Share Email Print

Proceedings Paper

An MRI myocarditis index defined by a PCA-based object recognition algorithm
Author(s): Rocco Romano; Igino De Giorgi; Fausto Acernese; Gerardo Giordano; Antonio Orientale; Giovanni Babino; Fabrizio Barone
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Magnetic Resonance Imaging (MRI) has shown promising results in diagnosing myocarditis that can be qualitatively observed as enhanced pixels on the cardiac muscles images. In this paper, a myocarditis index, defined as the ratio between enhanced pixels, representing an inflammation, and the total pixels of myocardial muscle, is presented. In order to recognize and quantify enhanced pixels, a PCA-based recognition algorithm is used. The algorithm, implemented in Matlab, was tested by examining a group of 10 patients, referred to MRI with presumptive, clinical diagnosis of myocarditis. To assess intra- and interobserver variability, two observers blindly analyzed data related to the 10 patients by delimiting myocardial region and selecting enhanced pixels. After 5 days the same observers redid the analysis. The obtained myocarditis indexes were compared to an ordinal variable (values in the 1 - 5 range) that represented the blind assessment of myocarditis seriousness given by two radiologists on the base of the patient case histories. Results show that there is a significant correlation (P < 0:001; r = 0:94) between myocarditis indexes and the radiologists' clinical judgments. Furthermore, a good intraobserver and interobserver reproducibility was obtained.

Paper Details

Date Published: 12 March 2015
PDF: 6 pages
Proc. SPIE 9401, Computational Imaging XIII, 94010K (12 March 2015); doi: 10.1117/12.2082547
Show Author Affiliations
Rocco Romano, Univ. degli Studi di Salerno (Italy)
Igino De Giorgi, Azienda Ospedaliera Univ. San Giovanni di Dio e Ruggi D'Aragona (Italy)
Fausto Acernese, Univ. degli Studi di Salerno (Italy)
Gerardo Giordano, Univ. degli Studi di Salerno (Italy)
Antonio Orientale, Azienda Ospedaliera Univ. San Giovanni di Dio e Ruggi D'Aragona (Italy)
Giovanni Babino, Azienda Ospedaliera Univ. San Giovanni di Dio e Ruggi D'Aragona (Italy)
Fabrizio Barone, Univ. degli Studi di Salerno (Italy)

Published in SPIE Proceedings Vol. 9401:
Computational Imaging XIII
Charles A. Bouman; Ken D. Sauer, Editor(s)

© SPIE. Terms of Use
Back to Top