Automated Contouring of Contrast and Noncontrast Computed Tomography Liver Images With Fully Convolutional Networks

Abstract

Purpose: The deformable nature of the liver can make focal treatment challenging and is not adequately addressed with simple rigid registration techniques. More advanced registration techniques can take deformations into account (eg, biomechanical modeling) but require segmentations of the whole liver for each scan, which is a time-intensive process. We hypothesize that fully convolutional networks can be used to rapidly and accurately autosegment the liver, removing the temporal bottleneck for biomechanical modeling.

Methods and materials: Manual liver segmentations on computed tomography scans from 183 patients treated at our institution and 30 scans from the Medical Image Computing & Computer Assisted Intervention challenges were collected for this study. Three architectures were investigated for rapid automated segmentation of the liver (VGG-16, DeepLabv3 +, and a 3-dimensional UNet). Fifty-six cases were set aside as a final test set for quantitative model evaluation. Accuracy of the autosegmentations was assessed using Dice similarity coefficient and mean surface distance. Qualitative evaluation was also performed by 3 radiation oncologists on 50 independent cases with previously clinically treated liver contours.

Results: The mean (minimum-maximum) mean surface distance for the test groups with the final model, DeepLabv3 +, were as follows: μ_{Contrast(N = 17)}: 0.99 mm (0.47-2.2), μ_{Non_Contrast(N = 19)l}: 1.12 mm (0.41-2.87), and μ_{Miccai(N = 30)t}: 1.48 mm (0.82-3.96). The qualitative evaluation showed that 30 of 50 autosegmentations (60%) were preferred to manual contours (majority voting) in a blinded comparison, and 48 of 50 autosegmentations (96%) were deemed clinically acceptable by at least 1 reviewing physician.

Conclusions: The autosegmentations were preferred compared with manually defined contours in the majority of cases. The ability to rapidly segment the liver with high accuracy achieved in this investigation has the potential to enable the efficient integration of biomechanical model-based registration into a clinical workflow.

Figure 1

Hyper-parameter searching for ideal UNet style architecture. Parameters varied were number of layers in depth (2-5), number of convolution layers (0-2) versus atrous layers, and maximum number of filters (16-32). For ease of viewing, convolution layer 2 is not shown.

Figure 2

Predictions (red) overlayed on top of computed tomography scans for median and worst cases for each architecture. Red arrows indicate regions of failure. (A color version of this figure is available at https://doi.org/10.1016/j.adro.2020.04.023.)

Figure 3

(A) Presence of high-contrast biliary stent causing autosegmentation to underestimate liver, requiring edits, and (B) ascites misidentified as liver. Teal: ground truth; red: auto segmentation. (A color version of this figure is available at https://doi.org/10.1016/j.adro.2020.04.023.)