Computer-Aided Diagnosis of Diagnostically Challenging Lesions in Breast MRI: A Comparison between a Radiomics and a Feature-Selective Approach

Sebastian Hoffmann; Marc Lobbes,; Ivo Houben,; Katja Pinker-Domenig,; Georg Wengert,; Bernhard Burgeth; Uwe Meyer-Base,; Guillaume Lemaître; Anke Meyer-Baese

doi:10.1117/12.2228994

Communication dans un congrès

Computer-Aided Diagnosis of Diagnostically Challenging Lesions in Breast MRI: A Comparison between a Radiomics and a Feature-Selective Approach

Sebastian Hoffmann ¹ Marc Lobbes, ² Ivo Houben, ² Katja Pinker-Domenig, ^{3, 4} Georg Wengert, ⁴ Bernhard Burgeth ⁵ Uwe Meyer-Base, ⁶ Guillaume Lemaître ⁷ Anke Meyer-Baese ^{1, 2}

1 Dept Computer Science, Florida State University

2 Dept Radiol. Nuclear Medicine, Maastricht University

3 Memorial Sloane Kettering Cancer Center [New York]

4 Medizinische Universität Wien = Medical University of Vienna

5 Universität des Saarlandes [Saarbrücken]

6 Dept Elect and Comp Engn, Florida State University

7 Le2i - Laboratoire Electronique, Informatique et Image [UMR6306]

Abstract : Diagnostically challenging lesions pose a challenge both for the radiological reading and also for current CAD systems. They are not well-defined in both morphology (geometric shape) and kinetics (temporal enhancement) and pose a problem to lesion detection and classification. Their strong phenotypic differences can be visualized by MRI. Radiomics represents a novel approach to achieve a detailed quantification of the tumour phenotypes by analyzing a large number of image descriptors. In this paper, we apply a quantitative radiomics approach based on shape, texture and kinetics tumor features and evaluate it in comparison to a reduced-order feature approach in a computer-aided diagnosis system applied to diagnostically challenging lesions.

Keywords : Diagnostically challenging lesions morphological and kinetic features classification computer-aided diagnosis radiomics breast magnetic resonance imaging Enhancement Moments Tool

Type de document :

Communication dans un congrès

Domaine :

Physique [physics] / Physique [physics] / Optique [physics.optics]

Sciences de l'ingénieur [physics]

Liste complète des métadonnées

https://hal-univ-bourgogne.archives-ouvertes.fr/hal-01438462
Contributeur : Le2i - Université de Bourgogne Connectez-vous pour contacter le contributeur
Soumis le : mardi 17 janvier 2017 - 17:17:51
Dernière modification le : mercredi 3 novembre 2021 - 08:51:26

Computer-Aided Diagnosis of Diagnostically Challenging Lesions in Breast MRI: A Comparison between a Radiomics and a Feature-Selective Approach

Identifiants

Collections

Citation

Exporter

Métriques

Computer-Aided Diagnosis of Diagnostically Challenging Lesions in Breast MRI: A Comparison between a Radiomics and a Feature-Selective Approach

Identifiants

Collections

Citation

Exporter

Partager

Métriques