Rxivist logo

Predicting and Visualizing STK11 Mutation in Lung Adenocarcinoma Histopathology Slides Using Deep Learning

By Runyu Hong, Wenke Liu, David Fenyƶ

Posted 23 Feb 2020
bioRxiv DOI: 10.1101/2020.02.20.956557

Studies have shown that STK11 mutation plays a critical role in affecting the lung adenocarci-noma (LUAD) tumor immune environment. By training an Inception-Resnet-v2 deep convolution-al neural network model, we were able to classify STK11-mutated and wild type LUAD tumor histopathology images with a promising accuracy (per slide AUROC=0.795). Dimensional reduc-tion of the activation maps before the output layer of the test set images revealed that fewer im-mune cells were accumulated around cancer cells in STK11-mutation cases. Our study demon-strated that deep convolutional network model can automatically identify STK11 mutations based on histopathology slides and confirmed that the immune cell density was the main feature used by the model to distinguish STK11-mutated cases.

Download data

  • Downloaded 354 times
  • Download rankings, all-time:
    • Site-wide: 106,793
    • In bioinformatics: 8,986
  • Year to date:
    • Site-wide: 25,055
  • Since beginning of last month:
    • Site-wide: 7,593

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide