Related Experiment Video
Updated: Jul 24, 2025
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
Published on: December 15, 2023
Multi-Scale Attentional Network for Multi-Focal Segmentation of Active Bleed after Pelvic Fractures
Yuyin Zhou1, David Dreizin2, Yingwei Li1
1The Johns Hopkins University.
Insights
Automated segmentation of arterial bleeding in trauma CT scans is crucial for patient care. A new Multi-Scale Attentional Network (MSAN) significantly improves the accuracy of identifying active hemorrhage.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Radiology
Background:
- Trauma is a leading cause of death globally, with pelvic fractures posing significant risks.
- Accurate and rapid assessment of active arterial bleeding in abdominopelvic trauma CT scans is critical for patient outcomes.
- Current segmentation methods are limited by complexity and lack of end-to-end optimization.
Purpose of the Study:
- To develop a reliable, end-to-end automated segmentation network for active hemorrhage in trauma CT scans.
- To address the challenges of variable contrast, size, location, and multiplicity of bleeding foci.
- To improve objective measurements of bleeding extent for enhanced clinical decision-making.
Main Methods:
- Introduction of the Multi-Scale Attentional Network (MSAN), an end-to-end deep learning model.
- Utilizing a 2D encoder for global contextual information and a multi-scale strategy for varied target sizes.
- Incorporating an attentional module for feature refinement and a multi-view mechanism for 3D information integration.
Main Results:
- MSAN achieves automated segmentation of active hemorrhage from contrast-enhanced trauma CT scans.
- The network effectively handles variations in bleeding focus characteristics.
- MSAN demonstrates a significant improvement of over 7% in Dice Similarity Coefficient (DSC) compared to existing methods.
Conclusions:
- MSAN represents a novel and effective approach for automated hemorrhage segmentation in trauma CT.
- The developed network has the potential to enhance patient triage, resource allocation, and timely intervention.
- This automated tool can provide rapid, objective measurements of bleeding extent, aiding in outcome prediction.
Abstract:
Trauma is the worldwide leading cause of death and disability in those younger than 45 years, and pelvic fractures are a major source of morbidity and mortality. Automated segmentation of multiple foci of arterial bleeding from ab-dominopelvic trauma CT could provide rapid objective measurements of the total extent of active bleeding, potentially augmenting outcome prediction at the point of care, while improving patient triage, allocation of appropriate resources, and time to definitive intervention. In spite of the importance of active bleeding in the quick tempo of trauma care, the task is still quite challenging due to the variable contrast, intensity, location, size, shape, and multiplicity of bleeding foci. Existing work presents a heuristic rule-based segmentation technique which requires multiple stages and cannot be efficiently optimized end-to-end. To this end, we present, Multi-Scale Attentional Network (MSAN), the first yet reliable end-to-end network, for automated segmentation of active hemorrhage from contrast-enhanced trauma CT scans. MSAN consists of the following components: 1) an encoder which fully integrates the global contextual information from holistic 2D slices; 2) a multi-scale strategy applied both in the training stage and the inference stage to handle the challenges induced by variation of target sizes; 3) an attentional module to further refine the deep features, leading to better segmentation quality; and 4) a multi-view mechanism to leverage the 3D information. MSAN reports a significant improvement of more than 7% compared to prior arts in terms of DSC.
