:利用多实例学习和一类分类进行低级别胶质瘤的生物标志物预测
机构 * Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院,清华大学) ; Department of Oncology, Xiangya Hospital, Central South University(湘雅医院肿瘤科,中南大学) ; School of Science, Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳)科学学院) ; Department of Neurosurgery, Xiangya Hospital, Central South University(湘雅医院神经外科,中南大学) ; School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳)计算机科学与技术学院)
AI总结 本文提出Multi-Beholder方法,通过全切片图像预测低级别胶质瘤的五个生物标志物状态,利用多实例学习和一类分类提高预测性能,并在两个不同队列中验证了其有效性。
Comments 14 pages, 5 figures