Deep Learning Predicts Biomarker Status and Discovers Related Histomorphology Characteristics for Low-Grade Glioma

• Published in: arXiv.org 2023-10
• Main Authors: Fang, Zijie, Liu, Yihan, Wang, Yifeng, Zhang, Xiangyang, Chen, Yang, Cai, Changjing, Lin, Yiyang, Han, Ying, Wang, Zhi, Zeng, Shan, Shen, Hong, Tan, Jun, Zhang, Yongbing
• Format: Article
• Language: English
• Subjects: Biomarkers; Deep learning; Labels; Performance prediction; Qualitative analysis
• ISSN: 2331-8422

Biomarker detection is an indispensable part in the diagnosis and treatment of low-grade glioma (LGG). However, current LGG biomarker detection methods rely on expensive and complex molecular genetic testing, for which professionals are required to analyze the results, and intra-rater variability is often reported. To overcome these challenges, we propose an interpretable deep learning pipeline, a Multi-Biomarker Histomorphology Discoverer (Multi-Beholder) model based on the multiple instance learning (MIL) framework, to predict the status of five biomarkers in LGG using only hematoxylin and eosin-stained whole slide images and slide-level biomarker status labels. Specifically, by incorporating the one-class classification into the MIL framework, accurate instance pseudo-labeling is realized for instance-level supervision, which greatly complements the slide-level labels and improves the biomarker prediction performance. Multi-Beholder demonstrates superior prediction performance and generalizability for five LGG biomarkers (AUROC=0.6469-0.9735) in two cohorts (n=607) with diverse races and scanning protocols. Moreover, the excellent interpretability of Multi-Beholder allows for discovering the quantitative and qualitative correlations between biomarker status and histomorphology characteristics. Our pipeline not only provides a novel approach for biomarker prediction, enhancing the applicability of molecular treatments for LGG patients but also facilitates the discovery of new mechanisms in molecular functionality and LGG progression.