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

by 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

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.