Unsupervised Cerebrovascular Segmentation of TOF-MRA Images Based on Deep Neural Network and Hidden Markov Random Field Model

Automated cerebrovascular segmentation of time-of-flight magnetic resonance angiography (TOF-MRA) images is an important technique, which can be used to diagnose abnormalities in the cerebrovascular system, such as vascular stenosis and malformation. Automated cerebrovascular segmentation can direct show the shape, direction and distribution of blood vessels. Although deep neural network (DNN)-based cerebrovascular segmentation methods have shown to yield outstanding performance, they are limited by their dependence on huge training dataset. In this paper, we propose an unsupervised cerebrovascular segmentation method of TOF-MRA images based on DNN and hidden Markov random field (HMRF) model. Our DNN-based cerebrovascular segmentation model is trained by the labeling of HMRF rather than manual annotations. The proposed method was trained and tested using 100 TOF-MRA images. The results were evaluated using the dice similarity coefficient (DSC), which reached a value of 0.79. The trained model achieved better performance than that of the traditional HMRF-based cerebrovascular segmentation method in binary pixel-classification. This paper combines the advantages of both DNN and HMRF to train the model with a not so large amount of the annotations in deep learning, which leads to a more effective cerebrovascular segmentation method.

[1]  Osamu Abe,et al.  Deep neural network‐based computer‐assisted detection of cerebral aneurysms in MR angiography , 2018, Journal of magnetic resonance imaging : JMRI.

[2]  Thomas S. Hatsukami,et al.  3D intracranial artery segmentation using a convolutional autoencoder , 2017, 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[3]  Nils Daniel Forkert,et al.  Vascular Segmentation in TOF MRA Images of the Brain Using a Deep Convolutional Neural Network , 2017, CVII-STENT/LABELS@MICCAI.

[4]  Jing Qin,et al.  3D Deeply-Supervised U-Net Based Whole Heart Segmentation , 2017, STACOM@MICCAI.

[5]  Yusuf Huseyin Sahin,et al.  Cerebral vessel classification with convolutional neural networks , 2017, 2017 25th Signal Processing and Communications Applications Conference (SIU).

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

[7]  David A. Bennett,et al.  Relation of Cerebral Vessel Disease to Alzheimer’s Disease Dementia and Cognitive Function in Older Persons: A Cross-sectional Study , 2016, The Lancet Neurology.

[8]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling , 2015, CVPR 2015.

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

[10]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[12]  Mutlu Avci,et al.  A fluid dynamics-based deformable model for segmentation of cervical cell images , 2014 .

[13]  J. Gore,et al.  Multiplicative intrinsic component optimization (MICO) for MRI bias field estimation and tissue segmentation. , 2014, Magnetic resonance imaging.

[14]  Anthony S. Kim,et al.  Global Variation in the Relative Burden of Stroke and Ischemic Heart Disease , 2011, Circulation.

[15]  Gustavo Carneiro,et al.  Fast and Robust 3-D MRI Brain Structure Segmentation , 2009, MICCAI.

[16]  Y. Sertdemir,et al.  Estimation of the Ratio of Renal Artery Stenosis with Magnetic Resonance Angiography Using Parallel Imaging Technique in Suspected Renovascular Hypertension , 2006, Nephron Clinical Practice.

[17]  Ashraf A. Kassim,et al.  Segmentation of volumetric MRA images by using capillary active contour , 2006, Medical Image Anal..

[18]  Aly A. Farag,et al.  Cerebrovascular segmentation from TOF using stochastic models , 2006, Medical Image Anal..

[19]  Aly A. Farag,et al.  Automatic Cerebrovascular Segmentation by Accurate Probabilistic Modeling of TOF-MRA Images , 2005, MICCAI.

[20]  Ashraf A. Kassim,et al.  MRA Image Segmentation with Capillary Active Contour , 2005, MICCAI.

[21]  C. C. Lim,et al.  Imaging collateral circulation: magnetic resonance angiography and perfusion magnetic resonance imaging at 3 T. , 2005, Archives of neurology.

[22]  Elsa D. Angelini,et al.  State of the Art of Level Set Methods in Segmentation and Registration of Medical Imaging Modalities , 2005 .

[23]  Albert C. S. Chung,et al.  Vascular segmentation in three-dimensional rotational angiography based on maximum intensity projections , 2004, 2004 2nd IEEE International Symposium on Biomedical Imaging: Nano to Macro (IEEE Cat No. 04EX821).

[24]  Peter L. Choyke,et al.  Isosurfaces as deformable models for magnetic resonance angiography , 2003, IEEE Transactions on Medical Imaging.

[25]  Stephen R. Aylward,et al.  Initialization, noise, singularities, and scale in height ridge traversal for tubular object centerline extraction , 2002, IEEE Transactions on Medical Imaging.

[26]  Stephen M. Smith,et al.  Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm , 2001, IEEE Transactions on Medical Imaging.

[27]  Max A. Viergever,et al.  Fast delineation and visualization of vessels in 3-D angiographic images , 2000, IEEE Transactions on Medical Imaging.

[28]  Olivier D. Faugeras,et al.  Co-dimension 2 Geodesic Active Contours for MRA Segmentation , 1999, IPMI.

[29]  J. Alison Noble,et al.  Segmentation of Cerebral Vessels and Aneurysms from MR Angiography Data , 1997, IPMI.

[30]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[31]  L. R. Dice.  Measures of the Amount of Ecologic Association Between Species , 1945 .