Deep Mouse: An End-to-end Auto-context Refinement Framework for Brain Ventricle and Body Segmentation in Embryonic Mice Ultrasound Volumes

TL;DR

This paper introduces a deep learning framework that automates and accelerates the segmentation of brain ventricles and body in embryonic mice ultrasound images, achieving high accuracy and efficiency.

Contribution

The work presents a novel end-to-end auto-context refinement framework with two stages, significantly improving segmentation accuracy and speed over previous methods.

Findings

Dice Similarity Coefficient improved from 0.818 to 0.906 for BV

Inference time reduced from 102.36s to 0.09s per volume

Method outperforms previous slide-window approaches in accuracy and speed

Abstract

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.