AI Could Improve Diagnostic Accuracy of Breast DCE-MRI

Early detection is key to improving breast cancer outcomes. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) has a high sensitivity in detecting breast cancer and is sometimes used for women at higher risk of breast cancer but often leads to unnecessary biopsies and patient workup. Now, a new study has demonstrated that a deep learning (DL) system could improve the diagnostic accuracy of DCE-MRI of breast tissue for detecting breast cancer,

For the study, researchers at the New York University Grossman School of Medicine (New York City, NY, USA) used a DL system to improve the overall accuracy of breast cancer diagnosis and personalize management of patients undergoing DCE-MRI. On the internal test set (n = 3936 exams), the system achieved an area under the receiver operating characteristic curve (AUROC) of 0.92 (95% CI: 0.92 to 0.93). In a retrospective reader study, there was no statistically significant difference (P = 0.19) between five board-certified breast radiologists and the DL system (mean ΔAUROC, +0.04 in favor of the DL system). Radiologists’ performance improved when their predictions were averaged with DL’s predictions [mean ΔAUPRC (area under the precision-recall curve), +0.07].

Additionally, the researchers demonstrated the generalizability of the DL system using multiple datasets from Poland and the U.S. An additional reader study on a Polish dataset showed that the DL system was as robust to distribution shift as radiologists. In subgroup analysis, the researchers observed consistent results across different cancer subtypes and patient demographics. Using decision curve analysis, the researchers showed that the DL system can reduce unnecessary biopsies in the range of clinically relevant risk thresholds. This would lead to avoiding biopsies yielding benign results in up to 20% of all patients with BI-RADS category 4 lesions. Last, the researchers performed an error analysis, investigating situations where DL predictions were mostly incorrect. This exploratory work creates a foundation for deployment and prospective analysis of DL-based models for breast MRI.

Related Links:
New York University Grossman School of Medicine