Assessing the classification of liver focal lesions by using multi-phase computer tomography scans

Authors:
Auréline Quatrehomme;Ingrid Millet;Denis Hoa;Gérard Subsol;William Puech
Affiliations:
IMAIOS, Montpellier, France, LIRMM, Université Montpellier 2 / CNRS, Montpellier, France;Department of Medical Imaging, CHU Lapeyronie, Montpellier, France;IMAIOS, Montpellier, France;LIRMM, Université Montpellier 2 / CNRS, Montpellier, France;LIRMM, Université Montpellier 2 / CNRS, Montpellier, France
Venue:
MCBR-CDS'12 Proceedings of the Third MICCAI international conference on Medical Content-Based Retrieval for Clinical Decision Support
Year:
2012

Citing 2
Cited 1

Sum and Difference Histograms for Texture Classification

IEEE Transactions on Pattern Analysis and Machine Intelligence
Fast training of support vector machines using sequential minimal optimization

Advances in kernel methods

Overview of the third workshop on medical content---based retrieval for clinical decision support (MCBR---CDS 2012)

MCBR-CDS'12 Proceedings of the Third MICCAI international conference on Medical Content-Based Retrieval for Clinical Decision Support

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a system for the automated classification of liver focal lesions of Computer Tomography (CT) images based on a multi-phase examination protocol. Many visual features are first extracted from the CT-scans and then labelled by a Support Vector Machine classifier. Our dataset contains 95 lesions from 5 types: cysts, adenomas, haemangiomas, hepatocellular carcinomas and metastasis. A Leave-One-Out cross-validation technique allows for classification evaluation. The multi-phase results are compared to the single-phase ones and show a significant improvement, in particular on hypervascular lesions.