TY - JOUR
T1 - Deep learning auto-segmentation of cervical skeletal muscle for sarcopenia analysis in patients with head and neck cancer
AU - Naser, Mohamed A.
AU - Wahid, Kareem A.
AU - Grossberg, Aaron J.
AU - Olson, Brennan
AU - Jain, Rishab
AU - El-Habashy, Dina
AU - Dede, Cem
AU - Salama, Vivian
AU - Abobakr, Moamen
AU - Mohamed, Abdallah S.R.
AU - He, Renjie
AU - Jaskari, Joel
AU - Sahlsten, Jaakko
AU - Kaski, Kimmo
AU - Fuller, Clifton D.
N1 - Publisher Copyright:
Copyright © 2022 Naser, Wahid, Grossberg, Olson, Jain, El-Habashy, Dede, Salama, Abobakr, Mohamed, He, Jaskari, Sahlsten, Kaski and Fuller.
PY - 2022/7/28
Y1 - 2022/7/28
N2 - Background/Purpose: Sarcopenia is a prognostic factor in patients with head and neck cancer (HNC). Sarcopenia can be determined using the skeletal muscle index (SMI) calculated from cervical neck skeletal muscle (SM) segmentations. However, SM segmentation requires manual input, which is time-consuming and variable. Therefore, we developed a fully-automated approach to segment cervical vertebra SM. Materials/Methods: 390 HNC patients with contrast-enhanced CT scans were utilized (300-training, 90-testing). Ground-truth single-slice SM segmentations at the C3 vertebra were manually generated. A multi-stage deep learning pipeline was developed, where a 3D ResUNet auto-segmented the C3 section (33 mm window), the middle slice of the section was auto-selected, and a 2D ResUNet auto-segmented the auto-selected slice. Both the 3D and 2D approaches trained five sub-models (5-fold cross-validation) and combined sub-model predictions on the test set using majority vote ensembling. Model performance was primarily determined using the Dice similarity coefficient (DSC). Predicted SMI was calculated using the auto-segmented SM cross-sectional area. Finally, using established SMI cutoffs, we performed a Kaplan-Meier analysis to determine associations with overall survival. Results: Mean test set DSC of the 3D and 2D models were 0.96 and 0.95, respectively. Predicted SMI had high correlation to the ground-truth SMI in males and females (r>0.96). Predicted SMI stratified patients for overall survival in males (log-rank p = 0.01) but not females (log-rank p = 0.07), consistent with ground-truth SMI. Conclusion: We developed a high-performance, multi-stage, fully-automated approach to segment cervical vertebra SM. Our study is an essential step towards fully-automated sarcopenia-related decision-making in patients with HNC.
AB - Background/Purpose: Sarcopenia is a prognostic factor in patients with head and neck cancer (HNC). Sarcopenia can be determined using the skeletal muscle index (SMI) calculated from cervical neck skeletal muscle (SM) segmentations. However, SM segmentation requires manual input, which is time-consuming and variable. Therefore, we developed a fully-automated approach to segment cervical vertebra SM. Materials/Methods: 390 HNC patients with contrast-enhanced CT scans were utilized (300-training, 90-testing). Ground-truth single-slice SM segmentations at the C3 vertebra were manually generated. A multi-stage deep learning pipeline was developed, where a 3D ResUNet auto-segmented the C3 section (33 mm window), the middle slice of the section was auto-selected, and a 2D ResUNet auto-segmented the auto-selected slice. Both the 3D and 2D approaches trained five sub-models (5-fold cross-validation) and combined sub-model predictions on the test set using majority vote ensembling. Model performance was primarily determined using the Dice similarity coefficient (DSC). Predicted SMI was calculated using the auto-segmented SM cross-sectional area. Finally, using established SMI cutoffs, we performed a Kaplan-Meier analysis to determine associations with overall survival. Results: Mean test set DSC of the 3D and 2D models were 0.96 and 0.95, respectively. Predicted SMI had high correlation to the ground-truth SMI in males and females (r>0.96). Predicted SMI stratified patients for overall survival in males (log-rank p = 0.01) but not females (log-rank p = 0.07), consistent with ground-truth SMI. Conclusion: We developed a high-performance, multi-stage, fully-automated approach to segment cervical vertebra SM. Our study is an essential step towards fully-automated sarcopenia-related decision-making in patients with HNC.
KW - auto-segmentation
KW - deep learning
KW - head and neck cancer
KW - sarcopenia
KW - skeletal muscle index
UR - http://www.scopus.com/inward/record.url?scp=85135274472&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85135274472&partnerID=8YFLogxK
U2 - 10.3389/fonc.2022.930432
DO - 10.3389/fonc.2022.930432
M3 - Article
AN - SCOPUS:85135274472
SN - 2234-943X
VL - 12
JO - Frontiers in Oncology
JF - Frontiers in Oncology
M1 - 930432
ER -