Automatic bladder segmentation from CT images using deep CNN and 3D fully connected CRF-RNN

International Journal of Computer Assisted Radiology and Surgery
Xuanang XuBo Liu

Abstract

Automatic approach for bladder segmentation from computed tomography (CT) images is highly desirable in clinical practice. It is a challenging task since the bladder usually suffers large variations of appearance and low soft-tissue contrast in CT images. In this study, we present a deep learning-based approach which involves a convolutional neural network (CNN) and a 3D fully connected conditional random fields recurrent neural network (CRF-RNN) to perform accurate bladder segmentation. We also propose a novel preprocessing method, called dual-channel preprocessing, to further advance the segmentation performance of our approach. The presented approach works as following: first, we apply our proposed preprocessing method on the input CT image and obtain a dual-channel image which consists of the CT image and an enhanced bladder density map. Second, we exploit a CNN to predict a coarse voxel-wise bladder score map on this dual-channel image. Finally, a 3D fully connected CRF-RNN refines the coarse bladder score map and produce final fine-localized segmentation result. We compare our approach to the state-of-the-art V-net on a clinical dataset. Results show that our approach achieves superior segmentation accuracy, outperforming...Continue Reading

References

Nov 28, 2018·Proceedings of the National Academy of Sciences of the United States of America·Shanto Iyengar, Douglas S Massey
Feb 9, 2019·Medical Physics·Xiangyuan MaYao Lu

Citations

Nov 19, 2003·Neural Networks : the Official Journal of the International Neural Network Society·Rolf Kötter, Klaas E Stephan
Dec 7, 2007·Medical Image Computing and Computer-assisted Intervention : MICCAI·María Jimena CostaNicholas Ayache
Mar 1, 2014·Medical Image Computing and Computer-assisted Intervention : MICCAI·Adhish PrasoonMads Nielsen
Oct 22, 2014·Medical Image Computing and Computer-assisted Intervention : MICCAI·Holger R RothRonald M Summers
Mar 10, 2016·IEEE Transactions on Medical Imaging·Arnaud Arindra Adiyoso SetioBram van Ginneken
Jun 1, 2016·IEEE Transactions on Pattern Analysis and Machine Intelligence·Evan ShelhamerTrevor Darrell
Nov 20, 2016·Medical Image Analysis·Konstantinos KamnitsasBen Glocker
May 4, 2017·IEEE Transactions on Pattern Analysis and Machine Intelligence·Liang-Chieh ChenAlan L Yuille

Related Concepts

CNN1
Study
Biological Neural Networks
Biologic Segmentation
Neoplasm of Uncertain or Unknown Behavior of Bladder
Three-dimensional
Reversal Learning
X-Ray Computed Tomography
Carcinoma in Situ of Bladder
Bladder Tissue

Related Feeds

Bladder Carcinoma In Situ

Bladder Carcinoma In Situ is a superficial bladder cancer that occurs on the surface layer of the bladder. Discover the latest research on this precancerous condition in this feed.

Related Papers

International Journal of Computer Assisted Radiology and Surgery
Jinlian MaDexing Kong
Conference Proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Ke Yan Jinman Kim
© 2020 Meta ULC. All rights reserved