publication . Article . Other literature type . 2017

A 3-D Riesz-Covariance Texture Model for Prediction of Nodule Recurrence in Lung CT

Henning Müller; Xavier Binefa; Todd A. Aguilera; Yashin Dicente Cid; Daniel L. Rubin; Billy W. Loo; Maximilian Diehn; Pol Cirujeda; Adrien Depeursinge;
Open Access
  • Published: 09 Mar 2017 Journal: IEEE Transactions on Medical Imaging, volume 35, issue 12, pages 2,620-2,630
  • Country: Switzerland
Abstract
This paper proposes a novel imaging biomarker of lung cancer relapse from 3–D texture analysis of CT images. Three–dimensional morphological nodular tissue properties are described in terms of 3–D Riesz–wavelets. The responses of the latter are aggregated within nodular regions by means of feature covariances, which leverage rich intra– and inter– variations of the feature space dimensions. When compared to the classical use of the average for feature aggregation, feature covariances preserve spatial co–variations between features. The obtained Riesz–covariance descriptors lie on a manifold governed by Riemannian geometry allowing geodesic measurements and diffe...
Subjects
free text keywords: Electrical and Electronic Engineering, Radiological and Ultrasound Technology, Software, Computer Science Applications, Informatique, Pattern recognition, Kernel (linear algebra), Computer-aided diagnosis, Mathematics, Geodesic, Feature vector, Covariance, Medical imaging, Computer vision, Support vector machine, Imaging biomarker, Artificial intelligence, business.industry, business
Any information missing or wrong?Report an Issue