Deep learning on mammary glands distribution for architectural distortion detection in digital breast tomosynthesis.

Researchers

Journal

Modalities

Models

Abstract

Computer aided detection (CADe) for breast lesion can provide an important reference for radiologists in breast cancer screening. Architectural distortion (AD) is a type of breast lesion that is difficult to detect. A majority of CADe methods focus on detecting the radial pattern, which is a main characteristic of typical ADs. However, a few atypical ADs do not exhibit such a pattern. To improve the performance of CADe for typical and atypical ADs, we proposed a deep-learning-based model that used the mammary glands distribution as prior information to detect ADs in digital breast tomosynthesis (DBT). First, information about gland distributions, including Gabor magnitude, Gabor orientation field, and convergence map, were produced using a bank of Gabor filters and convergence measures. Then, this prior information and original slice were input into a Faster-RCNN detection network to obtain the 2-D candidates for each slice. Finally, a 3-D aggregation scheme was employed to fuse these 2-D candidates as 3-D candidates for each DBT volume. Retrospectively, 64 typical AD volumes, 74 atypical AD volumes, and 127 normal volumes were collected. Six-fold cross validation and mean true positive fraction (MTPF) were used to evaluate the model. Compared to an existing convergence-based model, our proposed model achieved an MTPF of 0.53 ± 0.04, 0.61 ± 0.05, and 0.45 ± 0.04 for all DBT volumes, typical + normal volumes, and atypical + normal volumes, respectively. These results were significantly better than those of 0.36 ± 0.03, 0.46 ± 0.04, and 0.28 ± 0.04 for a convergence-based model (p < 0.01). These results indicate that employing the prior information of glands distribution and a deep learning method can improve the performance of CADe for AD.
© 2020 Institute of Physics and Engineering in Medicine.