28 33

Cited 0 times in

Automatic segmentation of multiple cardiovascular structures from cardiac computed tomography angiography images using deep learning

Authors
 Lohendran Baskaran  ;  Subhi J Al'Aref  ;  Gabriel Maliakal  ;  Benjamin C Lee  ;  Zhuoran Xu  ;  Jeong W Choi  ;  Sang-Eun Lee  ;  Ji Min Sung  ;  Fay Y Lin  ;  Simon Dunham  ;  Bobak Mosadegh  ;  Yong-Jin Kim  ;  Ilan Gottlieb  ;  Byoung Kwon Lee  ;  Eun Ju Chun  ;  Filippo Cademartiri  ;  Erica Maffei  ;  Hugo Marques  ;  Sanghoon Shin  ;  Jung Hyun Choi  ;  Kavitha Chinnaiyan  ;  Martin Hadamitzky  ;  Edoardo Conte  ;  Daniele Andreini  ;  Gianluca Pontone  ;  Matthew J Budoff  ;  Jonathon A Leipsic  ;  Gilbert L Raff  ;  Renu Virmani  ;  Habib Samady  ;  Peter H Stone  ;  Daniel S Berman  ;  Jagat Narula  ;  Jeroen J Bax  ;  Hyuk-Jae Chang  ;  James K Min  ;  Leslee J Shaw 
Citation
 PLOS ONE, Vol.15(5) : e0232573, 2020-05 
Journal Title
 PLOS ONE 
Issue Date
2020-05
MeSH
Aged ; Computed Tomography Angiography / methods* ; Coronary Vessels / diagnostic imaging* ; Deep Learning* ; Female ; Heart / diagnostic imaging* ; Heart Atria / diagnostic imaging ; Heart Ventricles / diagnostic imaging ; Humans ; Male ; Middle Aged
Abstract
Objectives: To develop, demonstrate and evaluate an automated deep learning method for multiple cardiovascular structure segmentation. Background: Segmentation of cardiovascular images is resource-intensive. We design an automated deep learning method for the segmentation of multiple structures from Coronary Computed Tomography Angiography (CCTA) images. Methods: Images from a multicenter registry of patients that underwent clinically-indicated CCTA were used. The proximal ascending and descending aorta (PAA, DA), superior and inferior vena cavae (SVC, IVC), pulmonary artery (PA), coronary sinus (CS), right ventricular wall (RVW) and left atrial wall (LAW) were annotated as ground truth. The U-net-derived deep learning model was trained, validated and tested in a 70:20:10 split. Results: The dataset comprised 206 patients, with 5.130 billion pixels. Mean age was 59.9 ± 9.4 yrs., and was 42.7% female. An overall median Dice score of 0.820 (0.782, 0.843) was achieved. Median Dice scores for PAA, DA, SVC, IVC, PA, CS, RVW and LAW were 0.969 (0.979, 0.988), 0.953 (0.955, 0.983), 0.937 (0.934, 0.965), 0.903 (0.897, 0.948), 0.775 (0.724, 0.925), 0.720 (0.642, 0.809), 0.685 (0.631, 0.761) and 0.625 (0.596, 0.749) respectively. Apart from the CS, there were no significant differences in performance between sexes or age groups. Conclusions: An automated deep learning model demonstrated segmentation of multiple cardiovascular structures from CCTA images with reasonable overall accuracy when evaluated on a pixel level.
Files in This Item:
T202002617.pdf Download
DOI
10.1371/journal.pone.0232573
Appears in Collections:
1. College of Medicine (의과대학) > Dept. of Internal Medicine (내과학교실) > 1. Journal Papers
Yonsei Authors
Sung, Ji Min(성지민)
Lee, Byoung Kwon(이병권) ORCID logo https://orcid.org/0000-0001-9259-2776
Chang, Hyuk-Jae(장혁재) ORCID logo https://orcid.org/0000-0002-6139-7545
URI
https://ir.ymlib.yonsei.ac.kr/handle/22282913/179192
사서에게 알리기
  feedback

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse

Links