Deep learning‐based 3D classification of head and neck cancer PET/MRI: Radiologist comparison and Grad‐CAM interpretability
Clinical Physiology and Functional Imaging · 2025
DOI: 10.1111/cpf.70030 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift Clinical Physiology and Functional Imaging, 2025. Verfasst von Joonas Liedes und 6 weiteren Autor:innen. Beteiligte Einrichtung: Turku PET Centre, University of Turku and Turku University Hospital, Turku, Finland. Hauptthemen laut MEDLINE: Deep Learning, Head and Neck Neoplasms, Magnetic Resonance Imaging, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 17 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Sakari Alhopuro Foundation, Cancer Foundation Finland, Sigrid Jusélius Foundation.
Abstract (Originalsprache)
Purpose
To develop and evaluate a three‐dimensional convolutional neural network for automated classification of PET/MRI images in head and neck cancer (HNC) patients, assessing its performance against radiologist interpretation and its potential as a diagnostic aid.
Methods
Data from 202 patients with HNC who underwent 18 F‐FDG PET/MRI were used to train and validate PET‐, MRI‐, and PET/MRI‐based models. Of these data, 101 patients were labelled as positive in terms of having HNC, and 101 patients as negative. An additional test set of 20 patients was also evaluated, where 10 patients were labelled as positive and 10 as negative. The model performance was assessed using sensitivity, specificity, accuracy, and AUC. Grad‐CAM was utilised to improve interpretability and classification results on the test set were compared with a radiologist.
Results
The PET‐based model achieved an AUC of 0.92 on the test set, with an accuracy of 90%, a sensitivity of 100% and a specificity of 80%. PET/MRI and MRI‐based models underperformed relative to the PET‐based model. The radiologist achieved perfect classification accuracy. Analysis of Grad‐CAM showed that the model classifications are based on real areas of interest. In addition, it gave valuable insight into using similar systems in identifying false positive findings.
Conclusion
The PET‐based model demonstrated high sensitivity, indicating its potential as a pre‐screening tool for HNC. However, specificity requires improvement to reduce false‐positive rates. Enhanced datasets and refinement of model architecture will be crucial before clinical adoption. Grad‐CAM provides valuable insights into model decisions, aiding clinical integration.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Turku PET Centre, University of Turku and Turku University Hospital, Turku, Finland.
- Department of Radiology, University of Turku and Turku University Hospital, Turku, Finland.
- Department of Otorhinolaryngology, Turku University Hospital, Turku, Finland.
- Department of Clinical Physiology and Nuclear Medicine, Turku University Hospital, Turku, Finland.
ORCID-Profile: Joonas Liedes, Jussi Hirvonen, Oona Rainio, Sarita Murtojärvi, Simona Malaspina, Riku Klén, Jukka Kemppainen
Förderung
- Sakari Alhopuro Foundation
- Cancer Foundation Finland
- Sigrid Jusélius Foundation
Zitieren
APA
Liedes, J., Hirvonen, J., Rainio, O., Murtojärvi, S., Malaspina, S., Klén, R., & Kemppainen, J. (2025). Deep learning‐based 3D classification of head and neck cancer PET/MRI: Radiologist comparison and Grad‐CAM interpretability. Clinical Physiology and Functional Imaging. https://doi.org/10.1111/cpf.70030
Vancouver
Liedes J, Hirvonen J, Rainio O, Murtojärvi S, Malaspina S, Klén R, et al. Deep learning‐based 3D classification of head and neck cancer PET/MRI: Radiologist comparison and Grad‐CAM interpretability. Clinical Physiology and Functional Imaging. 2025. doi:10.1111/cpf.70030
BibTeX
@article{Liedes2025,
author = {Liedes, Joonas and Hirvonen, Jussi and Rainio, Oona and Murtojärvi, Sarita and Malaspina, Simona and Klén, Riku and Kemppainen, Jukka},
title = {Deep learning‐based 3D classification of head and neck cancer PET/MRI: Radiologist comparison and Grad‐CAM interpretability},
journal = {Clinical Physiology and Functional Imaging},
year = {2025},
doi = {10.1111/cpf.70030}
}
EUVIMED