Development and evaluation of an auto-segmentation tool for the left anterior descending coronary artery of breast cancer patients based on anatomical landmarks

Veerle A B van den Bogaard; Lisanne V van Dijk; Rozemarijn Vliegenthart; Nanna M Sijtsema; Johannes A Langendijk; John H Maduro; Anne P G Crijns

doi:10.1016/j.radonc.2019.03.013

Development and evaluation of an auto-segmentation tool for the left anterior descending coronary artery of breast cancer patients based on anatomical landmarks

Radiother Oncol. 2019 Jul:136:15-20. doi: 10.1016/j.radonc.2019.03.013. Epub 2019 Apr 4.

Authors

Veerle A B van den Bogaard¹, Lisanne V van Dijk¹, Rozemarijn Vliegenthart², Nanna M Sijtsema¹, Johannes A Langendijk¹, John H Maduro¹, Anne P G Crijns³

Affiliations

¹ Department of Radiation Oncology, University of Groningen, University Medical Center Groningen, The Netherlands.
² Center for Medical Imaging, University of Groningen, University Medical Center Groningen, The Netherlands.
³ Department of Radiation Oncology, University of Groningen, University Medical Center Groningen, The Netherlands. Electronic address: a.p.g.crijns@umcg.nl.

PMID: 31015118
DOI: 10.1016/j.radonc.2019.03.013

Abstract

This study describes the development and evaluation of an auto-segmentation tool for the left anterior descending coronary artery (LAD), on non-contrast planning computed tomography scans of breast cancer patients. The dosimetric parameters of the auto-segmented LAD contours are highly correlated with those of manual contours (R²-values ≥0.89).

Keywords: Auto-segmentation; Breast cancer; Left anterior descending coronary artery; Radiotherapy.

MeSH terms

Breast Neoplasms / diagnostic imaging
Breast Neoplasms / pathology
Breast Neoplasms / radiotherapy*
Coronary Vessels / anatomy & histology*
Coronary Vessels / diagnostic imaging
Female
Humans
Middle Aged
Neoplasm Staging
Organs at Risk / anatomy & histology
Organs at Risk / diagnostic imaging
Radiotherapy Planning, Computer-Assisted / methods*
Tomography, X-Ray Computed / methods