PMID- 33571002
OWN - NLM
STAT- MEDLINE
DCOM- 20210330
LR  - 20231111
IS  - 1748-880X (Electronic)
IS  - 0007-1285 (Print)
IS  - 0007-1285 (Linking)
VI  - 94
IP  - 1120
DP  - 2021 Apr 1
TI  - Validation of a deep-learning semantic segmentation approach to fully automate 
      MRI-based left-ventricular deformation analysis in cardiotoxicity.
PG  - 20201101
LID - 10.1259/bjr.20201101 [doi]
LID - 20201101
AB  - OBJECTIVE: Left-ventricular (LV) strain measurements with the Displacement 
      Encoding with Stimulated Echoes (DENSE) MRI sequence provide accurate estimates 
      of cardiotoxicity damage related to chemotherapy for breast cancer. This study 
      investigated an automated and supervised deep convolutional neural network (DCNN) 
      model for LV chamber quantification before strain analysis in DENSE images. 
      METHODS: The DeepLabV3 +DCNN with three versions of ResNet-50 backbone was 
      designed to conduct chamber quantification on 42 female breast cancer data sets. 
      The convolutional layers in the three ResNet-50 backbones were varied as 
      non-atrous, atrous and modified, atrous with accuracy improvements like using 
      Laplacian of Gaussian filters. Parameters such as LV end-diastolic diameter 
      (LVEDD) and ejection fraction (LVEF) were quantified, and myocardial strains 
      analyzed with the Radial Point Interpolation Method (RPIM). Myocardial 
      classification was validated with the performance metrics of accuracy, Dice, 
      average perpendicular distance (APD) and others. Repeated measures ANOVA and 
      intraclass correlation (ICC) with Cronbach's alpha (C-Alpha) tests were conducted 
      between the three DCNNs and a vendor tool on chamber quantification and 
      myocardial strain analysis. RESULTS: Validation results in the same test-set for 
      myocardial classification were accuracy = 97%, Dice = 0.92, APD = 1.2 mm with the 
      modified ResNet-50, and accuracy = 95%, Dice = 0.90, APD = 1.7 mm with the atrous 
      ResNet-50. The ICC results between the modified ResNet-50, atrous ResNet-50 and 
      vendor-tool were C-Alpha = 0.97 for LVEF (55+/-7%, 54+/-7%, 54+/-7%, p = 0.6), and 
      C-Alpha = 0.87 for LVEDD (4.6 +/- 0.3 cm, 4.6 +/- 0.3 cm, 4.6 +/- 0.4 cm, p = 0.7). 
      CONCLUSION: Similar performance metrics and equivalent parameters obtained from 
      comparisons between the atrous networks and vendor tool show that segmentation 
      with the modified, atrous DCNN is applicable for automated LV chamber 
      quantification and subsequent strain analysis in cardiotoxicity. ADVANCES IN 
      KNOWLEDGE: A novel deep-learning technique for segmenting DENSE images was 
      developed and validated for LV chamber quantification and strain analysis in 
      cardiotoxicity detection.
FAU - Karr, Julia
AU  - Karr J
AUID- ORCID: 0000-0003-1140-4310
AD  - Departments of Mechanical Engineering and Pharmacology, University of South 
      Alabama, Mobile, AL, USA.
FAU - Cohen, Michael
AU  - Cohen M
AD  - Department of Cardiology, College of Medicine, University of South Alabama, 
      Mobile, AL, USA.
FAU - McQuiston, Samuel A
AU  - McQuiston SA
AD  - Department of Radiology, University of South Alabama, Mobile, AL, USA.
FAU - Poorsala, Teja
AU  - Poorsala T
AD  - Departments of Oncology and Hematology, University of South Alabama, Mobile, AL, 
      USA.
FAU - Malozzi, Christopher
AU  - Malozzi C
AD  - Department of Cardiology, College of Medicine, University of South Alabama, 
      Mobile, AL, USA.
LA  - eng
PT  - Journal Article
PT  - Validation Study
DEP - 20210224
PL  - England
TA  - Br J Radiol
JT  - The British journal of radiology
JID - 0373125
SB  - IM
MH  - Breast Neoplasms/*drug therapy
MH  - Cardiotoxicity/diagnostic imaging
MH  - *Deep Learning
MH  - Female
MH  - Heart Ventricles/diagnostic imaging
MH  - Humans
MH  - Image Interpretation, Computer-Assisted/*methods
MH  - Magnetic Resonance Imaging/*methods
MH  - Middle Aged
MH  - Reproducibility of Results
MH  - Ventricular Dysfunction, Left/*chemically induced/*diagnostic imaging
PMC - PMC8010548
EDAT- 2021/02/12 06:00
MHDA- 2021/03/31 06:00
PMCR- 2022/04/01
CRDT- 2021/02/11 17:12
PHST- 2021/02/12 06:00 [pubmed]
PHST- 2021/03/31 06:00 [medline]
PHST- 2021/02/11 17:12 [entrez]
PHST- 2022/04/01 00:00 [pmc-release]
AID - 10.1259/bjr.20201101 [doi]
PST - ppublish
SO  - Br J Radiol. 2021 Apr 1;94(1120):20201101. doi: 10.1259/bjr.20201101. Epub 2021 
      Feb 24.