PMID- 38510543
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20240322
IS  - 2329-4302 (Print)
IS  - 2329-4310 (Electronic)
IS  - 2329-4302 (Linking)
VI  - 11
IP  - 2
DP  - 2024 Mar
TI  - Automated segmentation of the left-ventricle from MRI with a fully convolutional 
      network to investigate CTRCD in breast cancer patients.
PG  - 024003
LID - 10.1117/1.JMI.11.2.024003 [doi]
LID - 024003
AB  - Purpose: The goal of this study was to develop a fully convolutional network 
      (FCN) tool to automatedly segment the left-ventricular (LV) myocardium in 
      displacement encoding with stimulated echoes MRI. The segmentation results are 
      used for LV chamber quantification and strain analyses in breast cancer patients 
      susceptible to cancer therapy-related cardiac dysfunction (CTRCD). Approach: A 
      DeepLabV3+ FCN with a ResNet-101 backbone was custom-designed to conduct chamber 
      quantification on 45 female breast cancer datasets (23 training, 11 validation, 
      and 11 test sets). LV structural parameters and LV ejection fraction (LVEF) were 
      measured, and myocardial strains estimated with the radial point interpolation 
      method. Myocardial classification validation was against quantization-based 
      ground-truth with computations of accuracy, Dice score, average perpendicular 
      distance (APD), Hausdorff-distance, and others. Additional validations were 
      conducted with equivalence tests and Cronbach's alpha (C-alpha) intraclass 
      correlation coefficients between the FCN and a vendor tool on chamber 
      quantification and myocardial strain computations. Results: Myocardial 
      classification results against ground-truth were Dice = 0.89, APD = 2.4  mm, and 
      accuracy = 97% for the validation set and Dice = 0.90, APD = 2.5  mm, and 
      accuracy = 97% for the test set. The confidence intervals (CI) and two one-sided 
      t-test results of equivalence tests between the FCN and vendor-tool were CI =  
      - 1.36% to 2.42%, p-value < 0.001 for LVEF (58 +/- 5% versus 57 +/- 6%), and CI =  
      - 0.71% to 0.63%, p-value < 0.001 for longitudinal strain ( - 15 +/- 2% versus 
      - 15 +/- 3%). Conclusions: The validation results were found equivalent to the 
      vendor tool-based parameter estimates, which show that accurate LV chamber 
      quantification followed by strain analysis for CTRCD investigation can be 
      achieved with our proposed FCN methodology.
CI  - (c) 2024 Society of Photo-Optical Instrumentation Engineers (SPIE).
FAU - Kar, Julia
AU  - Kar J
AUID- ORCID: 0000-0003-1140-4310
AD  - University of South Alabama, Departments of Mechanical Engineering and 
      Pharmacology, Alabama, United States.
FAU - Cohen, Michael V
AU  - Cohen MV
AD  - University of South Alabama, Department of Cardiology, College of Medicine, 
      Alabama, United States.
FAU - McQuiston, Samuel A
AU  - McQuiston SA
AD  - University of South Alabama, Department of Radiology, Alabama, United States.
FAU - Poorsala, Teja
AU  - Poorsala T
AD  - University of South Alabama, Departments of Oncology and Hematology, Alabama, 
      United States.
FAU - Malozzi, Christopher M
AU  - Malozzi CM
AD  - University of South Alabama, Department of Cardiology, College of Medicine, 
      Alabama, United States.
LA  - eng
PT  - Journal Article
DEP - 20240319
PL  - United States
TA  - J Med Imaging (Bellingham)
JT  - Journal of medical imaging (Bellingham, Wash.)
JID - 101643461
PMC - PMC10950093
OTO - NOTNLM
OT  - CTRCD
OT  - artificial intelligence
OT  - cardiotoxicity
OT  - chamber quantification
OT  - deep-learning
OT  - displacement encoding with stimulated echoes
EDAT- 2024/03/21 06:43
MHDA- 2024/03/21 06:44
PMCR- 2025/03/19
CRDT- 2024/03/21 04:11
PHST- 2020/08/25 00:00 [received]
PHST- 2022/03/01 00:00 [accepted]
PHST- 2025/03/19 00:00 [pmc-release]
PHST- 2024/03/21 06:44 [medline]
PHST- 2024/03/21 06:43 [pubmed]
PHST- 2024/03/21 04:11 [entrez]
AID - 20223RR [pii]
AID - 10.1117/1.JMI.11.2.024003 [doi]
PST - ppublish
SO  - J Med Imaging (Bellingham). 2024 Mar;11(2):024003. doi: 
      10.1117/1.JMI.11.2.024003. Epub 2024 Mar 19.