Automatic Multi-Organ Segmentation on Abdominal CT With Dense V-Networks

Automatic segmentation of abdominal anatomy on computed tomography (CT) images can support diagnosis, treatment planning, and treatment delivery workflows. Segmentation methods using statistical models and multi-atlas label fusion (MALF) require inter-subject image registrations, which are challenging for abdominal images, but alternative methods without registration have not yet achieved higher accuracy for most abdominal organs. We present a registration-free deep-learning-based segmentation algorithm for eight organs that are relevant for navigation in endoscopic pancreatic and biliary procedures, including the pancreas, the gastrointestinal tract (esophagus, stomach, and duodenum) and surrounding organs (liver, spleen, left kidney, and gallbladder). We directly compared the segmentation accuracy of the proposed method to the existing deep learning and MALF methods in a cross-validation on a multi-centre data set with 90 subjects. The proposed method yielded significantly higher Dice scores for all organs and lower mean absolute distances for most organs, including Dice scores of 0.78 versus 0.71, 0.74, and 0.74 for the pancreas, 0.90 versus 0.85, 0.87, and 0.83 for the stomach, and 0.76 versus 0.68, 0.69, and 0.66 for the esophagus. We conclude that the deep-learning-based segmentation represents a registration-free method for multi-organ abdominal CT segmentation whose accuracy can surpass current methods, potentially supporting image-guided navigation in gastrointestinal endoscopy procedures.

[1]  Michael Brady,et al.  MRF-Based Deformable Registration and Ventilation Estimation of Lung CT , 2013, IEEE Transactions on Medical Imaging.

[2]  Masahiro Oda,et al.  Organ Segmentation from 3D Abdominal CT Images Based on Atlas Selection and Graph Cut , 2011, Abdominal Imaging.

[3]  Feng Chen,et al.  Automatic abdominal multi-organ segmentation using deep convolutional neural network and time-implicit level sets , 2016, International Journal of Computer Assisted Radiology and Surgery.

[4]  Y. Matsuoka,et al.  Robotics for surgery. , 1999, Annual review of biomedical engineering.

[5]  Yuichiro Hayashi,et al.  Hierarchical 3D fully convolutional networks for multi-organ segmentation , 2017, ArXiv.

[6]  Zoubin Ghahramani,et al.  Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning , 2015, ICML.

[7]  Ben Glocker,et al.  Geodesic Patch-Based Segmentation , 2014, MICCAI.

[8]  Ronald M. Summers,et al.  Automatic multi-resolution shape modeling of multi-organ structures , 2015, Medical Image Anal..

[9]  Federico Tombari,et al.  Hierarchical Multi-Organ Segmentation Without Registration in 3D Abdominal CT Images , 2015, MCV@MICCAI.

[10]  Dean C. Barratt,et al.  Towards Image-Guided Pancreas and Biliary Endoscopy: Automatic Multi-organ Segmentation on Abdominal CT with Dense Dilated Networks , 2017, MICCAI.

[11]  B. van Ginneken,et al.  Computer-aided diagnosis: how to move from the laboratory to the clinic. , 2011, Radiology.

[12]  Michel Desvignes,et al.  Automatic Multiorgan Segmentation Using Hierarchically Registered Probabilistic Atlases , 2017, Cloud-Based Benchmarking of Medical Image Analysis.

[13]  Thomas Brox,et al.  3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.

[14]  Sébastien Ourselin,et al.  Evaluation of Six Registration Methods for the Human Abdomen on Clinically Acquired CT , 2016, IEEE Transactions on Biomedical Engineering.

[15]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[16]  Konstantinos Kamnitsas,et al.  Anatomically Constrained Neural Networks (ACNNs): Application to Cardiac Image Enhancement and Segmentation , 2017, IEEE Transactions on Medical Imaging.

[17]  M E Ryan,et al.  Guidelines for credentialing and granting privileges for endoscopic ultrasound. , 2001, Gastrointestinal endoscopy.

[18]  Jonathan Tompson,et al.  Efficient object localization using Convolutional Networks , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[20]  Bennett A Landman,et al.  Efficient multi-atlas abdominal segmentation on clinically acquired CT with SIMPLE context learning , 2015, Medical Image Anal..

[21]  Akinobu Shimizu,et al.  Segmentation of multiple organs in non-contrast 3D abdominal CT images , 2007, International Journal of Computer Assisted Radiology and Surgery.

[22]  Daniel Rueckert,et al.  Discriminative dictionary learning for abdominal multi-organ segmentation , 2015, Medical Image Anal..

[23]  Joachim Denzler,et al.  Efficient Convolutional Patch Networks for Scene Understanding , 2015 .

[24]  Hans-Peter Meinzer,et al.  Statistical shape models for 3D medical image segmentation: A review , 2009, Medical Image Anal..

[25]  Seyed-Ahmad Ahmadi,et al.  V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[26]  Fredrik Kahl,et al.  Robust abdominal organ segmentation using regional convolutional neural networks , 2018, Appl. Soft Comput..

[27]  Marius George Linguraru,et al.  Abdominal multi-organ segmentation from CT images using conditional shape-location and unsupervised intensity priors , 2015, Medical Image Anal..

[28]  Ashish Verma,et al.  An Automated System for Atlas Based Multiple OrganSegmentation of Abdominal CT Images , 2016 .

[29]  Song Wang,et al.  Three-Dimensional CT Image Segmentation by Combining 2D Fully Convolutional Network with 3D Majority Voting , 2016, LABELS/DLMIA@MICCAI.

[30]  Ronald M. Summers,et al.  DeepOrgan: Multi-level Deep Convolutional Networks for Automated Pancreas Segmentation , 2015, MICCAI.

[31]  Stephen M. Moore,et al.  The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository , 2013, Journal of Digital Imaging.

[32]  Geoffrey E. Hinton,et al.  Regularizing Neural Networks by Penalizing Confident Output Distributions , 2017, ICLR.

[33]  Gabriele Lombardi,et al.  Automatic Abdominal Organ Segmentation from CT images , 2009 .

[34]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[35]  Kilian Q. Weinberger,et al.  Memory-Efficient Implementation of DenseNets , 2017, ArXiv.

[36]  Cheng Huang,et al.  Fully Automatic Multi-Organ Segmentation Based on Multi-Boost Learning and Statistical Shape Model Search , 2015, VISCERAL Challenge@ISBI.

[37]  Ghassan Hamarneh,et al.  Topology Aware Fully Convolutional Networks for Histology Gland Segmentation , 2016, MICCAI.

[38]  Patrick D. Gerard,et al.  An enhanced sign test for dependent binary data with small numbers of clusters , 2007, Comput. Stat. Data Anal..

[39]  Bram van Ginneken,et al.  A survey on deep learning in medical image analysis , 2017, Medical Image Anal..

[40]  Serge J. Belongie,et al.  Residual Networks Behave Like Ensembles of Relatively Shallow Networks , 2016, NIPS.

[41]  Marius George Linguraru,et al.  Multi-Organ Segmentation with Missing Organs in Abdominal CT Images , 2012, MICCAI.

[42]  Hao Chen,et al.  VoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images , 2017, NeuroImage.

[43]  Nicholas Ayache,et al.  Laplacian Forests: Semantic Image Segmentation by Guided Bagging , 2014, MICCAI.

[44]  Vladlen Koltun,et al.  Multi-Scale Context Aggregation by Dilated Convolutions , 2015, ICLR.

[45]  Vincent Dumoulin,et al.  Deconvolution and Checkerboard Artifacts , 2016 .

[46]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[47]  Jonathan Sykes,et al.  Reflections on the current status of commercial automated segmentation systems in clinical practice , 2014, Journal of medical radiation sciences.

[48]  Timothy F. Cootes,et al.  Active Appearance Models , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[49]  Paul A. Yushkevich,et al.  Multi-Atlas Segmentation with Joint Label Fusion , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.