An open source auto-segmentation algorithm for delineating heart and substructures – Development and validation within a multicenter lung cancer cohort
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
An open source auto-segmentation algorithm for delineating heart and substructures – Development and validation within a multicenter lung cancer cohort. / Olloni, Agon; Lorenzen, Ebbe Laugaard; Jeppesen, Stefan Starup; Diederichsen, Axel; Finnegan, Robert; Hoffmann, Lone; Kristiansen, Charlotte; Knap, Marianne; Milo, Marie Louise Holm; Møller, Ditte Sloth; Pøhl, Mette; Persson, Gitte; Sand, Hella M.B.; Sarup, Nis; Thing, Rune Slot; Brink, Carsten; Schytte, Tine.
In: Radiotherapy and Oncology, Vol. 191, 110065, 2024.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - An open source auto-segmentation algorithm for delineating heart and substructures – Development and validation within a multicenter lung cancer cohort
AU - Olloni, Agon
AU - Lorenzen, Ebbe Laugaard
AU - Jeppesen, Stefan Starup
AU - Diederichsen, Axel
AU - Finnegan, Robert
AU - Hoffmann, Lone
AU - Kristiansen, Charlotte
AU - Knap, Marianne
AU - Milo, Marie Louise Holm
AU - Møller, Ditte Sloth
AU - Pøhl, Mette
AU - Persson, Gitte
AU - Sand, Hella M.B.
AU - Sarup, Nis
AU - Thing, Rune Slot
AU - Brink, Carsten
AU - Schytte, Tine
N1 - Publisher Copyright: © 2023 The Authors
PY - 2024
Y1 - 2024
N2 - Background and purpose: Irradiation of the heart in thoracic cancers raises toxicity concerns. For accurate dose estimation, automated heart and substructure segmentation is potentially useful. In this study, a hybrid automatic segmentation is developed. The accuracy of delineation and dose predictions were evaluated, testing the method's potential within heart toxicity studies. Materials and Methods: The hybrid segmentation method delineated the heart, four chambers, three large vessels, and the coronary arteries. The method consisted of a nnU-net heart segmentation and partly atlas- and model-based segmentation of the substructures. The nnU-net training and atlas segmentation was based on lung cancer patients and was validated against a national consensus dataset of 12 patients with breast cancer. The accuracy of dose predictions between manual and auto-segmented heart and substructures was evaluated by transferring the dose distribution of 240 previously treated lung cancer patients to the consensus data set. Results: The hybrid auto-segmentation method performed well with a heart dice similarity coefficient (DSC) of 0.95, with no statistically significant difference between the automatic and manual delineations. The DSC for the chambers varied from 0.78-0.86 for the automatic segmentation and was comparable with the inter-observer variability. Most importantly, the automatic segmentation was as precise as the clinical experts in predicting the dose distribution to the heart and all substructures. Conclusion: The hybrid segmentation method performed well in delineating the heart and substructures. The prediction of dose by the automatic segmentation was aligned with the manual delineations, enabling measurement of heart and substructure dose in large cohorts. The delineation algorithm will be available for download.
AB - Background and purpose: Irradiation of the heart in thoracic cancers raises toxicity concerns. For accurate dose estimation, automated heart and substructure segmentation is potentially useful. In this study, a hybrid automatic segmentation is developed. The accuracy of delineation and dose predictions were evaluated, testing the method's potential within heart toxicity studies. Materials and Methods: The hybrid segmentation method delineated the heart, four chambers, three large vessels, and the coronary arteries. The method consisted of a nnU-net heart segmentation and partly atlas- and model-based segmentation of the substructures. The nnU-net training and atlas segmentation was based on lung cancer patients and was validated against a national consensus dataset of 12 patients with breast cancer. The accuracy of dose predictions between manual and auto-segmented heart and substructures was evaluated by transferring the dose distribution of 240 previously treated lung cancer patients to the consensus data set. Results: The hybrid auto-segmentation method performed well with a heart dice similarity coefficient (DSC) of 0.95, with no statistically significant difference between the automatic and manual delineations. The DSC for the chambers varied from 0.78-0.86 for the automatic segmentation and was comparable with the inter-observer variability. Most importantly, the automatic segmentation was as precise as the clinical experts in predicting the dose distribution to the heart and all substructures. Conclusion: The hybrid segmentation method performed well in delineating the heart and substructures. The prediction of dose by the automatic segmentation was aligned with the manual delineations, enabling measurement of heart and substructure dose in large cohorts. The delineation algorithm will be available for download.
KW - Automatic segmenation
KW - Breast Cancer
KW - Chambers
KW - Coronary arteries
KW - Heart
KW - Hybrid segmentation
KW - Lung Cancer
KW - Multi-atlas
KW - nnU-net
U2 - 10.1016/j.radonc.2023.110065
DO - 10.1016/j.radonc.2023.110065
M3 - Journal article
C2 - 38122851
AN - SCOPUS:85181026165
VL - 191
JO - Radiotherapy & Oncology
JF - Radiotherapy & Oncology
SN - 0167-8140
M1 - 110065
ER -
ID: 379711887