Adding Artificial Intelligence (AI) System to Breast Ultrasound Can Reduce Unnecessary Biopsies, Finds Study

In the study, conventional ultrasound and AI analyses were prospectively performed on 173 suspicious breast lesions before ultrasound-guided core needle biopsy or vacuum-assisted excision. Conventional ultrasound images were retrospectively reviewed according to the BI-RADS 2013 lexicon and categories. Two downgrading stratifications based on AI assessments were manually used to downgrade the BI-RADS category 4A lesions to category 3. Stratification A was used to downgrade if the assessments of both orthogonal sections of a lesion from AI were possibly benign. Stratification B was used to downgrade if the assessment of any of the orthogonal sections was possibly benign. The effects of AI-based diagnosis on lesions to reduce unnecessary biopsy were analyzed using histopathological results as reference standards.

The researchers found that 43 lesions diagnosed as BI-RADS category 4A by conventional ultrasound received AI-based hypothetical downgrading. While downgrading with stratification A, 14 biopsies were correctly avoided. The biopsy rate for BI-RADS category 4A lesions decreased from 100% to 67.4% (P <  0.001). While downgrading with stratification B, 27 biopsies could be avoided with two malignancies missed, and the biopsy rate decreased to 37.2% (P <  0.05, compared with conventional ultrasound and stratification A). Based on their findings, the researchers concluded that adding an AI system to breast ultrasound could reduce unnecessary lesion biopsies and have recommended downgrading stratification A for its lower misdiagnosis rate.

Related Links:
Peking University Third Hospital