Tumor Segmentation from Magnetic Resonance Imaging by Learning via one-class support vector machine - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2004

Tumor Segmentation from Magnetic Resonance Imaging by Learning via one-class support vector machine

Abstract

In image segmentation, one challenge is how to deal with the nonlinearity of real data distribution, which often makes segmentation methods need more human interactions and make unsatisfied segmentation results. In this paper, we formulate this research issue as a one-class learning problem from both theoretical and practical viewpoints with application on medical image segmentation. For that, a novel and user-friendly tumor segmentation method is proposed by exploring one-class support vector machine (SVM), which has the ability of learning the nonlinear distribution of the tumor data without using any prior knowledge. Extensive experimental results obtained from real patients' medical images clearly show that the proposed unsupervised one-class SVM segmentation method outperforms supervised two-class SVM segmentation method in terms of segmentation accuracy, speed and with less human intervention.
Fichier principal
Vignette du fichier
ZMEC04.pdf (645.38 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00548532 , version 1 (20-12-2010)

Identifiers

  • HAL Id : inria-00548532 , version 1

Cite

Jianguo Zhang, Kai-Kuang Ma, Meng-Hwa Er, Vincent Chong. Tumor Segmentation from Magnetic Resonance Imaging by Learning via one-class support vector machine. International Workshop on Advanced Image Technology (IWAIT '04), Jan 2004, Singapore, Singapore. pp.207--211. ⟨inria-00548532⟩
855 View
683 Download

Share

Gmail Facebook X LinkedIn More