EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Prognostic modeling in head and neck cancer: deep learning or handcrafted radiomics?

Varsha Gouthamchand iD, Louise A F Fonseca, Frank J P Hoebers, Rianne Fijten iD, Andre Dekker iD, Leonard Wee iD, Hannah Mary Thomas T iD

BJR|Artificial Intelligence · 2025

DOI: 10.1093/bjrai/ubaf008 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift BJR|Artificial Intelligence, 2025. Verfasst von Varsha Gouthamchand und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiation Oncology (Maastro), GROW Research Institute for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht,…. Die Arbeit nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: India and the Netherlands—TRAIN project, Stichting Hanarth Fonds and the Proton Therapy Research Infrastructure—ProTRAIT project, Dutch Cancer Society.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Head and neck squamous cell carcinoma (HNSCC) presents a complex clinical challenge due to its heterogeneous nature and diverse treatment responses. This review critically appraises the performance of handcrafted radiomics (HC) and deep learning (DL) models in prognosticating outcomes in HNSCC patients treated with (chemo)-radiotherapy. The focus was on methodological rigor, performance metrics, and long-term outcome reporting. A comprehensive literature search was conducted up to May 2023, identifying 23 eligible studies that met the inclusion criteria. We analyzed methodological variability and predictive performance metrics of both models for outcomes including overall survival, loco-regional recurrence, and distant metastasi. Our findings concluded that DL models exhibited slightly superior performance metrics compared to HC models, particularly in outcome prediction. However, the highest methodological quality was noted predominantly in HC studies. Substantial variability in methodology, outcome definitions, and performance metrics was observed, highlighting the need for standardization. While DL models show potential for improved prognostic performance, the methodological robustness in HC studies underscores their reliability. This emphasizes the necessity for methodological improvements, including pre-registration of protocols and clinical utility assessments, to enhance the reliability and applicability of radiomics-based prognostic models in clinical practice.

Schlagwörter

Stichwörter der Autor:innen

deep learninghead and neck cancerprognosisquality checklistradiomicsreview

Autor:innen und Institutionen

  • Department of Radiation Oncology (Maastro), GROW Research Institute for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht, 6229ER, The Netherlands.
  • Academic Center for General Practice, Department of Public Health and Primary Care, KU Leuven, Leuven, 3000, Belgium.
  • Brightlands Institute for Smart Society, Faculty of Science and Engineering, Maastricht University, Heerlen, 6411CR, The Netherlands.
  • Quantitative Imaging Research and Artificial Intelligence Lab, Department of Radiation Oncology, Unit II, Christian Medical College, Vellore, Tamil Nadu, 632004, India.

ORCID-Profile: Varsha Gouthamchand, Rianne Fijten, Andre Dekker, Leonard Wee, Hannah Mary Thomas T

Förderung

  • India and the Netherlands—TRAIN project
  • Stichting Hanarth Fonds and the Proton Therapy Research Infrastructure—ProTRAIT project
  • Dutch Cancer Society

Zitieren

APA

Gouthamchand, V., Fonseca, L. A. F., Hoebers, F. J. P., Fijten, R., Dekker, A., Wee, L., & Thomas T, H. M. (2025). Prognostic modeling in head and neck cancer: deep learning or handcrafted radiomics?. BJR|Artificial Intelligence. https://doi.org/10.1093/bjrai/ubaf008

Vancouver

Gouthamchand V, Fonseca LAF, Hoebers FJP, Fijten R, Dekker A, Wee L, et al. Prognostic modeling in head and neck cancer: deep learning or handcrafted radiomics?. BJR|Artificial Intelligence. 2025. doi:10.1093/bjrai/ubaf008

BibTeX
@article{Gouthamchand2025,
  author = {Gouthamchand, Varsha and Fonseca, Louise A F and Hoebers, Frank J P and Fijten, Rianne and Dekker, Andre and Wee, Leonard and Thomas T, Hannah Mary},
  title = {Prognostic modeling in head and neck cancer: deep learning or handcrafted radiomics?},
  journal = {BJR|Artificial Intelligence},
  year = {2025},
  doi = {10.1093/bjrai/ubaf008}
}
Kostenlos starten →