Multi‐domain features for reducing false positives in automated detection of clustered microcalcifications in digital breast tomosynthesis

Purpose In digital breast tomosynthesis ( DBT ) imaging, a microcalcification ( MC ) cluster may span across different slices and blurring exists in the out‐of‐focus slices. We developed a radiomics approach to extract features from focus slice and combine multiple spatial domains to reduce false positives ( FP s) in an automated pipeline of detecting MC clusters. Methods We performed a retrospective study on a cohort of 290 Chinese women patients with a total of 580 DBT volumes. We developed an automated MC detection pipeline that consists of two stages: an initial detection to identify a set of MC candidates that may include many FP s, followed by a radiomics‐based classification model to identify and reduce the FP s. We extract both two‐dimensional (2D) and three‐dimensional (3D) radiomics features from multiple spatial domains, including a focus slice, projection image, and tomographic volume. A linear discriminant classifier was used coupled with a sequential forward feature selection procedure. The free‐response operating characteristics ( FROC ) curve and partial area under the FROC curve ( pAUC ) in the FP rate range of 0 to 2 per DBT volume were used to evaluate the model's performance. Results At a sensitivity of 90%, the FP rate was reduced from 1.3 to 0.2 per DBT volume after applying the multi‐domain‐based classification on the initial detections. The multi‐domain yielded a significantly higher pAUC compared to the initial detection (increase of pAUC  = 0.2278, P  < 0.0001), focus slice (increase of pAUC  = 0.0345, P  = 0.0152), project image (increase of pAUC  = 0.1043, P  < 0.0001), and tomographic volume (increase of pAUC  = 0.0791, P  = 0.0032). Conclusion The radiomic features extracted from the three domains may provide complementary information and their integration can significantly reduce FP s in automated detection of MC s in DBT volumes on a large Chinese women population.