Deep‐learning convolutional neural network: Inner and outer bladder wall segmentation in CT urography

Abstract

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 Institutional Review Board (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 × 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 three‐dimensional (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 ± 1.6 mm, respectively. The corresponding values for the test set were 86.9 ± 9.6%, −8.3 ± 37.7%, 18.4 ± 33.8%, and 3.4 ± 1.8 mm, 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 ± 1.2 mm, respectively. The corresponding values for the test set were 87.5 ± 9.9%, −1.2 ± 20.8%, 11.9 ± 17.0%, and 3.5 ± 2.3 mm, 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 were 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.

Study Progress of Noninvasive Imaging and Radiomics for Decoding the Phenotypes and Recurrence Risk of Bladder Cancer

“…Recently, CNN-based DL strategies have emerged as powerful tools for the semantic segmentation of bladder lumen CT images (90)(91)(92). During 2018, our group (83) proposed a modified UNet framework with a progressive dilated CNN module, realizing the simultaneous segmentation of IB, OB and BCa on T2WI for the first time.…”

Bladder segmentation based on deep learning approaches: current limitations and lessons

“…Preliminary work adapted 2D classification networks to achieve the segmentation task [73,74,75,81]. Particularly, these studies employed the seminal work in [87], AlexNet, as the backbone architecture for their approach.…”

“…In addition to these well-known region-based metrics, other less-employed criteria include the volume intersection (VI) between ground truth and predicted volumes [73,75,84], volume error (VE) [73,81,84], and relative volume difference (RVD) [78].…”

“…Thus, distance-based metrics are sometimes included in the evaluation of proposed methods. For example, the average symmetric surface distance (ASSD) has been considered in [73,27,79,81]. The ASSD between contours A and B is defined as follows:…”

“…First, regarding the number of training and testing images, we have identified three main groups: i ) less than 50 patients [76? , 80, 83, 82, 86], ii between 50 and 100 patients [75,27] and iii ) more than 100 patients [74,77,78,81,84,85]. This results in small test groups to evaluated the proposed methods, some including less than 10 testing images.…”