Basic Study
Copyright ©The Author(s) 2021. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Clin Oncol. Feb 24, 2021; 12(2): 95-102
Published online Feb 24, 2021. doi: 10.5306/wjco.v12.i2.95
Autosegmentation of cardiac substructures in respiratory-gated, non-contrasted computed tomography images
Mark Farrugia, Han Yu, Anurag K Singh, Harish Malhotra
Mark Farrugia, Anurag K Singh, Harish Malhotra, Department of Radiation Medicine, Roswell Park Comprehensive Cancer Center, Buffalo, NY 14203, United States
Han Yu, Department of Biostatistics and Bioinformatics, Roswell Park Comprehensive Cancer Center, Buffalo, NY 14203, United States
Author contributions: Farrugia M participated in conceptualization, manual contouring, data analysis, figure construction, writing and editing; Yu H provided statistical support and review; Singh AK was involved in conceptualization and supervision; Malhotra H participated in conceptualization, supervision, software utilization, writing and editing.
Institutional review board statement: The study was reviewed and approved by the Roswell Park Comprehensive Cancer Center Institutional Review Board, No. EDR 171710.
Institutional animal care and use committee statement: The current project did not require any work with animal subjects.
Conflict-of-interest statement: No author claims any conflicts of interest.
Data sharing statement: No additional data are available.
Open-Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See:
Corresponding author: Harish Malhotra, PhD, Assistant Professor, Department of Radiation Medicine, Roswell Park Comprehensive Cancer Center, Elm and Carlton Streets, Buffalo, NY 14203, United States.
Received: November 20, 2020
Peer-review started: November 20, 2020
First decision: December 3, 2020
Revised: December 7, 2020
Accepted: December 22, 2020
Article in press: December 22, 2020
Published online: February 24, 2021

Radiation dose to specific cardiac substructures can have a significant on treatment related morbidity and mortality, yet definition of these structures is labor intensive and not standard. Autosegmentation software may potentially address these issues, however it is unclear whether this approach can be broadly applied across different treatment planning conditions. We investigated the feasibility of autosegmentation of the cardiac substructures in four-dimensional (4D) computed tomography (CT), respiratory-gated, non-contrasted imaging.


To determine whether autosegmentation can be successfully employed on 4DCT respiratory-gated, non-contrasted imaging.


We included patients who underwent stereotactic body radiation therapy for inoperable, early-stage non-small cell lung cancer from 2007 to 2019. All patients were simulated via 4DCT imaging with respiratory gating without intravenous contrast. Generated structure quality was evaluated by degree of required manual edits and volume discrepancy between the autocontoured structures and its edited sister structure.


Initial 17-structure cardiac atlas was generated with 20 patients followed by three successive iterations of 10 patients using MIM software. The great vessels and heart chambers were reliably autosegmented with most edits considered minor. In contrast, coronary arteries either failed to be autosegmented or the generated structures required major alterations necessitating deletion and manual definition. Similarly, the generated mitral and tricuspid valves were poor whereas the aortic and pulmonary valves required at least minor and moderate changes respectively. For the majority of subsites, the additional samples did not appear to substantially impact the quality of generated structures. Volumetric analysis between autosegmented and its manually edited sister structure yielded comparable findings to the physician-based assessment of structure quality.


The use of MIM software with 30-sample subject library was found to be useful in delineating many of the heart substructures with acceptable clinical accuracy on respiratory-gated 4DCT imaging. Small volume structures, such as the coronary arteries were poorly autosegmented and require manual definition.

Keywords: Autosegmentation, Autocontouring, Lung cancer, Radiation therapy, Heart substructures, Stereotactic body radiation therapy

Core Tip: Autosegmentation is an attractive tool to reduce the labor involved with manual delineation of anatomy. However, it is unclear whether this approach is viable for all treatment conditions. Stereotactic body radiation therapy frequently utilizes respiratory gated, non-contrasted computed tomography imaging for radiation planning and involuntary heart motion as well as lack of intravenous contrast may impact the quality of generated structures. In our study, MIM software successfully contoured the great vessels and heart chambers yet failed in generating coronary arteries. We provide evidence that MIM software can reliably autocontour the larger cardiac substructures, but not coronary arteries or heart valves.