Do, Yoon Ah; Jang, Mijung; Yun, Bo La; Shin, Sung Ui; Kim, Bohyoung; Kim, Sun Mi
Diagnostics (Basel, Switzerland)
2021Aug ; 11 ( 8 ) :.
PMID : 34441343
ÀúÀÚ »ó¼¼Á¤º¸
Do, Yoon Ah - Department of Radiology, Seoul National University Bundang Hospital, Seoul National University College of Medicine, Seongnam 13620, Korea.
Jang, Mijung - Department of Radiology, Seoul National University Bundang Hospital, Seoul National
Yun, Bo La - Department of Radiology, Seoul National University Bundang Hospital, Seoul National
Shin, Sung Ui - Department of Radiology, Seoul National University Bundang Hospital, Seoul National
Kim, Bohyoung - Division of Biomedical Engineering, Hankuk University of Foreign Studies, Seoul
Kim, Sun Mi - Department of Radiology, Seoul National University Bundang Hospital, Seoul National
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.
keyword
artificial intelligence; breast cancer; computer-aided diagnosis; diagnosis; mammography; radiology
¸µÅ©