Fully automated 3D body composition analysis and its association with overall survival in head and neck squamous cell carcinoma patients

Miłosz Rozynek; Daniel Gut; Iwona Kucybała; Ewa Strzałkowska-Kominiak; Zbisław Tabor; Andrzej Urbanik; Stanisław Kłęk; Wadim Wojciechowski

doi:10.3389/fonc.2023.1176425

Fully automated 3D body composition analysis and its association with overall survival in head and neck squamous cell carcinoma patients

Front Oncol. 2023 Oct 19:13:1176425. doi: 10.3389/fonc.2023.1176425. eCollection 2023.

Authors

Miłosz Rozynek¹, Daniel Gut², Iwona Kucybała¹, Ewa Strzałkowska-Kominiak³, Zbisław Tabor², Andrzej Urbanik¹, Stanisław Kłęk⁴, Wadim Wojciechowski¹

Affiliations

¹ Department of Radiology, Jagiellonian University Medical College, Krakow, Poland.
² Department of Biocybernetics and Biomedical Engineering, AGH University of Science and Technology, Krakow, Poland.
³ Department of Statistics, Universidad Carlos III de Madrid, Madrid, Spain.
⁴ Surgical Oncology Clinic, Maria Skłodowska-Curie National Cancer Institute, Krakow, Poland.

Abstract

Objectives: We developed a method for a fully automated deep-learning segmentation of tissues to investigate if 3D body composition measurements are significant for survival of Head and Neck Squamous Cell Carcinoma (HNSCC) patients.

Methods: 3D segmentation of tissues including spine, spine muscles, abdominal muscles, subcutaneous adipose tissue (SAT), visceral adipose tissue (VAT), and internal organs within volumetric region limited by L1 and L5 levels was accomplished using deep convolutional segmentation architecture - U-net implemented in a nnUnet framework. It was trained on separate dataset of 560 single-channel CT slices and used for 3D segmentation of pre-radiotherapy (Pre-RT) and post-radiotherapy (Post-RT) whole body PET/CT or abdominal CT scans of 215 HNSCC patients. Percentages of tissues were used for overall survival analysis using Cox proportional hazard (PH) model.

Results: Our deep learning model successfully segmented all mentioned tissues with Dice's coefficient exceeding 0.95. The 3D measurements including difference between Pre-RT and post-RT abdomen and spine muscles percentage, difference between Pre-RT and post-RT VAT percentage and sum of Pre-RT abdomen and spine muscles percentage together with BMI and Cancer Site were selected and significant at the level of 5% for the overall survival. Aside from Cancer Site, the lowest hazard ratio (HR) value (HR, 0.7527; 95% CI, 0.6487-0.8735; p = 0.000183) was observed for the difference between Pre-RT and post-RT abdomen and spine muscles percentage.

Conclusion: Fully automated 3D quantitative measurements of body composition are significant for overall survival in Head and Neck Squamous Cell Carcinoma patients.

Keywords: artificial intelligence; body composition; head and neck cancer; overall survival; squamous cell carcinoma.