Combining deep learning with anatomical analysis for segmentation of the portal vein for liver SBRT planning

Automated segmentation of the portal vein (PV) for liver radiotherapy planning is a challenging task due to potentially low vasculature contrast, complex PV anatomy and image artifacts originated from fiducial markers and vasculature stents. In this paper, we propose a novel framework for automated segmentation of the PV from computed tomography (CT) images. We apply convolutional neural networks (CNNs) to learn the consistent appearance patterns of the PV using a training set of CT images with reference annotations and then enhance the PV in previously unseen CT images. Markov random fields (MRFs) were further used to smooth the results of the enhancement of the CNN enhancement and remove isolated mis-segmented regions. Finally, CNN-MRF-based enhancement was augmented with PV centerline detection that relied on PV anatomical properties such as tubularity and branch composition. The framework was validated on a clinical database with 72 CT images of patients scheduled for liver stereotactic body radiation therapy. The obtained accuracy of the segmentation was [Formula: see text] 0.83 and [Formula: see text] 1.08 mm in terms of the median Dice coefficient and mean symmetric surface distance, respectively, when segmentation is encompassed into the PV region of interest. The obtained results indicate that CNNs and anatomical analysis can be used for the accurate segmentation of the PV and potentially integrated into liver radiation therapy planning.

[1]  Benoit M. Dawant,et al.  Adaptive directional region growing segmentation of the hepatic vasculature , 2008, SPIE Medical Imaging.

[2]  Lei Wu,et al.  Automatic Multi-Scale Segmentation of Intrahepatic Vessel in CT Images for Liver Surgery Planning , 2013, Int. J. Pattern Recognit. Artif. Intell..

[3]  F. Pernus,et al.  Automated detection of spinal centrelines, vertebral bodies and intervertebral discs in CT and MR images of lumbar spine , 2010, Physics in medicine and biology.

[4]  P. Bankhead,et al.  Fast Retinal Vessel Detection and Measurement Using Wavelets and Edge Location Refinement , 2012, PloS one.

[5]  Shankar M. Krishnan,et al.  Detection and measurement of retinal vessels in fundus images using amplitude modified second-order Gaussian filter , 2002, IEEE Transactions on Biomedical Engineering.

[6]  Alejandro F. Frangi,et al.  Muliscale Vessel Enhancement Filtering , 1998, MICCAI.

[7]  Jean-Louis Dillenseger,et al.  Liver Vessels Segmentation Using a Hybrid Geometrical Moments/Graph Cuts Method , 2010, IEEE Transactions on Biomedical Engineering.

[8]  Bostjan Likar,et al.  Automated measurement of anterior and posterior acetabular sector angles , 2012, Medical Imaging.

[9]  Wiro Niessen,et al.  Quantitative evaluation of noise reduction and vesselness filters for liver vessel segmentation on abdominal CTA images , 2015, Physics in medicine and biology.

[10]  Brian B. Avants,et al.  The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) , 2015, IEEE Transactions on Medical Imaging.

[11]  Bulat Ibragimov,et al.  Segmentation of organs‐at‐risks in head and neck CT images using convolutional neural networks , 2017, Medical physics.

[12]  Bostjan Likar,et al.  Model-Based Segmentation of Vertebral Bodies from MR Images with 3D CNNs , 2016, MICCAI.

[13]  Dário A. B. Oliveira,et al.  Segmentation of liver, its vessels and lesions from CT images for surgical planning , 2011, Biomedical engineering online.

[14]  Konstantinos Kamnitsas,et al.  Efficient multi‐scale 3D CNN with fully connected CRF for accurate brain lesion segmentation , 2016, Medical Image Anal..

[15]  Evgin Goceri,et al.  Vessel segmentation from abdominal magnetic resonance images: adaptive and reconstructive approach , 2016, International journal for numerical methods in biomedical engineering.

[16]  Luca Antiga,et al.  Software for hepatic vessel classification: feasibility study for virtual surgery , 2009, International Journal of Computer Assisted Radiology and Surgery.

[17]  R. Tibshirani,et al.  Sparse inverse covariance estimation with the graphical lasso. , 2008, Biostatistics.

[18]  Isabelle Bloch,et al.  A review of 3D vessel lumen segmentation techniques: Models, features and extraction schemes , 2009, Medical Image Anal..

[19]  Lixu Gu,et al.  A new segmentation framework based on sparse shape composition in liver surgery planning system. , 2013, Medical physics.

[20]  Daniel T Chang,et al.  Central liver toxicity after SBRT: An expanded analysis and predictive nomogram. , 2017, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[21]  Silvia D. Chang,et al.  Imaging assessment of congenital and acquired abnormalities of the portal venous system. , 2011, Radiographics : a review publication of the Radiological Society of North America, Inc.

[22]  Nikos Komodakis,et al.  Approximate Labeling via Graph Cuts Based on Linear Programming , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[24]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[25]  Horst Bischof,et al.  Segmentation of interwoven 3d tubular tree structures utilizing shape priors and graph cuts , 2010, Medical Image Anal..

[26]  Leo Joskowicz,et al.  A variational method for vessels segmentation: algorithm and application to liver vessels visualization , 2009, Medical Imaging.

[27]  Wei Wang,et al.  Liver vessel segmentation based on extreme learning machine. , 2016, Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics.

[28]  Xin Yang,et al.  Vascular Active Contour for Vessel Tree Segmentation , 2011, IEEE Transactions on Biomedical Engineering.

[29]  Evgin Goceri,et al.  Automatic labeling of portal and hepatic veins from MR images prior to liver transplantation , 2016, International Journal of Computer Assisted Radiology and Surgery.

[30]  Bradford J. Wood,et al.  Intra-hepatic vessel segmentation and classification in multi-phase CT using optimized graph cuts , 2011, 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[31]  G. Lockwood,et al.  Phase I study of individualized stereotactic body radiotherapy of liver metastases. , 2009, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[32]  Til Aach,et al.  A two-stage approach for fully automatic segmentation of venous vascular structures in liver CT images , 2009, Medical Imaging.

[33]  Héctor Benítez-Pérez,et al.  Parallel Multiscale Feature Extraction and Region Growing: Application in Retinal Blood Vessel Detection , 2010, IEEE Transactions on Information Technology in Biomedicine.

[34]  Daniel T Chang,et al.  Predictors of toxicity associated with stereotactic body radiation therapy to the central hepatobiliary tract. , 2015, International journal of radiation oncology, biology, physics.

[35]  Bulat Ibragimov,et al.  Segmentation of Pathological Structures by Landmark-Assisted Deformable Models , 2017, IEEE Transactions on Medical Imaging.

[36]  Xiangrong Zhou,et al.  Automated segmentation of hepatic vessels in non-contrast X-ray CT images , 2008, Radiological physics and technology.

[37]  Roberto Marcondes Cesar Junior,et al.  Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification , 2005, IEEE Transactions on Medical Imaging.

[38]  Bradford J. Wood,et al.  Automatic labeling of liver veins in CT by probabilistic backward tracing , 2014, 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI).

[39]  Paul Suetens,et al.  Segmentation of liver portal veins by global optimization , 2010, Medical Imaging.

[40]  Yadong Wang,et al.  Accurate Vessel Segmentation With Constrained B-Snake , 2015, IEEE Transactions on Image Processing.

[41]  A. Jemal,et al.  Cancer statistics, 2017 , 2017, CA: a cancer journal for clinicians.

[42]  Qi Tian,et al.  Segmentation of Liver Vasculature From Contrast Enhanced CT Images Using Context-Based Voting , 2011, IEEE Transactions on Biomedical Engineering.

[43]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[44]  Yoshinobu Sato,et al.  A Hessian-based filter for vascular segmentation of noisy hepatic CT scans , 2012, International Journal of Computer Assisted Radiology and Surgery.

[45]  Bostjan Likar,et al.  A Framework for Automated Spine and Vertebrae Interpolation-Based Detection and Model-Based Segmentation , 2015, IEEE Transactions on Medical Imaging.