Author + information
- Received May 30, 2019
- Revision received August 8, 2019
- Accepted August 23, 2019
- Published online May 4, 2020.
- Lohendran Baskaran, MBBSa,b,c,∗∗ (, )
- Gabriel Maliakal, MSca,∗,
- Subhi J. Al’Aref, MDa,b,
- Gurpreet Singh, PhDa,
- Zhuoran Xu, MD, MSca,
- Kelly Michalak, BAa,
- Kristina Dolan, BAa,
- Umberto Giannia,
- Alexander van Rosendael, MDa,
- Inge van den Hoogena,
- Donghee Hand,
- Wijnand Stuijfzande,
- Mohit Pandey, MSca,
- Benjamin C. Lee, PhDa,
- Fay Lin, MDa,b,
- Gianluca Pontone, MD, PhDf,
- Paul Knaapen, MD, PhDe,
- Hugo Marques, MD, PhDg,
- Jeroen Bax, MD, PhDh,
- Daniel Berman, MDd,
- Hyuk-Jae Chang, MD, PhDi,
- Leslee J. Shaw, PhDa,b and
- James K. Min, MDa,b
- aDalio Institute of Cardiovascular Imaging, Weill Cornell Medicine, New York, New York
- bDepartment of Radiology, New York-Presbyterian Hospital and Weill Cornell Medicine, New York, New York
- cDepartment of Cardiovascular Medicine, National Heart Centre, Singapore
- dDepartment of Imaging, Cedars-Sinai Medical Center, Cedars-Sinai Heart Institute, Los Angeles, California
- eDepartment of Cardiology, Amsterdam UMC, Location VU University Medical Center, Amsterdam, the Netherlands
- fCentro Cardiologico Monzino, IRCCS, Milan, Italy
- gUNICA, Cardiac CT and MRI Unit, Hospital da Luz, Lisbon, Portugal
- hDepartment of Cardiology, Heart Lung Center, Leiden University Medical Center, Leiden, the Netherlands
- iDivision of Cardiology, Severance Cardiovascular Hospital, Integrative Cardiovascular Imaging Center, Yonsei University College of Medicine, Seoul, South Korea
- ↵∗Address for correspondence:
Dr. Lohendran Baskaran, Weill Cornell Medical College and the Dalio Institute of Cardiovascular Imaging, 413 East 69th Street, Suite 108, New York, New York 10021.
Objectives This study designed and evaluated an end-to-end deep learning solution for cardiac segmentation and quantification.
Background Segmentation of cardiac structures from coronary computed tomography angiography (CCTA) images is laborious. We designed an end-to-end deep-learning solution.
Methods Scans were obtained from multicenter registries of 166 patients who underwent clinically indicated CCTA. Left ventricular volume (LVV) and right ventricular volume (RVV), left atrial volume (LAV) and right atrial volume (RAV), and left ventricular myocardial mass (LVM) were manually annotated as ground truth. A U-Net−inspired, deep-learning model was trained, validated, and tested in a 70:20:10 split.
Results Mean age was 61.1 ± 8.4 years, and 49% were women. A combined overall median Dice score of 0.9246 (interquartile range: 0.8870 to 0.9475) was achieved. The median Dice scores for LVV, RVV, LAV, RAV, and LVM were 0.938 (interquartile range: 0.887 to 0.958), 0.927 (interquartile range: 0.916 to 0.946), 0.934 (interquartile range: 0.899 to 0.950), 0.915 (interquartile range: 0.890 to 0.920), and 0.920 (interquartile range: 0.811 to 0.944), respectively. Model prediction correlated and agreed well with manual annotation for LVV (r = 0.98), RVV (r = 0.97), LAV (r = 0.78), RAV (r = 0.97), and LVM (r = 0.94) (p < 0.05 for all). Mean difference and limits of agreement for LVV, RVV, LAV, RAV, and LVM were 1.20 ml (95% CI: −7.12 to 9.51), −0.78 ml (95% CI: −10.08 to 8.52), −3.75 ml (95% CI: −21.53 to 14.03), 0.97 ml (95% CI: −6.14 to 8.09), and 6.41 g (95% CI: −8.71 to 21.52), respectively.
Conclusions A deep-learning model rapidly segmented and quantified cardiac structures. This was done with high accuracy on a pixel level, with good agreement with manual annotation, facilitating its expansion into areas of research and clinical import.
↵∗ Mr. Baskaran and Mr. Maliakal contributed equally to the content of this paper.
The study was supported by the Dalio Institute of Cardiovascular Imaging. Dr. Lee has been a consultant for Cleerly. Dr. Bax has received speaker fees from Abbott Vascular and Boehringer Ingelheim. Dr. Min has received funding from the Dalio Foundation, National Institutes of Health, and GE Healthcare; has served on the scientific advisory board of Arineta and GE Healthcare; and has an equity interest in Cleerly. All other authors have reported that they have no relationships relevant to the contents of this paper to disclose. Joseph Schoepf, MD, served as Guest Editor for this paper.
The authors attest they are in compliance with human studies committees and animal welfare regulations of the authors’ institutions and Food and Drug Administration guidelines, including patient consent where appropriate. For more information, visit the JACC: Cardiovascular Imaging author instructions page.
- Received May 30, 2019.
- Revision received August 8, 2019.
- Accepted August 23, 2019.
- 2020 American College of Cardiology Foundation
This article requires a subscription or purchase to view the full text. If you are a subscriber or member, click Login or the Subscribe link (top menu above) to access this article.