Concordance in Breast Cancer Grading by Artificial Intelligence on Whole Slide Images Compares With a Multi-Institutional Cohort of Breast Pathologists

Siddhartha Mantrala, Paula S. Ginter, Aditya Mitkari, Sripad Joshi, Harish Prabhala, Vikas Ramachandra, Lata Kini, Romana Idress, Timothy M. D'Alfonso, Susan Fineberg, Shabnam Jaffer, Abida K. Sattar, Anees B. Chagpar, Parker Wilson, Kamaljeet Singh, Malini Harigopal, Dinesh Koka

Research output: Contribution to journalArticlepeer-review

11 Citations (Scopus)

Abstract

Context.-Breast carcinoma grade, as determined by the Nottingham Grading System (NGS), is an important criterion for determining prognosis. The NGS is based on 3 parameters: tubule formation (TF), nuclear pleomorphism (NP), and mitotic count (MC). The advent of digital pathology and artificial intelligence (AI) have increased interest in virtual microscopy using digital whole slide imaging (WSI) more broadly. Objective.-To compare concordance in breast carcinoma grading between AI and a multi-institutional group of breast pathologists using digital WSI. Design.-We have developed an automated NGS framework using deep learning. Six pathologists and AI independently reviewed a digitally scanned slide from 137 invasive carcinomas and assigned a grade based on scoring of the TF, NP, and MC. Results.-Interobserver agreement for the pathologists and AI for overall grade was moderate (j = 0.471). Agreement was good (j = 0.681), moderate (j = 0.442), and fair (j = 0.368) for grades 1, 3, and 2, respectively. Observer pair concordance for AI and individual pathologists ranged from fair to good (j = 0.313-0.606). Perfect agreement was observed in 25 cases (27.4%). Interobserver agreement for the individual components was best for TF (j = 0.471 each) followed by NP (j = 0.342) and was worst for MC (j = 0.233). There were no observed differences in concordance amongst pathologists alone versus pathologists AI. Conclusions.-Ours is the first study comparing concordance in breast carcinoma grading between a multiinstitutional group of pathologists using virtual microscopy to a newly developed WSI AI methodology. Using explainable methods, AI demonstrated similar concordance to pathologists alone.

Original languageEnglish
Pages (from-to)1369-1377
Number of pages9
JournalArchives of Pathology and Laboratory Medicine
Volume146
Issue number11
DOIs
Publication statusPublished - Nov 2022

Fingerprint

Dive into the research topics of 'Concordance in Breast Cancer Grading by Artificial Intelligence on Whole Slide Images Compares With a Multi-Institutional Cohort of Breast Pathologists'. Together they form a unique fingerprint.

Cite this