Can an Artificial Intelligence Decision Aid Decrease False-Positive Breast Biopsies?

Abstract

This study aimed to evaluate the effect of an artificial intelligence (AI) support system on breast ultrasound diagnostic accuracy. In this Health Insurance Portability and Accountability Act–compliant, institutional review board–approved retrospective study, 200 lesions (155 benign, 45 malignant) were randomly selected from consecutive ultrasound-guided biopsies (June 2017–January 2019). Two readers, blinded to clinical history and pathology, evaluated lesions with and without an Food and Drug Administration–approved AI software. Lesion features, Breast Imaging Reporting and Data System (BI-RADS) rating (1–5), reader confidence level (1–5), and AI BI-RADS equivalent (1–5) were recorded. Statistical analysis was performed for diagnostic accuracy, negative predictive value, positive predictive value (PPV), sensitivity, and specificity of reader versus AI BI-RADS. Generalized estimating equation analysis was used for reader versus AI accuracy regarding lesion features and AI impact on low-confidence score lesions. Artificial intelligence effect on false-positive biopsy rate was determined. Statistical tests were conducted at a 2-sided 5% significance level. There was no significant difference in accuracy (73 vs 69.8%), negative predictive value (100% vs 98.5%), PPV (45.5 vs 42.4%), sensitivity (100% vs 96.7%), and specificity (65.2 vs 61.9; P = 0.118–0.409) for AI versus pooled reader assessment. Artificial intelligence was more accurate than readers for irregular shape (74.1% vs 57.4%, P = 0.002) and less accurate for round shape (26.5% vs 50.0%, P = 0.049). Artificial intelligence improved diagnostic accuracy for reader-rated low-confidence lesions with increased PPV (24.7% AI vs 19.3%, P = 0.004) and specificity (57.8% vs 44.6%, P = 0.008). Artificial intelligence decision support aid may help improve sonographic diagnostic accuracy, particularly in cases with low reader confidence, thereby decreasing false-positives.

Ultrasound radiomics in personalized breast management: Current status and future prospects

“…Chen et al (21) established an AI model with 288,767 US examinations in a retrospective study and demonstrated that with the assistance of AI, radiologists reduced the FP rate by 37.3% and unnecessary biopsies by 27.8% without sacrificing sensitivity. And several other studies have also confirmed this finding (33,34). Recent studies have challenged the use of ultrasound radiomics for specific breast lesions that are difficult to diagnose in clinical practice, particularly for BI-RADS 4A lesions.…”

Barriers and facilitators of artificial intelligence conception and implementation for breast imaging diagnosis in clinical practice: a scoping review

“…MRI studies especially lacked data (from 93 [59] to 1715 patients [25] in included studies, with varying types of MR protocols). While US imaging may benefit from larger accessibility, an important discrepancy was observed among studies where the number of patients ranged from 92 to 5151 [54,[60][61][62][63][64][65][66][67]. Variety in the data was also reported as a critical issue since clinical data is often imbalanced due to disease prevalence, data availability, or population characteristics, which remains an unsolved issue still under research in the ML field [16].…”