Comparative Evaluation of 3D and 2D Deep Learning Techniques for Semantic Segmentation in CT Scans

TL;DR

This study compares 3D and 2D deep learning methods for segmenting lung abnormalities in CT scans, demonstrating that 3D approaches outperform 2D in accuracy and inference speed, with better contextual understanding.

Contribution

The paper introduces a 3D stack-based deep learning technique for CT scan segmentation and provides a comprehensive comparison with traditional 2D methods, highlighting advantages in accuracy and efficiency.

Findings

3D technique achieves 79% dice score, outperforming 73% of 2D.

3D method reduces inference time by 5 times compared to 2D.

Area-plots from 3D models are more similar to ground truth.

Abstract

Image segmentation plays a pivotal role in several medical-imaging applications by assisting the segmentation of the regions of interest. Deep learning-based approaches have been widely adopted for semantic segmentation of medical data. In recent years, in addition to 2D deep learning architectures, 3D architectures have been employed as the predictive algorithms for 3D medical image data. In this paper, we propose a 3D stack-based deep learning technique for segmenting manifestations of consolidation and ground-glass opacities in 3D Computed Tomography (CT) scans. We also present a comparison based on the segmentation results, the contextual information retained, and the inference time between this 3D technique and a traditional 2D deep learning technique. We also define the area-plot, which represents the peculiar pattern observed in the slice-wise areas of the pathology regions predicted by these deep learning models. In our exhaustive evaluation, 3D technique performs better than the 2D technique for the segmentation of CT scans. We get dice scores of 79% and 73% for the 3D and the 2D techniques respectively. The 3D technique results in a 5X reduction in the inference time compared to the 2D technique. Results also show that the area-plots predicted by the 3D model are more similar to the ground truth than those predicted by the 2D model. We also show how increasing the amount of contextual information retained during the training can improve the 3D model's performance.