Diagnostic Performance of Artificial Intelligence-Based Computer-Aided Diagnosis for Breast Microcalcification on Mammography.

Yoon Ah Do,Bohyoung Kim,Mijung Jang,Sung Ui Shin,Sun Mi Kim,Bo La Yun

doi:10.3390/diagnostics11081409

Abstract

The present study evaluated the diagnostic performance of artificial intelligence-based computer-aided diagnosis (AI-CAD) compared to that of dedicated breast radiologists in characterizing suspicious microcalcification on mammography. We retrospectively analyzed 435 unilateral mammographies from 420 patients (286 benign; 149 malignant) undergoing biopsy for suspicious microcalcification from June 2003 to November 2019. Commercial AI-CAD was applied to the mammography images, and malignancy scores were calculated. Diagnostic performance was compared between radiologists and AI-CAD using the area under the receiving operator characteristics curve (AUC). The AUCs of radiologists and AI-CAD were not significantly different (0.722 vs. 0.745, p = 0.393). The AUCs of the adjusted category were 0.726, 0.744, and 0.756 with cutoffs of 2%, 10%, and 38.03% for AI-CAD, respectively, which were all significantly higher than those for radiologists alone (all p < 0.05). None of the 27 cases downgraded to category 3 with a cutoff of 2% were confirmed as malignant on pathological analysis, suggesting that unnecessary biopsies could be avoided. Our findings suggest that the diagnostic performance of AI-CAD in characterizing suspicious microcalcification on mammography was similar to that of the radiologists, indicating that it may aid in making clinical decisions regarding the treatment of breast microcalcification.

Highlights

Screening mammography is the most common and most effective method for detecting early breast cancer, with a demonstrated effect in reducing breast cancer mortality [1,2]
Our findings indicated that artificial intelligence-based computer-aided diagnosis (AI-CAD) and radiologists exhibited similar diagnostic performance in characterizing suspicious microcalcifications on mammography
AI-CAD may aid in making clinical decisions for treating breast microcalcifications

Summary

Introduction

Screening mammography is the most common and most effective method for detecting early breast cancer, with a demonstrated effect in reducing breast cancer mortality [1,2]. After the United States Food and Drug Administration approved the computer-aided detection system for mammography in 1998, it has been improved and has helped radiologists detect subtle features of malignancy by reducing the perception error [7]. It has increased the sensitivity of mammography by aiding in the detection of suspicious findings, such as microcalcifications, asymmetries, and masses regardless of breast density which is one of the important causes of false-negative cases [8,9,10]. Previous computeraided detection systems were able to detect microcalcifications on mammography [11,12]

Methods

Results

Discussion

Conclusion