Rxivist logo

Predicting Endometrial Cancer Subtypes and Molecular Features from Histopathology Images Using Multi-resolution Deep Learning Models

By Runyu Hong, Wenke Liu, Deborah DeLair, Narges Razavian, David Fenyƶ

Posted 26 Feb 2020
bioRxiv DOI: 10.1101/2020.02.25.965038

The determination of endometrial carcinoma histological subtypes, molecular subtypes, and mutation status is a critical diagnostic process that directly affects patients' prognosis and treatment options. Compared to the histopathological approach, however, the availability of molecular subtyping is limited as it can only be accurately obtained by genomic sequencing, which may be cost prohibitive. Here, we implemented a customized multi-resolution deep convolutional neural network, Panoptes, that predicts not only the histological subtypes, but also molecular subtypes and 18 common gene mutations based on digitized H&E stained pathological images. The model achieved high accuracy and generalized well on independent datasets. Our results suggest that Panoptes has potential clinical application of helping pathologists determine molecular subtypes and mutations of endometrial carcinoma without sequencing.

Download data

  • Downloaded 1,275 times
  • Download rankings, all-time:
    • Site-wide: 20,594
    • In bioinformatics: 2,290
  • Year to date:
    • Site-wide: 54,734
  • Since beginning of last month:
    • Site-wide: 75,549

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide