Reproducibility and discriminative power of MRI liver radiomics: Impact of deep learning-based image…

AI / informaticsEuropean journal of radiology· Aug 2026

Reproducibility and discriminative power of MRI liver radiomics: Impact of deep learning-based image reconstruction.

Louison Rey, Navid Rabbani, Benoit Chauveau … Benoit Magnin

Read paper

Medical Imaging AIAI / informaticsQ1IF 4.0

Liver MRI radiomic reproducibility was similar with and without deep learning image reconstruction

Reproducibility and discriminative power of MRI liver radiomics: Impact of deep learning-based image reconstruction.

Louison Rey … Benoit Magnin

European journal of radiology · Aug 2026 · Q1 in General Medicine

Background

While Deep Learning-based Image Reconstruction (DLIR) is increasingly used to improve MRI quality, its influence on radiomic stability remains underexplored.

Purpose

This study aimed to assess the impact of DLIR on the reproducibility and discriminative power of radiomic features in liver MRI.

Methods

In this retrospective study, 95 patients with malignant liver lesions underwent 1.5 T MRI (T2, T2FS, and Diffusion).

n = 95 patients

Results

reproducibility of features was about the same with DLIR as without

OR 0.86 (95% CI 0.65 to 1.14)

null 1

0.65

1.14

CI crosses the null - not significant

More results

Inter-observer reproducibility remained low across all reconstructions, particularly for intensity features.

Classifier performance for tissue differentiation remained comparable between reconstructions.

A slight decrease (2-7%) in the percentage of discriminative features was observed with DLIR, suggesting a mild smoothing effect on subtle textures.

“

Conclusion · 1 of 2

DLIR does not significantly improve or degrade the reproducibility of radiomics in liver MRI. However, DLIR preserves the essential signatures required for tissue discrimination.

Conclusion · 2 of 2

These results support the clinical integration of DLIR in radiomic workflows, confirming that it can be used without compromising the reliability of quantitative imaging biomarkers.

Reproducibility and discriminative power of MRI liver radiomics: Impact of deep learning-based image reconstruction.

Reproducibility and discriminative power of MRI liver radiomics: Impact of deep learning-based image reconstruction.

Related papers