Comparison of 2D vs. 3D U-Net Organ Segmentation in abdominal 3D CT images
This is an incremental study comparing existing methods for medical image segmentation, potentially benefiting researchers and practitioners in computational efficiency.
The paper tackled the problem of segmenting abdominal organs in 3D CT images by comparing 2D and 3D U-Net architectures, finding that 2D U-Nets achieved up to 6% Dice improvement for some organs while being faster and more GPU-efficient.
A two-step concept for 3D segmentation on 5 abdominal organs inside volumetric CT images is presented. First each relevant organ's volume of interest is extracted as bounding box. The extracted volume acts as input for a second stage, wherein two compared U-Nets with different architectural dimensions re-construct an organ segmentation as label mask. In this work, we focus on comparing 2D U-Nets vs. 3D U-Net counterparts. Our initial results indicate Dice improvements of about 6\% at maximum. In this study to our surprise, liver and kidneys for instance were tackled significantly better using the faster and GPU-memory saving 2D U-Nets. For other abdominal key organs, there were no significant differences, but we observe highly significant advantages for the 2D U-Net in terms of GPU computational efforts for all organs under study.