Searching Images for Consensus: Can AI Remove Observer Variability in Pathology?

Hamid R Tizhoosh; Phedias Diamandis; Clinton J V Campbell; Amir Safarpoor; Shivam Kalra; Danial Maleki; Abtin Riasatian; Morteza Babaie

doi:10.1016/j.ajpath.2021.01.015

Searching Images for Consensus: Can AI Remove Observer Variability in Pathology?

Am J Pathol. 2021 Oct;191(10):1702-1708. doi: 10.1016/j.ajpath.2021.01.015. Epub 2021 Feb 24.

Authors

Hamid R Tizhoosh¹, Phedias Diamandis², Clinton J V Campbell³, Amir Safarpoor⁴, Shivam Kalra⁴, Danial Maleki⁴, Abtin Riasatian⁴, Morteza Babaie⁴

Affiliations

¹ Kimia Laboratory, University of Waterloo, Waterloo, Canada. Electronic address: [email protected].
² Department of Laboratory Medicine and Pathobiology, University of Toronto, Toronto, Canada.
³ Department of Pathology and Molecular Medicine, Faculty of Health Sciences, McMaster University, Hamilton, Ontario, Canada.
⁴ Kimia Laboratory, University of Waterloo, Waterloo, Canada.

PMID: 33636179
DOI: 10.1016/j.ajpath.2021.01.015

Abstract

One of the major obstacles in reaching diagnostic consensus is observer variability. With the recent success of artificial intelligence, particularly the deep networks, the question emerges as to whether the fundamental challenge of diagnostic imaging can now be resolved. This article briefly reviews the problem and how eventually both supervised and unsupervised AI technologies could help to overcome it.

Publication types

Review

MeSH terms

Artificial Intelligence*
Humans
Image Processing, Computer-Assisted*
Natural Language Processing
Neural Networks, Computer
Observer Variation*
Pathology*