Artificial Intelligence-Informed Handheld Breast Ultrasound for Screening: A Systematic Review of Diagnostic Test Accuracy

TL;DR

This systematic review evaluates the current state of AI-enabled handheld breast ultrasound for cancer screening, highlighting promising results but emphasizing the need for more robust validation to ensure effectiveness in resource-limited settings.

Contribution

The review synthesizes recent studies on AI applications in handheld breast ultrasound, categorizing tasks and assessing study quality to identify gaps and future directions.

Findings

AI shows high performance in detection, segmentation, and classification tasks.

Most studies have high or unclear risk of bias, indicating need for better validation.

Limited prospective testing reduces confidence in clinical applicability.

Abstract

Background. Breast cancer screening programs using mammography have led to significant mortality reduction in high-income countries. However, many low- and middle-income countries lack resources for mammographic screening. Handheld breast ultrasound (BUS) is a low-cost alternative but requires substantial training. Artificial intelligence (AI) enabled BUS may aid in both the detection (perception) and classification (interpretation) of breast cancer. Materials and Methods. This review (CRD42023493053) is reported in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analysis) and SWiM (Synthesis Without Meta-analysis) guidelines. PubMed and Google Scholar were searched from January 1, 2016 to December 12, 2023. A meta-analysis was not attempted. Studies are grouped according to their AI task type, application time, and AI task. Study quality is assessed using the QUality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool. Results. Of 763 candidate studies, 314 total full texts were reviewed. 34 studies are included. The AI tasks of included studies are as follows: 1 frame selection, 6 detection, 11 segmentation, and 16 classification. In total, 5.7 million BUS images from over 185,000 patients were used for AI training or validation. A single study included a prospective testing set. 79% of studies were at high or unclear risk of bias. Conclusion. There has been encouraging development of AI for BUS. Despite studies demonstrating high performance across all identified tasks, the evidence supporting AI-enhanced BUS generally lacks robustness. High-quality model validation will be key to realizing the potential for AI-enhanced BUS in increasing access to screening in resource-limited environments.