Should end-to-end deep learning replace handcrafted radiomics?
European Journal of Nuclear Medicine and Molecular Imaging · 2025-10 · 52 (12) · 4360-4363
DOI: 10.1007/s00259-025-07314-y ↗Kurz gefasst
Leserbrief in der Zeitschrift European Journal of Nuclear Medicine and Molecular Imaging, online erschienen am 02.05.2025. Verfasst von Irène Buvat und 6 weiteren Autor:innen. Beteiligte Einrichtung: Institut Curie, PSL University, Inserm, LITO U1288, Orsay, France. irene.buvat@curie.fr. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 13 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
learning.Representation learning involves training a neural network to learn a parsimonious yet comprehensive representation of the useful information present in the images.This information can then be used as latent deep radiomic features to build models corresponding to different classification or prediction tasks.Unlike handcrafted features, not only the values, but the definitions of the features involved in deep radiomics themselves depend on the training data and model architecture used to train a classification or prediction model.While deep learning is gaining ground thanks to the increasing availability of open datasets and shared deep learning models (https://nmmitools.org,https://monai.io),one might ask whether researchers should focus efforts exclusively on deep learning rather than radiomics.This short paper examines the respective positions of handcrafted and end-to-end deep radiomics in relation to key factors to be considered when developing and implementing classification or outcome prediction models.It has been inspired by the content of a moderated debate held during the SNMMI 2023 meeting involving two advocates of handcrafted radiomics and two advocates of deep radiomics.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institut Curie, PSL University, Inserm, LITO U1288, Orsay, France. irene.buvat@curie.fr.
- Department of Electrical and Computer Engineering, University of Massachusetts Lowell, Lowell, MA, USA.
- Department of Biomedical Engineering, Mallinckrodt Institute of Radiology, Washington University in St. Louis, St. Louis, MO, USA.
- Department of Radiology and Nuclear Medicine, University of Maryland Medical Center, Baltimore, MD, USA.
- Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, Canada.
- Departments of Radiology and Physics, University of British Columbia, Vancouver, Canada.
Zitieren
APA
Buvat, I., Dutta, J., Jha, A. K., Siegel, E., Yousefirizi, F., Rahmim, A., & Bradshaw, T. (2025). Should end-to-end deep learning replace handcrafted radiomics?. European Journal of Nuclear Medicine and Molecular Imaging, 52(12), 4360-4363. https://doi.org/10.1007/s00259-025-07314-y
Vancouver
Buvat I, Dutta J, Jha AK, Siegel E, Yousefirizi F, Rahmim A, et al. Should end-to-end deep learning replace handcrafted radiomics?. European Journal of Nuclear Medicine and Molecular Imaging. 2025;52(12):4360-4363. doi:10.1007/s00259-025-07314-y
BibTeX
@article{Buvat2025,
author = {Buvat, Irène and Dutta, Joyita and Jha, Abhinav K and Siegel, Eliot and Yousefirizi, Fereshteh and Rahmim, Arman and Bradshaw, Tyler},
title = {Should end-to-end deep learning replace handcrafted radiomics?},
journal = {European Journal of Nuclear Medicine and Molecular Imaging},
year = {2025},
volume = {52},
number = {12},
pages = {4360--4363},
doi = {10.1007/s00259-025-07314-y}
}
EUVIMED