Urinary bladder segmentation in CT urography using deep‐learning convolutional neural network and level sets

Abstract

Purpose: The authors are developing a computerized system for bladder segmentation in CT urography (CTU) as a critical component for computer-aided detection of bladder cancer. Methods: A deep-learning convolutional neural network (DL-CNN) was trained to distinguish between the inside and the outside of the bladder using 160 000 regions of interest (ROI) from CTU images. The trained DL-CNN was used to estimate the likelihood of an ROI being inside the bladder for ROIs centered at each voxel in a CTU case, resulting in a likelihood map. Thresholding and hole-filling were applied to the map to generate the initial contour for the bladder, which was then refined by 3D and 2D level sets. The segmentation performance was evaluated using 173 cases: 81 cases in the training set (42 lesions, 21 wall thickenings, and 18 normal bladders) and 92 cases in the test set (43 lesions, 36 wall thickenings, and 13 normal bladders). The computerized segmentation accuracy using the DL likelihood map was compared to that using a likelihood map generated by Haar features and a random forest classifier, and that using our previous conjoint level set analysis and segmentation system (CLASS) without using a likelihood map. All methods were evaluated relative to the 3D hand-segmented reference contours. Results: With DL-CNN-based likelihood map and level sets, the average volume intersection ratio, average percent volume error, average absolute volume error, average minimum distance, and the Jaccard index for the test set were 81.9% ± 12.1%, 10.2% ± 16.2%, 14.0% ± 13.0%, 3.6 ± 2.0 mm, and 76.2% ± 11.8%, respectively. With the Haar-feature-based likelihood map and level sets, the corresponding values were 74.3% ± 12.7%, 13.0% ± 22.3%, 20.5% ± 15.7%, 5.7 ± 2.6 mm, and 66.7% ± 12.6%, respectively. With our previous CLASS with local contour refinement (LCR) method, the corresponding values were 78.0% ± 14.7%, 16.5% ± 16.8%, 18.2% ± 15.0%, 3.8 ± 2.3 mm, and 73.9% ± 13.5%, respectively. Conclusions: The authors demonstrated that the DL-CNN can overcome the strong boundary between two regions that have large difference in gray levels and provides a seamless mask to guide level set segmentation, which has been a problem for many gradient-based segmentation methods. Compared to our previous CLASS with LCR method, which required two user inputs to initialize the segmentation, DL-CNN with level sets achieved better segmentation performance while using a single user input. Compared to the Haar-feature-based likelihood map, the DL-CNN-based likelihood map could guide the level sets to achieve better segmentation. The results demonstrate the feasibility of our new approach of using DL-CNN in combination with level sets for segmentation of the bladder. C 2016 American Association of Physicists in Medicine. [http://dx

Deep learning of the sectional appearances of 3D CT images for anatomical structure segmentation based on an FCN voting method

“…Recently, deep CNNs have been applied to medical image analysis in several studies. Most of them have used deep CNNs for lesion detection or classification, while others have embedded CNNs into conventional organ‐segmentation processes to reduce the false positive rate in the segmentation results or to predict the likelihood of the image patches . Studies of this type usually divide CT images into numerous small 2D/3D patches at different locations, and then classify these patches into multiple predefined categories.…”

Bladder Cancer Segmentation in CT for Treatment Response Assessment: Application of Deep-Learning Convolution Neural Network—A Pilot Study

“…The neural network was trained to classify regions of interests (ROIs) on 2D sections as being either inside or outside of the bladder cancer. Details on the DL-CNN can be found in the literature (29). The DL-CNN was trained with the pretreatment scans of the cases.…”

“…DL-CNN has also been successfully used for computer-aided detection in medical imaging (28). We have previously applied DL-CNN to the segmentation of whole bladders in CT images (29); however, the segmentation of the tumors is more difficult because contrast material is generally not used in CT for patients undergoing chemotherapy, resulting in low contrast between the tumor and the inside of the bladder.…”

Deep Learning and Medical Diagnosis: A Review of Literature

“…[37] DL-CNN CT urography Urinary bladder segmentation; this method can overcome strong boundaries between two regions that have large differences of gray levels.…”