In Medical physics ; h5-index 59.0
BACKGROUND : Cadaveric CT image segmentation is a difficult task to solve, especially when applied to whole-body image volumes. Traditional algorithms require pre-processing using registration, or highly conserved organ morphologies. These requirements cannot be fulfilled by cadaveric specimens, so deep learning must be used to overcome this limitation. Further, the widespread use of 2D algorithms for volumetric data ignores the role of anatomical context. The use of 3D spatial context for volumetric segmentation of CT scans as well as the anatomical context required to optimize the segmentation has not been adequately explored.
PURPOSE : To determine whether 2D slice-by-slice UNet algorithms or 3D volumetric UNet (VNet) algorithms provide a more effective method for segmenting 3D volumes, and to what extent anatomical context plays in the segmentation of soft-tissue organs in cadaveric, non-contrast enhanced CT.
METHODS : We tested five CT segmentation algorithms: 2D UNets with and without 3D data augmentation (3D rotations) as well as volumetric UNets (VNets) with three levels of anatomical context (implemented via image downsampling at 1X, 2X, and 3X) for their performance via 3D Dice coefficients, and Hausdorff distance calculations. The classifiers were trained to segment the kidneys and liver and the performance was evaluated using Dice coefficient and Hausdorff distance on the segmentation versus the ground truth annotation.
RESULTS : Our results demonstrate that VNet algorithms perform significantly better (p < 0.05) than 2D models. Among the VNet classifiers, those that use some level of image downsampling outperform (as calculated through Dice coefficients) the VNet without downsampling. Additionally, the optimal amount of downsampling depends on the target organ.
CONCLUSIONS : Anatomical context is an important component of soft-tissue, multi-organ segmentation in cadaveric, non-contrast-enhanced CT imaging of the whole-body. Different amounts of anatomical contexts are optimal depending on the size, position, and surrounding tissue of the organ. This article is protected by copyright. All rights reserved.
Lewis Steven, Inglis Stuart, Doyle Scott
2023-Feb-27
anatomical context, cadaveric CT, segmentation
