PMID- 33571634
OWN - NLM
STAT- MEDLINE
DCOM- 20210429
LR  - 20220503
IS  - 1873-5894 (Electronic)
IS  - 0730-725X (Print)
IS  - 0730-725X (Linking)
VI  - 78
DP  - 2021 May
TI  - A deep-learning semantic segmentation approach to fully automated MRI-based 
      left-ventricular deformation analysis in cardiotoxicity.
PG  - 127-139
LID - S0730-725X(21)00006-0 [pii]
LID - 10.1016/j.mri.2021.01.005 [doi]
AB  - Left-ventricular (LV) strain measurements with the Displacement Encoding with 
      Stimulated Echoes (DENSE) MRI sequence provide accurate estimates of 
      cardiotoxicity damage related to breast cancer chemotherapy. This study 
      investigated an automated LV chamber quantification tool via segmentation with a 
      supervised deep convolutional neural network (DCNN) before strain analysis with 
      DENSE images. Segmentation for chamber quantification analysis was conducted with 
      a custom DeepLabV3+ DCNN with ResNet-50 backbone on 42 female breast cancer 
      datasets (22 training-sets, eight validation-sets and 12 independent test-sets). 
      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 against 
      ground-truth with sensitivity-specificity analysis, the metrics of Dice, average 
      perpendicular distance (APD) and Hausdorff-distance. Following segmentation, 
      validation was conducted with the Cronbach's Alpha (C-Alpha) intraclass 
      correlation coefficient between LV chamber quantification results with DENSE and 
      Steady State Free Precession (SSFP) acquisitions and a vendor tool-based method 
      to segment the DENSE data, and similarly for myocardial strain analysis in the 
      chambers. The results of myocardial classification from segmentation of the DENSE 
      data were accuracy = 97%, Dice = 0.89 and APD = 2.4 mm in the test-set. The 
      C-Alpha correlations from comparing chamber quantification results between the 
      segmented DENSE and SSFP data and vendor tool-based method were 0.97 for LVEF 
      (56 +/- 7% vs 55 +/- 7% vs 55 +/- 6%, p = 0.6) and 0.77 for LVEDD (4.6 +/- 0.4 cm vs 
      4.5 +/- 0.3 cm vs 4.5 +/- 0.3 cm, p = 0.8). The validation metrics against 
      ground-truth and equivalent parameters obtained from the SSFP segmentation and 
      vendor tool-based comparisons show that the DCNN approach is applicable for 
      automated LV chamber quantification and subsequent strain analysis in 
      cardiotoxicity.
CI  - Copyright (c) 2021 Elsevier Inc. All rights reserved.
FAU - Kar, By Julia
AU  - Kar BJ
AD  - Departments of Mechanical Engineering and Pharmacology, University of South 
      Alabama, 150 Jaguar Drive, Mobile, AL 36688, United States of America. Electronic 
      address: jkar@southalabama.edu.
FAU - Cohen, Michael V
AU  - Cohen MV
AD  - Department of Cardiology, College of Medicine, University of South Alabama, 1700 
      Center Street, Mobile, AL 36604, United States of America.
FAU - McQuiston, Samuel P
AU  - McQuiston SP
AD  - Department of Radiology, University of South Alabama, 2451 USA Medical Center 
      Drive, Mobile, AL 36617, United States of America.
FAU - Malozzi, Christopher M
AU  - Malozzi CM
AD  - Department of Cardiology, College of Medicine, University of South Alabama, 1700 
      Center Street, Mobile, AL 36604, United States of America.
LA  - eng
GR  - R21 EB028063/EB/NIBIB NIH HHS/United States
PT  - Journal Article
PT  - Research Support, N.I.H., Extramural
DEP - 20210208
PL  - Netherlands
TA  - Magn Reson Imaging
JT  - Magnetic resonance imaging
JID - 8214883
SB  - IM
MH  - Automation
MH  - Breast Neoplasms/drug therapy
MH  - Cardiotoxicity/*diagnostic imaging/pathology
MH  - *Deep Learning
MH  - Female
MH  - Heart Ventricles/*diagnostic imaging/*pathology
MH  - Humans
MH  - Image Processing, Computer-Assisted/*methods
MH  - *Magnetic Resonance Imaging
MH  - Semantics
MH  - Sensitivity and Specificity
PMC - PMC8103654
MID - NIHMS1671516
COIS- Competing Interests As authors we confirm that none of us have any competing 
      interests in the manuscript. Hence, there are no potential conflict of interests 
      with any entities within the University of South Alabama or outside including 
      institutes, organizations and commercial entities.
EDAT- 2021/02/12 06:00
MHDA- 2021/04/30 06:00
PMCR- 2022/05/01
CRDT- 2021/02/11 20:11
PHST- 2020/07/27 00:00 [received]
PHST- 2020/10/26 00:00 [revised]
PHST- 2021/01/31 00:00 [accepted]
PHST- 2021/02/12 06:00 [pubmed]
PHST- 2021/04/30 06:00 [medline]
PHST- 2021/02/11 20:11 [entrez]
PHST- 2022/05/01 00:00 [pmc-release]
AID - S0730-725X(21)00006-0 [pii]
AID - 10.1016/j.mri.2021.01.005 [doi]
PST - ppublish
SO  - Magn Reson Imaging. 2021 May;78:127-139. doi: 10.1016/j.mri.2021.01.005. Epub 
      2021 Feb 8.