Settings
  • Light
  • Dark
  • Auto
Select Page

Radiomics as a research topic in radiology is certainly a promising field. Over the last years, many publications have shown promising results, showing that image analysis using a radiomics approach could potentially help guide clinical decision making by allowing for accurate, non-invasive diagnosis and prognosis.

However, despite the large number of publications, we see only little to no translation of such tools into clinical routine. There may be several reasons for this perceived gap, but among other things, we feel that the lack of reproducibility studies combined with the sometimes sub-optimal reporting of methods and results in publications, and the fact that little prospective evidence to support the benefit of such techniques in clinical routine is available, may be key contributing factors.

With this editorial, we wanted to highlight some of the key considerations that should be taken into account for future radiomics studies. By no means do we intend to belittle the results of any published studies or call into question the validity of the technique itself, but instead want to highlight that it might be the right time to take the next step. Moving past feasibility studies towards clinical imaging trials with relevant endpoints will certainly require a tremendous amount of work. However, if we really want to put radiomics to work in order to serve our patients and improve their outcomes, it will be critical to take up that task.

Key points

  • Although radiomics is potentially a promising approach to analyze medical image data, many pitfalls need to be considered to avoid a reproducibility crisis.
  • There is a translation gap in radiomics research, with many studies being published but so far little to no translation into clinical practice.
  • Going forward, more studies with higher levels of evidence are needed, ideally also focusing on prospective studies with relevant clinical impact.

Article: A decade of radiomics research: are images really data or just patterns in the noise?

Authors: Daniel Pinto dos Santos, Matthias Dietzel & Bettina Baessler

Latest posts

Welcome to the blog on Artificial Intelligence of the European Society of Radiology

This blog aims at bringing educational and critical perspectives on AI to readers. It should help imaging professionals to learn and keep up to date with the technologies being developed in this rapidly evolving field.