Performance of Automated Classification of Diagnostic Entities in Dermatopathology Validated on Multisite Data Representing the Real-World Variability of Pathology Workload.

Abstract

CONTEXT.— More people receive a diagnosis of skin cancer each year in the United States than all other cancers combined. Many patients around the globe do not have access to the highly trained dermatopathologists, whereas some biopsy diagnoses of patients who do have access result in disagreements between such specialists. Mechanomind has developed software based on a deep-learning algorithm to classify 40 different diagnostic dermatopathology entities to improve diagnostic accuracy and to enable improvements in turnaround times and effort allocation. OBJECTIVE.— To assess the value of machine learning for microscopic tissue evaluation in dermatopathology. DESIGN.— A retrospective study comparing diagnoses of hematoxylin and eosin-stained glass slides rendered by 2 senior board-certified pathologists not involved in algorithm creation with the machine learning algorithm's classification was conducted. A total of 300 glass slides (1 slide per patient's case) from 4 hospitals in the United States and Africa with common variations in tissue preparation, staining, and scanning methods were included in the study. RESULTS.— The automated algorithm demonstrated sensitivity of 89 of 91 (97.8%), 107 of 107 (100%), and 101 of 102 (99%), as well as specificity of 204 of 209 (97.6%), 189 of 193 (97.9%), and 198 of 198 (100%) while identifying melanoma, nevi, and basal cell carcinoma in whole slide images, respectively. CONCLUSIONS.— Appropriately trained deep learning image analysis algorithms demonstrate high specificity and high sensitivity sufficient for use in screening, quality assurance, and workload distribution in anatomic pathology.