Artificial Intelligence Improves the Accuracy in Histologic Classification of Breast Lesions

Abstract

Objectives This study evaluated the usefulness of artificial intelligence (AI) algorithms as tools in improving the accuracy of histologic classification of breast tissue. Methods Overall, 100 microscopic photographs (test A) and 152 regions of interest in whole-slide images (test B) of breast tissue were classified into 4 classes: normal, benign, carcinoma in situ (CIS), and invasive carcinoma. The accuracy of 4 pathologists and 3 pathology residents were evaluated without and with the assistance of algorithms. Results In test A, algorithm A had accuracy of 0.87, with the lowest accuracy in the benign class (0.72). The observers had average accuracy of 0.80, and most clinically relevant discordances occurred in distinguishing benign from CIS (7.1% of classifications). With the assistance of algorithm A, the observers significantly increased their average accuracy to 0.88. In test B, algorithm B had accuracy of 0.49, with the lowest accuracy in the CIS class (0.06). The observers had average accuracy of 0.86, and most clinically relevant discordances occurred in distinguishing benign from CIS (6.3% of classifications). With the assistance of algorithm B, the observers maintained their average accuracy. Conclusions AI tools can increase the classification accuracy of pathologists in the setting of breast lesions.

DPA–ESDIP–JSDP Task Force for Worldwide Adoption of Digital Pathology

“…Computational pathology likely represents the next big revolution in Pathology after immunohistochemistry and molecular pathology. [ 14 ] AI-based algorithms are being developed to not only provide computer-assisted diagnosis,[ 15 ] but also to augment the practice of pathology by permitting predictions and prognosis to be made directly from H&E pathology images. [ 16 ] The potential for AI to be used in discovery to widen our knowledge about human diseases may challenge the way pathologists practice by altering how diseases are classified and also generating new biomarkers of diseases.…”

HEROHE Challenge: Predicting HER2 Status in Breast Cancer from Hematoxylin–Eosin Whole-Slide Imaging

“…CAD systems comprise image analysis and machine learning methodologies developed to assist physicians during diagnosis. Their use can not only speed up the diagnostic process, but also increase the accuracy of diagnosis [ 14 , 15 ].…”

A Machine Learning Decision Support System (DSS) for Neuroendocrine Tumor Patients Treated with Somatostatin Analog (SSA) Therapy

“…Several studies, for example, have attempted to use deep learning (DL) to help identify dysplasia and early esophageal cancer [ 37 ] while different AI models have been developed to evaluate different aspects of gastric cancer such as the diagnosis or prognosis [ 38 ]. In addition, DL models have been used in breast cancer to identify potential diagnostic biomarkers [ 39 ] and to improve the accuracy in the histologic classification [ 40 ] or diagnosis [ 41 ].…”