Learning cross-protocol radiomics and deep feature standardization from CT images of texture phantoms

Andrearczyk, Vincent (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)) ; Depeursinge, Adrien (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis); Nuclear Medicine and Molecular Imaging Department, Lausanne University Hospital, Lausanne, Switzerland) ; Müller, Henning (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis); University of Geneva (UNIGE), Geneva, Switzerland)

Radiomics has shown promising results in several medical studies, yet it suers from a limited discrimination and informative capability as well as a high variation and correlation with the tomographic scanner types, pixel spacing, acquisition protocol and reconstruction parameters. This paper introduces a new method to transform image features in order to improve their stability across scanners. This method is based on a two-layer neural network that can learn a non-linear standardization transformation of various types of features including handcrafted and deep features. In this setting, variations in extracted features will be representative of true physiopathological tissue changes in the scanned patients. This approach uses a publicly available texture phantom dataset and can be applied to both hand-crafted radiomic and deep features.


Mots-clés:
Type de conférence:
full paper
Faculté:
Economie et Services
Ecole:
HEG-VS
Institut:
Institut Informatique de gestion
Classification:
Informatique
Adresse bibliogr.:
San Diego, USA, 16-21 February 2019
Date:
2019-02
San Diego, USA
16-21 February 2019
Pagination:
8 p.
Veröffentlicht in:
Proceedings of SPIE medical Imaging 2019: imaging informatics for healthcare, research, and applications
DOI:
ISBN:
9781510625556
Le document apparaît dans:

Note: The status of this file is: restricted


 Datensatz erzeugt am 2019-04-26, letzte Änderung am 2020-10-27

PDF-éditeur:
Volltext herunterladen
PDF

Dieses Dokument bewerten:

Rate this document:
1
2
3
 
(Bisher nicht rezensiert)