A comparative study of 2D image segmentation algorithms for traumatic brain lesions using CT data from the ProTECTIII multicenter clinical trial

TL;DR

This study compares various deep learning algorithms for segmenting traumatic brain lesions in CT scans, achieving high accuracy and demonstrating the effectiveness of UNet++ with Focal Tversky Loss in medical image analysis.

Contribution

It introduces a comprehensive comparison of deep learning architectures for brain lesion segmentation in CT images, highlighting the superior performance of UNet++ with Focal Tversky Loss.

Findings

UNet++ with Focal Tversky Loss achieved a Dice score of 0.94 for IPH.

The best model outperformed previous architectures with significant accuracy improvements.

High segmentation accuracy was demonstrated across multiple lesion types.

Abstract

Automated segmentation of medical imaging is of broad interest to clinicians and machine learning researchers alike. The goal of segmentation is to increase efficiency and simplicity of visualization and quantification of regions of interest within a medical image. Image segmentation is a difficult task because of multiparametric heterogeneity within the images, an obstacle that has proven especially challenging in efforts to automate the segmentation of brain lesions from non-contrast head computed tomography (CT). In this research, we have experimented with multiple available deep learning architectures to segment different phenotypes of hemorrhagic lesions found after moderate to severe traumatic brain injury (TBI). These include: intraparenchymal hemorrhage (IPH), subdural hematoma (SDH), epidural hematoma (EDH), and traumatic contusions. We were able to achieve an optimal Dice Coefficient1 score of 0.94 using UNet++ 2D Architecture with Focal Tversky Loss Function, an increase from 0.85 using UNet 2D with Binary Cross-Entropy Loss Function in intraparenchymal hemorrhage (IPH) cases. Furthermore, using the same setting, we were able to achieve the Dice Coefficient score of 0.90 and 0.86 in cases of Extra-Axial bleeds and Traumatic contusions, respectively.