Title :
fMRI-Based Hierarchical SVM Model for the Classification and Grading of Liver Fibrosis
Author :
Sela, Yehonatan ; Freiman, Moti ; Dery, Elia ; Edrei, Yifat ; Safadi, Rifaat ; Pappo, Orit ; Joskowicz, Leo ; Abramovitch, Rinat
Author_Institution :
Sch. of Eng. & Comput. Sci., Hebrew Univ. of Jerusalem, Jerusalem, Israel
Abstract :
We present a novel method for the automatic classification and grading of liver fibrosis based on hepatic hemodynamic changes measured noninvasively from functional MRI (fMRI) scans combined with hypercapnia and hyperoxia. The supervised learning method automatically creates a classification and grading model for liver fibrosis grade from training datasets. It constructs a statistical model of liver fibrosis by evaluating the signal intensity time course and local variance in T2*-W fMRI scans acquired during the breathing of air, air-carbon dioxide, and carbogen with a hierarchical multiclass binary-based support vector machine (SVM) classifier. Two experimental studies on 162 slices from 34 mice with the hierarchical multiclass binary-based SVM classifier yield 96.9% separation accuracy between healthy and histological-based fibrosis graded subjects, and an overall accuracy of 75.3% for healthy, fibrotic, and cirrhotic subjects. These results outperform existing image-based methods that can discriminate between healthy and mild-grade fibrosis subjects.
Keywords :
biomedical MRI; diseases; haemodynamics; liver; medical image processing; pneumodynamics; support vector machines; T2<;sup>;*<;/sup>;-W fMRI scans; air breathing; air-carbon dioxide breathing; carbogen breathing; cirrhotic subject; fMRI-based hierarchical SVM model; fibrotic subject; functional MRI scans; healthy subject; hepatic hemodynamic changes; hierarchical multiclass binary-based support vector machine classifier; histological-based fibrosis graded subjects; hypercapnia; hyperoxia; image-based methods; liver fibrosis grade; mild-grade fibrosis subject; signal intensity time; Accuracy; Hemodynamics; Liver; Magnetic resonance imaging; Mice; Pixel; Support vector machines; Abdominal; characterization; early detection; fibrosis; functional MRI (fMRI); liver; machine learning; Animals; Databases, Factual; Disease Models, Animal; Image Interpretation, Computer-Assisted; Liver Cirrhosis; Magnetic Resonance Imaging; Mice; ROC Curve; Reproducibility of Results; Support Vector Machines;
Journal_Title :
Biomedical Engineering, IEEE Transactions on
DOI :
10.1109/TBME.2011.2159501