Bladder Cancer Multi-Class Segmentation in MRI With Pyramid-In-Pyramid Network

Recognition and segmentation of bladder walls and tumour in MRI is essential for bladder cancer diagnosis. In this paper, we propose a novel Pyramid in Pyramid (PiP) fully convolutional neural network to address this problem. A pyramid backbone with lateral connections between encoder and decoder is utilized to segment the bladder wall and tumour at multiple scales and in an end-to-end fashion. To boost the model’s capability of extracting multiscale contextual information, a pyramidal atrous convolution block is embedded into the pyramid backbone. We present experimental results to show that the new method outperforms other state-of-the-art models and that the results have a good consistency with that of experienced radiologists.

[1]  Rogério Schmidt Feris,et al.  A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection , 2016, ECCV.

[2]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  W. Shipley,et al.  Bladder cancer , 2009, The Lancet.

[4]  Jing Yuan,et al.  Multiregion segmentation of bladder cancer structures in MRI with progressive dilated convolutional networks , 2018, Medical physics.

[5]  Zhengrong Liang,et al.  A new partial volume segmentation approach to extract bladder wall for computer-aided detection in virtual cystoscopy , 2004, SPIE Medical Imaging.

[6]  Zhaozheng Yin,et al.  Lung segmentation in CT images using a fully convolutional neural network with multi-instance and conditional adversary loss , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[7]  Zhengrong Liang,et al.  A Coupled Level Set Framework for Bladder Wall Segmentation With Application to MR Cystography , 2010, IEEE Transactions on Medical Imaging.

[8]  Kaiming He,et al.  Feature Pyramid Networks for Object Detection , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[10]  Xi Chen,et al.  Deep contextual residual network for electron microscopy image segmentation in connectomics , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[11]  Henrique Madeira,et al.  Xception: A Technique for the Experimental Evaluation of Dependability in Modern Computers , 1998, IEEE Trans. Software Eng..

[12]  Hao Chen,et al.  HL-FCN: Hybrid loss guided FCN for colorectal cancer segmentation , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[13]  T V Bell,et al.  Virtual cystoscopy: early clinical experience. , 1997, Radiology.

[14]  Iasonas Kokkinos,et al.  Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs , 2014, ICLR.