Clinical Evaluation of Deep Learning for Tumor Delineation on 18F-FDG PET/CT of Head and Neck Cancer

David G Kovacs; Claes N Ladefoged; Kim F Andersen; Jane M Brittain; Charlotte B Christensen; Danijela Dejanovic; Naja L Hansen; Annika Loft; Jørgen H Petersen; Michala Reichkendler; Flemming L Andersen; Barbara M Fischer

doi:10.2967/jnumed.123.266574

Clinical Evaluation of Deep Learning for Tumor Delineation on ¹⁸F-FDG PET/CT of Head and Neck Cancer

J Nucl Med. 2024 Feb 22;65(4):623-629. doi: 10.2967/jnumed.123.266574. Online ahead of print.

Authors

David G Kovacs^{1

2}, Claes N Ladefoged^{3

4}, Kim F Andersen³, Jane M Brittain³, Charlotte B Christensen⁵, Danijela Dejanovic³, Naja L Hansen³, Annika Loft³, Jørgen H Petersen⁶, Michala Reichkendler³, Flemming L Andersen^{3

2}, Barbara M Fischer^{3

2

7}

Affiliations

¹ Department of Clinical Physiology and Nuclear Medicine, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark; dkov0001@regionh.dk.
² Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark.
³ Department of Clinical Physiology and Nuclear Medicine, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark.
⁴ Department of Applied Mathematics and Computer Science, Technical University of Denmark, Lyngby, Denmark.
⁵ Department of Clinical Physiology and Nuclear Medicine, Herlev Hospital, University of Copenhagen, Copenhagen, Denmark.
⁶ Section of Biostatistics, Institute of Public Health, Faculty of Health Sciences, University of Copenhagen, Denmark; and.
⁷ PET Centre, School of Biomedical Engineering and Imaging Science, King's College London, London, United Kingdom.

Abstract

Artificial intelligence (AI) may decrease ¹⁸F-FDG PET/CT-based gross tumor volume (GTV) delineation variability and automate tumor-volume-derived image biomarker extraction. Hence, we aimed to identify and evaluate promising state-of-the-art deep learning methods for head and neck cancer (HNC) PET GTV delineation. Methods: We trained and evaluated deep learning methods using retrospectively included scans of HNC patients referred for radiotherapy between January 2014 and December 2019 (ISRCTN16907234). We used 3 test datasets: an internal set to compare methods, another internal set to compare AI-to-expert variability and expert interobserver variability (IOV), and an external set to compare internal and external AI-to-expert variability. Expert PET GTVs were used as the reference standard. Our benchmark IOV was measured using the PET GTV of 6 experts. The primary outcome was the Dice similarity coefficient (DSC). ANOVA was used to compare methods, a paired t test was used to compare AI-to-expert variability and expert IOV, an unpaired t test was used to compare internal and external AI-to-expert variability, and post hoc Bland-Altman analysis was used to evaluate biomarker agreement. Results: In total, 1,220 ¹⁸F-FDG PET/CT scans of 1,190 patients (mean age ± SD, 63 ± 10 y; 858 men) were included, and 5 deep learning methods were trained using 5-fold cross-validation (n = 805). The nnU-Net method achieved the highest similarity (DSC, 0.80 [95% CI, 0.77-0.86]; n = 196). We found no evidence of a difference between expert IOV and AI-to-expert variability (DSC, 0.78 for AI vs. 0.82 for experts; mean difference of 0.04 [95% CI, -0.01 to 0.09]; P = 0.12; n = 64). We found no evidence of a difference between the internal and external AI-to-expert variability (DSC, 0.80 internally vs. 0.81 externally; mean difference of 0.004 [95% CI, -0.05 to 0.04]; P = 0.87; n = 125). PET GTV-derived biomarkers of AI were in good agreement with experts. Conclusion: Deep learning can be used to automate ¹⁸F-FDG PET/CT tumor-volume-derived imaging biomarkers, and the deep-learning-based volumes have the potential to assist clinical tumor volume delineation in radiation oncology.

Keywords: 18F-FDG PET/CT; deep learning; head and neck cancer; imaging biomarkers; tumor volume delineation.