Self-supervised attention-based deep learning for pan-cancer mutation prediction from histopathology

作者：O. Saldanha, C. Loeffler, J. Niehues, Marko van Treeck, T. Seraphin, K. Hewitt, Didem Cifci, G. Veldhuizen, S. Ramesh, Alexander T. Pearson, Jakob Nikolas Kather · 发表于：npj Precision Oncology · 年份：2023 · DOI：10.1038/s41698-023-00365-0 · 被引用次数：88 · 研究领域：Medicine

The histopathological phenotype of tumors reflects the underlying genetic makeup. Deep learning can predict genetic alterations from pathology slides, but it is unclear how well these predictions generalize to external datasets. We performed a systematic study on Deep-Learning-based prediction of genetic alterations from histology, using two large datasets of multiple tumor types. We show that an analysis pipeline that integrates self-supervised feature extraction and attention-based multiple instance learning achieves a robust predictability and generalizability.