PMID- 32476706
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20200928
IS  - 0277-786X (Print)
IS  - 1996-756X (Electronic)
IS  - 0277-786X (Linking)
VI  - 11317
DP  - 2020 Feb
TI  - Fully automated segmentation of the right ventricle in patients with repaired 
      Tetralogy of Fallot using U-Net.
LID - 113171M [pii]
LID - 10.1117/12.2549052 [doi]
AB  - Cardiac magnetic resonance (CMR) imaging is considered the standard imaging 
      modality for volumetric analysis of the right ventricle (RV), an especially 
      important practice in the evaluation of heart structure and function in patients 
      with repaired Tetralogy of Fallot (rTOF). In clinical practice, however, this 
      requires time-consuming manual delineation of the RV endocardium in multiple 
      2-dimensional (2D) slices at multiple phases of the cardiac cycle. In this work, 
      we employed a U-Net based 2D convolutional neural network (CNN) classifier in the 
      fully automatic segmentation of the RV blood pool. Our dataset was comprised of 
      5,729 short-axis cine CMR slices taken from 100 individuals with rTOF. Training 
      of our CNN model was performed on images from 50 individuals while validation was 
      performed on images from 10 individuals. Segmentation results were evaluated by 
      Dice similarity coefficient (DSC) and Hausdorff distance (HD). Use of the CNN 
      model on our testing group of 40 individuals yielded a median DSC of 90% and a 
      median 95(th) percentile HD of 5.1 mm, demonstrating good performance in these 
      metrics when compared to literature results. Our preliminary results suggest that 
      our deep learning-based method can be effective in automating RV segmentation.
FAU - Tran, Christopher T
AU  - Tran CT
AD  - University of Texas at Dallas, Department of Bioengineering, Richardson, TX, USA.
FAU - Halicek, Martin
AU  - Halicek M
AD  - University of Texas at Dallas, Department of Bioengineering, Richardson, TX, USA.
AD  - Georgia Inst. of Tech. and Emory Univ., Dept. of Biomedical Engineering, Atlanta, 
      GA.
FAU - Dormer, James D
AU  - Dormer JD
AD  - Georgia Inst. of Tech. and Emory Univ., Dept. of Biomedical Engineering, Atlanta, 
      GA.
FAU - Tandon, Animesh
AU  - Tandon A
AD  - Dept. of Radiology, Univ. of Texas Southwestern Medical Center, Dallas, TX.
AD  - Department of Pediatrics, Univ. of Texas Southwestern Medical Center, Dallas, TX.
FAU - Hussain, Tarique
AU  - Hussain T
AD  - Dept. of Radiology, Univ. of Texas Southwestern Medical Center, Dallas, TX.
AD  - Department of Pediatrics, Univ. of Texas Southwestern Medical Center, Dallas, TX.
FAU - Fei, Baowei
AU  - Fei B
AD  - University of Texas at Dallas, Department of Bioengineering, Richardson, TX, USA.
AD  - Advanced Imaging Research Center, Univ. of Texas Southwestern Medical Center, 
      Dallas, TX.
AD  - Dept. of Radiology, Univ. of Texas Southwestern Medical Center, Dallas, TX.
LA  - eng
GR  - R01 CA156775/CA/NCI NIH HHS/United States
GR  - R01 CA204254/CA/NCI NIH HHS/United States
GR  - R01 HL140325/HL/NHLBI NIH HHS/United States
GR  - R21 CA231911/CA/NCI NIH HHS/United States
PT  - Journal Article
DEP - 20200228
PL  - United States
TA  - Proc SPIE Int Soc Opt Eng
JT  - Proceedings of SPIE--the International Society for Optical Engineering
JID - 101524122
PMC - PMC7261612
MID - NIHMS1592300
OTO - NOTNLM
OT  - Cardiac magnetic resonance imaging
OT  - Convolutional neural network (CNN)
OT  - Deep learning
OT  - Heart
OT  - Image segmentation
OT  - Left ventricle
OT  - Tetralogy of Fallot
COIS- DISCLOSURES The authors have no relevant financial interests in this article and 
      no potential conflicts of interest to disclose.
EDAT- 2020/06/02 06:00
MHDA- 2020/06/02 06:01
PMCR- 2020/05/31
CRDT- 2020/06/02 06:00
PHST- 2020/06/02 06:00 [entrez]
PHST- 2020/06/02 06:00 [pubmed]
PHST- 2020/06/02 06:01 [medline]
PHST- 2020/05/31 00:00 [pmc-release]
AID - 113171M [pii]
AID - 10.1117/12.2549052 [doi]
PST - ppublish
SO  - Proc SPIE Int Soc Opt Eng. 2020 Feb;11317:113171M. doi: 10.1117/12.2549052. Epub 
      2020 Feb 28.