PMID- 28624024
OWN - NLM
STAT- MEDLINE
DCOM- 20180227
LR  - 20181202
IS  - 1872-7727 (Electronic)
IS  - 0720-048X (Linking)
VI  - 92
DP  - 2017 Jul
TI  - Differentiation between acute and chronic myocardial infarction by means of 
      texture analysis of late gadolinium enhancement and cine cardiac magnetic 
      resonance imaging.
PG  - 78-83
LID - S0720-048X(17)30172-9 [pii]
LID - 10.1016/j.ejrad.2017.04.024 [doi]
AB  - The purpose of this study was to differentiate acute from chronic myocardial 
      infarction using machine learning techniques and texture features extracted from 
      cardiac magnetic resonance imaging (MRI). The study group comprised 22 cases with 
      acute myocardial infarction (AMI) and 22 cases with chronic myocardial infarction 
      (CMI). Cine and late gadolinium enhancement (LGE) MRI were analyzed independently 
      to differentiate AMI from CMI. A total of 279 texture features were extracted 
      from predefined regions of interest (ROIs): the infarcted area on LGE MRI, and 
      the entire myocardium on cine MRI. Classification performance was evaluated by a 
      nested cross-validation approach combining a feature selection technique with 
      three predictive models: random forest, support vector machine (SVM) with 
      Gaussian Kernel, and SVM with polynomial kernel. The polynomial SVM yielded the 
      best classification performance. Receiver operating characteristic curves 
      provided area-under-the-curve (AUC) (mean+/-standard deviation) of 0.86+/-0.06 on LGE 
      MRI using 72 features; AMI sensitivity=0.81+/-0.08 and specificity=0.84+/-0.09. On 
      cine MRI, AUC=0.82+/-0.06 using 75 features; AMI sensitivity=0.79+/-0.10 and 
      specificity=0.80+/-0.10. We concluded that texture analysis can be used for 
      differentiation of AMI from CMI on cardiac LGE MRI, and also on standard cine 
      sequences in which the infarction is visually imperceptible in most cases.
CI  - Copyright (c) 2017 Elsevier B.V. All rights reserved.
FAU - Larroza, Andres
AU  - Larroza A
AD  - Department of Medicine, Universitat de Valencia, Valencia, Spain.
FAU - Materka, Andrzej
AU  - Materka A
AD  - Institute of Electronics, Technical University of Lodz, Lodz, Poland.
FAU - Lopez-Lereu, Maria P
AU  - Lopez-Lereu MP
AD  - Unidad de Imagen Cardiaca, ERESA, Valencia, Spain.
FAU - Monmeneu, Jose V
AU  - Monmeneu JV
AD  - Unidad de Imagen Cardiaca, ERESA, Valencia, Spain.
FAU - Bodi, Vicente
AU  - Bodi V
AD  - Department of Medicine, Universitat de Valencia, Valencia, Spain. Electronic 
      address: vicente.bodi@uv.es.
FAU - Moratal, David
AU  - Moratal D
AD  - Center for Biomaterials and Tissue Engineering, Universitat Politecnica de 
      Valencia, Valencia, Spain. Electronic address: dmoratal@eln.upv.es.
LA  - eng
PT  - Journal Article
DEP - 20170501
PL  - Ireland
TA  - Eur J Radiol
JT  - European journal of radiology
JID - 8106411
RN  - 0 (Contrast Media)
RN  - AU0V1LM3JT (Gadolinium)
SB  - IM
MH  - Acute Disease
MH  - Algorithms
MH  - Area Under Curve
MH  - Chronic Disease
MH  - *Contrast Media
MH  - Diagnosis, Differential
MH  - Female
MH  - *Gadolinium
MH  - Humans
MH  - Magnetic Resonance Angiography/methods
MH  - Magnetic Resonance Imaging, Cine/methods
MH  - Male
MH  - Middle Aged
MH  - Myocardial Infarction/*pathology
MH  - Myocardium/pathology
MH  - ROC Curve
MH  - Reproducibility of Results
MH  - Sensitivity and Specificity
MH  - Support Vector Machine
OTO - NOTNLM
OT  - Cardiac MRI
OT  - Classification
OT  - Myocardial infarction
OT  - Texture analysis
EDAT- 2017/06/19 06:00
MHDA- 2018/02/28 06:00
CRDT- 2017/06/19 06:00
PHST- 2016/09/26 00:00 [received]
PHST- 2017/01/27 00:00 [revised]
PHST- 2017/04/30 00:00 [accepted]
PHST- 2017/06/19 06:00 [entrez]
PHST- 2017/06/19 06:00 [pubmed]
PHST- 2018/02/28 06:00 [medline]
AID - S0720-048X(17)30172-9 [pii]
AID - 10.1016/j.ejrad.2017.04.024 [doi]
PST - ppublish
SO  - Eur J Radiol. 2017 Jul;92:78-83. doi: 10.1016/j.ejrad.2017.04.024. Epub 2017 May 
      1.