An Adaptive Method for Fully Automatic Liver Segmentation in Medical MRI-Images

Despite the importance of the liver segmentation in the medical images for efficient noninvasive diagnosis, few studies found in the literatures for fully automated methods for liver segmentation in Magnetic Resonance Imaging (MRI) compared to that in Computed Tomography (CT) scans. Motivated by this, we propose an adaptive fully automatic liver segmentation method for MRI images based on thresholding and Bayesian classification. Bayesian classifications have proved to be highly robust to various image degradations. It only requires a small amount of training data to estimate the parameters necessary for classification, which is a huge advantage in medical applications. Furthermore, the Bayesian model is robust when large uncertainties are involved in medical image analysis problems. The proposed method is successfully tested on many MRI cases acquired from different patients, in various sizes. Experiments proved the robustness of the proposed liver automatic segmentation process even on data from different scanner types. The segmentation accuracy of the model has a mean Dice Similarity Coefficient (DSC) of 95.5% for MRI datasets.

[1]  Ronald M. Summers,et al.  Liver and Tumor Segmentation and Analysis from CT of Diseased Patients via a Generic Affine Invariant Shape Parameterization and Graph Cuts , 2011, Abdominal Imaging.

[2]  Franz J. Neyer,et al.  A Gentle Introduction to Bayesian Analysis: Applications to Developmental Research , 2013, Child development.

[3]  Yo-Sung Ho,et al.  Automatic liver segmentation for volume measurement in CT Images , 2006, J. Vis. Commun. Image Represent..

[4]  Syamsiah Mashohor,et al.  Automatic liver segmentation on Computed Tomography using random walkers for treatment planning , 2016, EXCLI journal.

[5]  Yohan Payan,et al.  SOFT TISSUE BIOMECHANICAL MODELING FOR COMPUTER ASSISTED SURGERY: CHALLENGES AND PERSPECTIVES , 2016 .

[6]  Kyung-Sik Seo,et al.  Automatic Hepatic Tumor Segmentation Using Composite Hypotheses , 2005, ICIAR.

[7]  Martin Styner,et al.  Comparison and Evaluation of Methods for Liver Segmentation From CT Datasets , 2009, IEEE Transactions on Medical Imaging.

[8]  Pedro Larrañaga,et al.  Feature selection in Bayesian classifiers for the prognosis of survival of cirrhotic patients treated with TIPS , 2005, J. Biomed. Informatics.

[9]  Noha A. Seada,et al.  Automatic Liver Segmentation from Abdominal MRI Images using Active Contours , 2017 .

[10]  Adrian Galdran,et al.  Automatic 3D model-based method for liver segmentation in MRI based on active contours and total variation minimization , 2015, Biomed. Signal Process. Control..

[11]  . S.Kiruthika LIVER EXTRACTION USING HISTOGRAM AND MORPHOLOGY , 2016 .

[12]  Ying Zhao,et al.  Automatic liver MR image segmentation with self-organizing map and hierarchical agglomerative clustering method , 2010, 2010 3rd International Congress on Image and Signal Processing.

[13]  Bram van Ginneken,et al.  Automatic segmentation of the liver in computed tomography scans with voxel classification and atlas matching , 2007 .

[14]  Imran Ahmed,et al.  Overview of Technical Elements of Liver Segmentation , 2016 .

[15]  Ron Kikinis,et al.  Statistical validation of image segmentation quality based on a spatial overlap index. , 2004, Academic radiology.

[16]  Longhai Li,et al.  BAYESIAN CLASSIFICATION AND REGRESSSION WITH HIGH DIMENSIONAL FEATURES , 2007, 0709.2936.

[17]  S. S. Kumar,et al.  Automatic Segmentation of Liver and Tumor for CAD of Liver , 2011 .

[18]  Raja' S. Alomari,et al.  LIVER SEGMENTATION FROM ABDOMEN CT IMAGES WITH BAYESIAN MODEL , 2014 .

[19]  J. Alamelu Mangai,et al.  A Novel Approach for Classifying Medical Images Using Data Mining Techniques , 2013 .

[20]  Shubhesh Amidwar Plagiarism detection using supervised machine learning algorithm , 2017 .

[21]  Yufei Chen,et al.  The domain knowledge based graph-cut model for liver CT segmentation , 2012, Biomed. Signal Process. Control..

[22]  Tao Wang,et al.  Generalized Additive Bayesian Network Classifiers , 2007, IJCAI.

[23]  Rui Tato Marinho,et al.  Classification and Staging of Chronic Liver Disease From Multimodal Data , 2013, IEEE Transactions on Biomedical Engineering.

[24]  Alireza Behrad,et al.  Automatic liver segmentation in MRI images using an iterative watershed algorithm and artificial neural network , 2012, Biomed. Signal Process. Control..

[25]  Dieter Schmalstieg,et al.  Algorithm guided outlining of 105 pancreatic cancer liver metastases in Ultrasound , 2017, Scientific Reports.

[26]  R Mallika Fraud Detection using Supervised Learning Algorithms , 2017 .

[27]  Leo Joskowicz,et al.  An iterative Bayesian approach for nearly automatic liver segmentation: algorithm and validation , 2008, International Journal of Computer Assisted Radiology and Surgery.

[28]  Jun S. Liu,et al.  A Bayesian method for classification of images from electron micrographs. , 2002, Journal of structural biology.

[29]  Yen-Wei Chen,et al.  Liver Segmentation from Low Contrast Open MR Scans Using K-Means Clustering and Graph-Cuts , 2010, ISNN.

[30]  Abdul Rahman Ramli,et al.  Survey on liver CT image segmentation methods , 2011, Artificial Intelligence Review.

[31]  Ina Singh A Study of Effective Segmentation Techniques for Liver Segmentation , 2015 .

[32]  Lixu Gu,et al.  A novel shape prior based level set method for liver segmentation from MR Images , 2008, 2008 International Conference on Information Technology and Applications in Biomedicine.

[33]  Carlos Platero,et al.  A Multiatlas Segmentation Using Graph Cuts with Applications to Liver Segmentation in CT Scans , 2014, Comput. Math. Methods Medicine.

[34]  Suhuai Luo,et al.  Review on the methods of automatic liver segmentation from abdominal images , 2014 .

[35]  Ali Rafiee,et al.  Using neural network for liver detection in abdominal MRI images , 2009, 2009 IEEE International Conference on Signal and Image Processing Applications.

[36]  K. Zou,et al.  Three validation metrics for automated probabilistic image segmentation of brain tumours , 2004, Statistics in medicine.