Back to all papers

External validation of deep learning-derived 18F-FDG PET/CT delta biomarkers for loco-regional control in head and neck cancer.

Authors

Kovacs DG,Aznar M,Van Herk M,Mohamed I,Price J,Ladefoged CN,Fischer BM,Andersen FL,McPartlin A,Osorio EMV,Abravan A

Affiliations (6)

  • Department of Clinical Physiology and Nuclear Medicine, Rigshospitalet, Copenhagen, Denmark; Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark. [email protected].
  • Division of Cancer Sciences, University of Manchester, Manchester, the United Kingdom of Great Britain and Northern Ireland; The Christie NHS Foundation Trust, Manchester, the United Kingdom of Great Britain and Northern Ireland.
  • The Christie NHS Foundation Trust, Manchester, the United Kingdom of Great Britain and Northern Ireland.
  • Department of Clinical Physiology and Nuclear Medicine, Rigshospitalet, Copenhagen, Denmark; Department of Applied Mathematics and Computer Science, Technical University of Denmark, Lyngby, Denmark.
  • Department of Clinical Physiology and Nuclear Medicine, Rigshospitalet, Copenhagen, Denmark; Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark.
  • Princess Margaret Cancer Centre, University of Toronto, Toronto, Canada.

Abstract

Delta biomarkers that reflect changes in tumour burden over time can support personalised follow-up in head and neck cancer. However, their clinical use can be limited by the need for manual image segmentation. This study externally evaluates a deep learning model for automatic determination of volume change from serial 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) scans to stratify patients by loco-regional outcome. Patient/material and methods: An externally developed deep learning algorithm for tumour segmentation was applied to pre- and post-radiotherapy (RT, with or without concomitant chemoradiotherapy) PET/CT scans of 50 consecutive head and neck cancer patients from The Christie NHS Foundation Trust, UK. The model, originally trained on pre-treatment scans from a different institution, was deployed to derive tumour volumes at both time points. The AI-derived change in tumour volume (ΔPET-Gross tumour volume (GTV)) was calculated for each patient. Kaplan-Meier analysis assessed loco-regional control based on ΔPET-GTV, dichotomised at the cohort median. In a separate secondary analysis confined to the pre‑treatment scans, a radiation oncologist qualitatively evaluated the AI‑generated PET‑GTV contours. Patients with higher ΔPET-GTV (i.e. greater tumour shrinkage) had significantly improved loco-regional control (log-rank p = 0.02). At 2 years, control was 94.1% (95% CI: 83.6-100%) vs. 53.6% (95% CI: 32.2-89.1%). Only one of nine failures occurred in the high ΔPET-GTV group. Clinician review found AI volumes acceptable for planning in 78% of cases. In two cases, the algorithm identified oropharyngeal primaries on pre-treatment PET-CT before clinical identification. Deep learning-derived ΔPET-GTV may support clinically meaningful assessment of post-treatment disease status and risk stratification, offering a scalable alternative to manual segmentation in PET/CT follow-up.

Topics

Deep LearningPositron Emission Tomography Computed TomographyHead and Neck NeoplasmsNeoplasm Recurrence, LocalJournal ArticleValidation Study

Ready to Sharpen Your Edge?

Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.