PMID- 30460430
OWN - NLM
STAT- MEDLINE
DCOM- 20190726
LR  - 20210109
IS  - 1352-8661 (Electronic)
IS  - 0968-5243 (Linking)
VI  - 32
IP  - 2
DP  - 2019 Apr
TI  - Development and testing of a deep learning-based strategy for scar segmentation 
      on CMR-LGE images.
PG  - 187-195
LID - 10.1007/s10334-018-0718-4 [doi]
AB  - OBJECTIVE: The aim of this paper is to investigate the use of fully convolutional 
      neural networks (FCNNs) to segment scar tissue in the left ventricle from cardiac 
      magnetic resonance with late gadolinium enhancement (CMR-LGE) images. METHODS: A 
      successful FCNN in the literature (the ENet) was modified and trained to provide 
      scar-tissue segmentation. Two segmentation protocols (Protocol 1 and Protocol 2) 
      were investigated, the latter limiting the scar-segmentation search area to the 
      left ventricular myocardial tissue region. CMR-LGE from 30 patients with 
      ischemic-heart disease were retrospectively analyzed, for a total of 250 images, 
      presenting high variability in terms of scar dimension and location. Segmentation 
      results were assessed against manual scar-tissue tracing using one-patient-out 
      cross validation. RESULTS: Protocol 2 outperformed Protocol 1 significantly (p 
      value < 0.05), with median sensitivity and Dice similarity coefficient equal to 
      88.07% [inter-quartile range (IQR) 18.84%] and 71.25% (IQR 31.82%), respectively. 
      DISCUSSION: Both segmentation protocols were able to detect scar tissues in the 
      CMR-LGE images but higher performance was achieved when limiting the search area 
      to the myocardial region. The findings of this paper represent an encouraging 
      starting point for the use of FCNNs for the segmentation of nonviable scar tissue 
      from CMR-LGE images.
FAU - Moccia, Sara
AU  - Moccia S
AD  - Department of Information Engineering, Universita Politecnica delle Marche, 
      Ancona, Italy.
AD  - Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genoa, Italy.
FAU - Banali, Riccardo
AU  - Banali R
AD  - Department of Electronics, Information and Bioengineering, Politecnico di Milano, 
      Milan, Italy.
FAU - Martini, Chiara
AU  - Martini C
AD  - Diagnostic Department, Azienda Ospedaliera-Universitaria di Parma, Parma, Italy.
FAU - Muscogiuri, Giuseppe
AU  - Muscogiuri G
AD  - Clinical Cardiology Unit and Department of Cardiovascular Imaging, Centro 
      Cardiologico Monzino IRCCS, Milan, Italy.
FAU - Pontone, Gianluca
AU  - Pontone G
AD  - Clinical Cardiology Unit and Department of Cardiovascular Imaging, Centro 
      Cardiologico Monzino IRCCS, Milan, Italy.
FAU - Pepi, Mauro
AU  - Pepi M
AD  - Clinical Cardiology Unit and Department of Cardiovascular Imaging, Centro 
      Cardiologico Monzino IRCCS, Milan, Italy.
FAU - Caiani, Enrico Gianluca
AU  - Caiani EG
AD  - Department of Electronics, Information and Bioengineering, Politecnico di Milano, 
      Milan, Italy. enrico.caiani@polimi.it.
LA  - eng
PT  - Evaluation Study
PT  - Journal Article
DEP - 20181120
PL  - Germany
TA  - MAGMA
JT  - Magma (New York, N.Y.)
JID - 9310752
RN  - 0 (Contrast Media)
RN  - AU0V1LM3JT (Gadolinium)
MH  - Cicatrix/*diagnostic imaging
MH  - Contrast Media
MH  - *Deep Learning
MH  - Female
MH  - Gadolinium
MH  - Heart Ventricles/*diagnostic imaging
MH  - Humans
MH  - Image Enhancement/methods
MH  - Magnetic Resonance Imaging/*methods/statistics & numerical data
MH  - Male
MH  - Myocardial Ischemia/*diagnostic imaging
MH  - Neural Networks, Computer
MH  - Retrospective Studies
OTO - NOTNLM
OT  - CMR-LGE images
OT  - Deep learning
OT  - Fully-convolutional neural networks
OT  - Scar segmentation
EDAT- 2018/11/22 06:00
MHDA- 2019/07/28 06:00
CRDT- 2018/11/22 06:00
PHST- 2018/08/06 00:00 [received]
PHST- 2018/11/08 00:00 [accepted]
PHST- 2018/11/01 00:00 [revised]
PHST- 2018/11/22 06:00 [pubmed]
PHST- 2019/07/28 06:00 [medline]
PHST- 2018/11/22 06:00 [entrez]
AID - 10.1007/s10334-018-0718-4 [pii]
AID - 10.1007/s10334-018-0718-4 [doi]
PST - ppublish
SO  - MAGMA. 2019 Apr;32(2):187-195. doi: 10.1007/s10334-018-0718-4. Epub 2018 Nov 20.