Artificial Intelligence in Histologic Diagnosis of Ductal Carcinoma In Situ

Abstract

A systematic review was conducted in line with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses protocol to evaluate the diagnostic accuracy of artificial intelligence (AI) in ductal carcinoma in situ. Four databases were searched for articles up to December 2022: Embase, PubMed, Scopus, and Web of Science. 23 studies were included, and a search of grey literature was not performed. The following parameters were extracted: the accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of each study. Statistical analysis of the included studies revealed that AI-assisted histopathological analysis is of high accuracy (83.78%), sensitivity (83.88%), and specificity (85.49%) and has a high positive predictive value (89.43%). Our results also reported that convolutional neural network (CNN) is the most commonly used mode of machine learning—21 models used only CNN, whereas 2 models used only support vector machines (SVM). On an average, CNN reported slightly higher accuracy and sensitivity (86.71% and 85.22%, respectively) than SVM (accuracy, 85.00%; sensitivity, 70.00%). When the 2 methods were combined, a mean accuracy of 82.52% and a mean sensitivity of 83.00% were achieved. The use of AI as a diagnostic adjunct can markedly improve the accuracy and efficiency of DCIS diagnosis and can, therefore, reduce pathologists’ workload.