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

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 (κ = 0.471). Agreement was good (κ = 0.681), moderate (κ = 0.442), and fair (κ = 0.368) for grades 1, 3, and 2, respectively. Observer pair concordance for AI and individual pathologists ranged from fair to good (κ = 0.313–0.606). Perfect agreement was observed in 25 cases (27.4%). Interobserver agreement for the individual components was best for TF (κ = 0.471 each) followed by NP (κ = 0.342) and was worst for MC (κ = 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 multi-institutional group of pathologists using virtual microscopy to a newly developed WSI AI methodology. Using explainable methods, AI demonstrated similar concordance to pathologists alone.

Impact of Tumor‐Infiltrating Lymphocytes on Disease Progression in Human Papillomavirus‐Related Oropharyngeal Carcinoma

“…The addition of immunohistochemistry staining to determine separate populations of CD4+, CD8+, CD56+, and Treg lymphocytes will greatly improve our understanding of the tumor microenvironment and may add specificity to the prognostic capability of TILs, as these different populations of lymphocytes have differential effects on prognosis 4,17,19 . The use of artificial intelligence in pathologic grading to determine tumor prognosis has shown early promise in urologic malignancies 27 and breast carcinoma 28 . Work on breast cancer has also demonstrated that from a pathologic perspective, the incorporation of TILs as a clinical biomarker is a definite possibility 29 —the use of TILs in the prognostic stratification of HER2‐positive breast cancer is now strongly recommended for standard clinical practice 30 …”

“…4,17,19 The use of artificial intelligence in pathologic grading to determine tumor prognosis has shown early promise in urologic malignancies 27 and breast carcinoma. 28 Work on breast cancer has also demonstrated that from a pathologic perspective, the incorporation of TILs as a clinical biomarker is a definite possibility 29 -the use of TILs in the prognostic stratification of HER2-positive breast cancer is now strongly recommended for standard clinical practice. 30…”

Automatic breast carcinoma detection in histopathological micrographs based on Single Shot Multibox Detector

“… 51 Very recently, Mantrala et al investigated the concordance rate in breast carcinoma grading as determined by the Nottingham Grading System between AI and pathologists using WSI. 27 However, the impact of assistance by AI in diagnosing various breast lesions on clinical utility has not been fully investigated. The present study revealed that medical students upregulated accuracy scores when using the assistance of the model and some students achieved the same or higher accuracy scores than pathologists, although the SSD model and medical students showed lower diagnostic accuracies than pathologists.…”

“…The technology has been developed to digitize an entire glass slide (Whole slide imaging; WSI), 25 and various AIs to classify WSI have been reported. 19 , 26 , 27 , 28 WSI gives various advantages, such as the automated WSI scanner that automatically scans. 29 , 30 However, introducing WSI scanners and digital pathology system and managing huge amounts of digital data need a lot of money.…”

Accuracy and Utility of Preoperative Ultrasound-Guided Axillary Lymph Node Biopsy for Invasive Breast Cancer: A Systematic Review and Meta-Analysis

“…The grading and staging of breast cancer has a significant impact on prognosis [ 22 , 23 ]. The WHO takes the Nottingham grading system as the standard histological grading system for invasive breast cancer [ 24 , 25 ]. The evaluation indicators are the proportion of glandular duct formation, nuclear pleomorphism, and mitotic image count [ 26 ].…”