An optimized two-stage cascaded deep neural network for adrenal segmentation on CT images

Segmentation of adrenal glands from CT images is a crucial step in the AI-assisted diagnosis of adrenal gland-related disease. However, highly intrasubject variability in shape and adhesive boundaries with surrounding tissues make accurate segmentation of the adrenal gland a challenging task. In the current study, we proposed a novel two-stage deep neural network for adrenal gland segmentation in an end-to-end fashion. In the first stage, a localization network that aims to determine the candidate volume of the target organ was used in the preprocessing step to reduce class imbalance and computational burden. Then, in the second stage, a Small-organNet model trained with a novel boundary attention focal loss was designed to refine the boundary of the organ within the screened volume. The experimental results show that our proposed cascaded framework outperforms the state-of-the-art deep learning method in segmenting the adrenal gland with respect to accuracy; it requires fewer trainable parameters and imposes a smaller demand on computational resources. •A high performance and low computational demand deep neural network designed for segmentaion of tiny organs from CT.•A novel loss function that focus on boundary was used in model training to solve fuzzy boundaries.•Adrenal dataset with high heterogeniety makes the trained model robust to variations in shape and intensity.