Deep Mouse: An End-to-end Auto-context Refinement Framework for Brain Ventricle and Body Segmentation in Embryonic Mice Ultrasound Volumes
This work addresses the time-consuming and expertise-intensive task of segmenting brain ventricles and body in embryonic mice ultrasound images for researchers in developmental biology or medical imaging.
The paper tackles the problem of manual segmentation of brain ventricles and body in embryonic mice ultrasound volumes, proposing an end-to-end auto-context refinement framework that improves Dice Similarity Coefficient from 0.818 to 0.906 for brain ventricles and 0.919 to 0.934 for the body, while reducing inference time from 102.36 to 0.09 seconds per volume.
High-frequency ultrasound (HFU) is well suited for imaging embryonic mice due to its noninvasive and real-time characteristics. However, manual segmentation of the brain ventricles (BVs) and body requires substantial time and expertise. This work proposes a novel deep learning based end-to-end auto-context refinement framework, consisting of two stages. The first stage produces a low resolution segmentation of the BV and body simultaneously. The resulting probability map for each object (BV or body) is then used to crop a region of interest (ROI) around the target object in both the original image and the probability map to provide context to the refinement segmentation network. Joint training of the two stages provides significant improvement in Dice Similarity Coefficient (DSC) over using only the first stage (0.818 to 0.906 for the BV, and 0.919 to 0.934 for the body). The proposed method significantly reduces the inference time (102.36 to 0.09 s/volume around 1000x faster) while slightly improves the segmentation accuracy over the previous methods using slide-window approaches.