Xuanang Xu1, Fugen Zhou1,2, Bo Liu3,4. 1. Image Processing Center, School of Astronautics, Beihang University, Xueyuan Road No.37, Beijing, China. 2. Beijing Advanced Innovation Center for Biomedical Engineering, Beihang University, Beijing, 100083, China. 3. Image Processing Center, School of Astronautics, Beihang University, Xueyuan Road No.37, Beijing, China. bo.liu@buaa.edu.cn. 4. Beijing Advanced Innovation Center for Biomedical Engineering, Beihang University, Beijing, 100083, China. bo.liu@buaa.edu.cn.
Abstract
PURPOSE: 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. METHODS: 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. RESULTS: 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 the V-net by a significant margin. The Dice Similarity Coefficient of our approach (92.24%) is 8.12% higher than that of the V-net. Moreover, the bladder probability maps performed by our approach present sharper boundaries and more accurate localizations compared with that of the V-net. CONCLUSION: Our approach achieves higher segmentation accuracy than the state-of-the-art method on clinical data. Both the dual-channel processing and the 3D fully connected CRF-RNN contribute to this improvement. The united deep network composed of the CNN and 3D CRF-RNN also outperforms a system where the CRF model acts as a post-processing method disconnected from the CNN.
PURPOSE: 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. METHODS: 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. RESULTS: 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 the V-net by a significant margin. The Dice Similarity Coefficient of our approach (92.24%) is 8.12% higher than that of the V-net. Moreover, the bladder probability maps performed by our approach present sharper boundaries and more accurate localizations compared with that of the V-net. CONCLUSION: Our approach achieves higher segmentation accuracy than the state-of-the-art method on clinical data. Both the dual-channel processing and the 3D fully connected CRF-RNN contribute to this improvement. The united deep network composed of the CNN and 3D CRF-RNN also outperforms a system where the CRF model acts as a post-processing method disconnected from the CNN.
Authors: B Haas; T Coradi; M Scholz; P Kunz; M Huber; U Oppitz; L André; V Lengkeek; D Huyskens; A van Esch; R Reddick Journal: Phys Med Biol Date: 2008-03-07 Impact factor: 3.609
Authors: Liang-Chieh Chen; George Papandreou; Iasonas Kokkinos; Kevin Murphy; Alan L Yuille Journal: IEEE Trans Pattern Anal Mach Intell Date: 2017-04-27 Impact factor: 6.226
Authors: Arnaud Arindra Adiyoso Setio; Francesco Ciompi; Geert Litjens; Paul Gerke; Colin Jacobs; Sarah J van Riel; Mathilde Marie Winkler Wille; Matiullah Naqibullah; Clara I Sanchez; Bram van Ginneken Journal: IEEE Trans Med Imaging Date: 2016-03-01 Impact factor: 10.048
Authors: Holger R Roth; Le Lu; Ari Seff; Kevin M Cherry; Joanne Hoffman; Shijun Wang; Jiamin Liu; Evrim Turkbey; Ronald M Summers Journal: Med Image Comput Comput Assist Interv Date: 2014
Authors: Konstantinos Kamnitsas; Christian Ledig; Virginia F J Newcombe; Joanna P Simpson; Andrew D Kane; David K Menon; Daniel Rueckert; Ben Glocker Journal: Med Image Anal Date: 2016-10-29 Impact factor: 8.545
Authors: Xiangyuan Ma; Lubomir M Hadjiiski; Jun Wei; Heang-Ping Chan; Kenny H Cha; Richard H Cohan; Elaine M Caoili; Ravi Samala; Chuan Zhou; Yao Lu Journal: Med Phys Date: 2019-02-28 Impact factor: 4.071
Authors: Hanna Sartor; David Minarik; Olof Enqvist; Johannes Ulén; Anders Wittrup; Maria Bjurberg; Elin Trägårdh Journal: Clin Transl Radiat Oncol Date: 2020-09-14
Authors: Xuanang Xu; Chunfeng Lian; Shuai Wang; Tong Zhu; Ronald C Chen; Andrew Z Wang; Trevor J Royce; Pew-Thian Yap; Dinggang Shen; Jun Lian Journal: Med Image Anal Date: 2021-05-28 Impact factor: 13.828