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

Lohendran Baskaran,Jagat Narula,Benjamin C Lee,Sanghoon Shin,Ji Min Sung,Fay Y Lin,Jeroen J Bax,Jung Hyun Choi,Edoardo Conte,Matthew J Budoff,Eun Ju Chun,Leslee J Shaw,Hugo Marques,Ilan Gottlieb,Daniel S Berman,Simon Dunham,Habib Samady,Gianluca Pontone,Bobak Mosadegh,Erica Maffei,Byoung Kwon Lee,Renu Virmani,Daniele Andreini,Peter H Stone,Filippo Cademartiri,Zhuoran Xu,Subhi J Al’Aref,Gabriel Maliakal,James K Min,Martin Hadamitzky,Jeong Won Choi ,Hyuk Jae Chang ,Gilbert Raff ,Jonathon Leipsic ,Kavitha M Chinnaiyan ,Sang Eun Lee ,Yong Jin Kim

doi:10.1371/journal.pone.0232573

Abstract

ObjectivesTo develop, demonstrate and evaluate an automated deep learning method for multiple cardiovascular structure segmentation.BackgroundSegmentation 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.MethodsImages 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.ResultsThe 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.ConclusionsAn automated deep learning model demonstrated segmentation of multiple cardiovascular structures from CCTA images with reasonable overall accuracy when evaluated on a pixel level.

Highlights

In evaluating cardiovascular disease (CVD), the imaging of structures plays a key role in diagnosis, as well as in surveillance of progression
Apart from the coronary sinus (CS), there were no significant differences in performance between sexes or age groups
An automated deep learning model demonstrated segmentation of multiple cardiovascular structures from Coronary Computed Tomography Angiography (CCTA) images with reasonable overall accuracy when evaluated on a pixel level

Summary

Introduction

In evaluating cardiovascular disease (CVD), the imaging of structures plays a key role in diagnosis, as well as in surveillance of progression. In both research and clinical workflows, the necessary quantitative and qualitative evaluation of these structures is assisted via available commercial software packages This requires manual input, rendering this process time-consuming and operator-dependent [1]. Deep learning is a subdomain of ML that uses sophisticated frameworks comprising networks with many intermediate layers of “neurons” to perform automated feature extraction. This results in the ability to map inputs to outputs via complex pathways [3]. We design an automated deep learning method for the segmentation of multiple structures from Coronary Computed Tomography Angiography (CCTA) images

Objectives

Methods

Results

Conclusion