Deep-Learning Convolutional Neural Network: Inner and Outer Bladder Wall Segmentation in CT Urography.

PURPOSE: We are developing a computerized segmentation tool for the inner and outer bladder wall as a part of an image analysis pipeline for CT urography (CTU).

MATERIALS AND METHODS: A data set of 172 CTU cases was collected retrospectively with IRB approval. The data set was randomly split into two independent sets of training (81 cases) and testing (92 cases) which were manually outlined for both the inner and outer wall. We trained a deep-learning convolutional neural network (DL-CNN) to distinguish the bladder wall from the inside and outside of the bladder using neighborhood information. Approximately 240,000 regions of interest (ROIs) of 16 x 16 pixels in size were extracted from regions in the training cases identified by the manually outlined inner and outer bladder walls to form a training set for the DL-CNN; half of the ROIs were selected to include the bladder wall and the other half were selected to exclude the bladder wall with some of these ROIs being inside the bladder and the rest outside the bladder entirely. The DL-CNN trained on these ROIs was applied to the cases in the test set slice by slice to generate a bladder wall likelihood map where the gray level of a given pixel represents the likelihood that a given pixel would belong to the bladder wall. We then used the DL-CNN likelihood map as an energy term in the energy equation of a cascaded level sets method to segment the inner and outer bladder wall. The DL-CNN segmentation with level sets was compared to the 3D hand-segmented contours as a reference standard.

RESULTS: For the inner wall contour, the training set achieved the average volume intersection, average volume error, average absolute volume error, and average distance of 90.0±8.7%, -4.2± 18.4%, 12.9±13.9%, and 3.0±1.6mm, respectively. The corresponding values for the test set were 86.9±9.6%, -8.3±37.7%, 18.4±33.8%, and 3.4±1.8mm, respectively. For the outer wall contour, the training set achieved the values of 93.7±3.9%, -7.8±11.4%, 10.3±9.3%, and 3.0±1.2mm, respectively. The corresponding values for the test set were 87.5±9.9%, -1.2±20.8%, 11.9±17.0%, and 3.5±2.3mm, respectively.

CONCLUSIONS: Our study demonstrates that DL-CNN assisted level sets can effectively segment bladder walls from the inner bladder and outer structures despite a lack of consistent distinctions along the inner wall. However, even with the addition of level sets, the inner and outer walls may still be over segmented and the DL-CNN assisted level sets may incorrectly segment parts of the prostate that overlap with the outer bladder wall. The outer wall segmentation was improved compared to our previous method and the DL-CNN assisted level sets was also able to segment the inner bladder wall with similar performance. This study shows the DL-CNN assisted level set segmentation tool can effectively segment the inner and outer wall of the bladder. This article is protected by copyright. All rights reserved.