An Automatic Cascaded Model for Hemorrhagic Stroke Segmentation and Hemorrhagic Volume Estimation

TL;DR

This paper introduces a cascaded 3D UNet-based model for accurate hemorrhagic stroke segmentation and volume estimation in CT images, improving clinical assessment speed and precision.

Contribution

A novel two-stage cascaded deep learning model for hemorrhage segmentation and automatic volume estimation from CT scans.

Findings

Achieved DSC of 85.66% in segmentation

Reduced computation time to 6.2 seconds per sample

Outperformed traditional volume estimation methods

Abstract

Hemorrhagic Stroke (HS) has a rapid onset and is a serious condition that poses a great health threat. Promptly and accurately delineating the bleeding region and estimating the volume of bleeding in Computer Tomography (CT) images can assist clinicians in treatment planning, leading to improved treatment outcomes for patients. In this paper, a cascaded 3D model is constructed based on UNet to perform a two-stage segmentation of the hemorrhage area in CT images from rough to fine, and the hemorrhage volume is automatically calculated from the segmented area. On a dataset with 341 cases of hemorrhagic stroke CT scans, the proposed model provides high-quality segmentation outcome with higher accuracy (DSC 85.66%) and better computation efficiency (6.2 second per sample) when compared to the traditional Tada formula with respect to hemorrhage volume estimation.