Iterative sliced inverse regression for segmentation of ultrasound and MR images

Authors:
Han-Ming Wu;Henry Horng-Shing Lu
Affiliations:
Institute of Statistical Science, Academia Sinica, Taipei 115, Taiwan, ROC;Institute of Statistics, National Chiao Tung University, Hsinchu 300, Taiwan, ROC
Venue:
Pattern Recognition
Year:
2007

Citing 5
Cited 4

The nature of statistical learning theory

The nature of statistical learning theory
Support-Vector Networks

Machine Learning
SVMTorch: support vector machines for large-scale regression problems

The Journal of Machine Learning Research
Attribute weighted mercer kernel based fuzzy clustering algorithm for general non-spherical datasets

Soft Computing - A Fusion of Foundations, Methodologies and Applications
A comparison of methods for multiclass support vector machines

IEEE Transactions on Neural Networks

Fully automatic and segmentation-robust classification of breast tumors based on local texture analysis of ultrasound images

Pattern Recognition
Probability density difference-based active contour for ultrasound image segmentation

Pattern Recognition
Entropy-based sliced inverse regression

Computational Statistics & Data Analysis
Isometric sliced inverse regression for nonlinear manifold learning

Statistics and Computing

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this study, we propose an integrated approach based on iterative sliced inverse regression (ISIR) for the segmentation of ultrasound and magnetic resonance (MR) images. The approach integrates two stages. The first is the unsupervised clustering which combines multidimensional scaling (MDS) with K-Means. The dimension reduction based on MDS is employed to obtain fewer representative variates as input variables for K-Means. This step intends to generate the initial group labels of the training data for the second stage of supervised segmentation. We then combine the SIR with the nearest mean classifier (NMC) or the support vector machine (SVM) to iteratively update the group labels for supervised segmentation. The method of SIR is introduced by Li [Sliced inverse regression for dimension reduction. J. Am. Stat. Assoc. 86 (1991) 316-342] to explore the effective dimension reduction (e.d.r.) directions from the training data embedded in high-dimensional space. The test data are then projected onto these directions and the classifiers are further applied to classify the test data. The integrated approach based on ISIR is evaluated on simulated and clinical images, which include ultrasound and MR images. The evaluation results indicate that this approach provides an improvement of image segmentation over the methods to be compared without dimension reduction.