Submit a comment

Artificial intelligence for automating the measurement of histologic image biomarkers
Toby C. Cornish
Toby C. Cornish
Published April 15, 2021
Citation Information: J Clin Invest. 2021;131(8):e147966. https://doi.org/10.1172/JCI147966.
View: Text | PDF
Commentary Article has an altmetric score of 2

Artificial intelligence for automating the measurement of histologic image biomarkers

Abstract

Artificial intelligence has been applied to histopathology for decades, but the recent increase in interest is attributable to well-publicized successes in the application of deep-learning techniques, such as convolutional neural networks, for image analysis. Recently, generative adversarial networks (GANs) have provided a method for performing image-to-image translation tasks on histopathology images, including image segmentation. In this issue of the JCI, Koyuncu et al. applied GANs to whole-slide images of p16-positive oropharyngeal squamous cell carcinoma (OPSCC) to automate the calculation of a multinucleation index (MuNI) for prognostication in p16-positive OPSCC. Multivariable analysis showed that the MuNI was prognostic for disease-free survival, overall survival, and metastasis-free survival. These results are promising, as they present a prognostic method for p16-positive OPSCC and highlight methods for using deep learning to measure image biomarkers from histopathologic samples in an inherently explainable manner.

Authors

Toby C. Cornish

×

Guidelines

The Editorial Board will only consider comments that are deemed relevant and of interest to readers. The Journal will not post data that have not been subjected to peer review; or a comment that is essentially a reiteration of another comment.

  • Comments appear on the Journal’s website and are linked from the original article’s web page.
  • Authors are notified by email if their comments are posted.
  • The Journal reserves the right to edit comments for length and clarity.
  • No appeals will be considered.
  • Comments are not indexed in PubMed.

Specific requirements

  • Maximum length, 400 words
  • Entered as plain text or HTML
  • Author’s name and email address, to be posted with the comment
  • Declaration of all potential conflicts of interest (even if these are not ultimately posted); see the Journal’s conflict-of-interest policy
  • Comments may not include figures
This field is required
This field is required
This field is required
This field is required
This field is required
This field is required
Rich Text Editor, eletter_body