EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Reproducible Radiomics Features from Multi‐MRI‐Scanner Test–Retest‐Study: Influence on Performance and Generalizability of Models

Markus Wennmann iD, Lukas T Rotkopf, Fabian Bauer iD, Thomas Hielscher, Jessica Kächele, Elias K Mai, Niels Weinhold, Marc-Steffen Raab, Hartmut Goldschmidt, Tim F Weber, Heinz-Peter Schlemmer, Stefan Delorme und 2 weitere

Journal of Magnetic Resonance Imaging · 2025

DOI: 10.1002/jmri.29442 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Magnetic Resonance Imaging, 2025. Verfasst von Markus Wennmann und 13 weiteren Autor:innen. Beteiligte Einrichtung: Division of Radiology, German Cancer Research Center (DKFZ) Heidelberg, Heidelberg, Germany. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Radiomics models trained on data from one center typically show a decline of performance when applied to data from external centers, hindering their introduction into large‐scale clinical practice. Current expert recommendations suggest to use only reproducible radiomics features isolated by multiscanner test–retest experiments, which might help to overcome the problem of limited generalizability to external data.

Purpose

To evaluate the influence of using only a subset of robust radiomics features, defined in a prior in vivo multi‐MRI‐scanner test–retest‐study, on the performance and generalizability of radiomics models. Study Type Retrospective. Population Patients with monoclonal plasma cell disorders. Training set (117 MRIs from center 1); internal test set (42 MRIs from center 1); external test set (143 MRIs from center 2–8). Field Strength/Sequence 1.5T and 3.0T; T1‐weighted turbo spin echo. Assessment The task for the radiomics models was to predict plasma cell infiltration, determined by bone marrow biopsy, noninvasively from MRI. Radiomics machine learning models, including linear regressor, support vector regressor (SVR), and random forest regressor (RFR), were trained on data from center 1, using either all radiomics features, or using only reproducible radiomics features. Models were tested on an internal (center 1) and a multicentric external data set (center 2–8). Statistical Tests Pearson correlation coefficient r and mean absolute error (MAE) between predicted and actual plasma cell infiltration. Fisher's z‐transformation, Wilcoxon signed‐rank test, Wilcoxon rank‐sum test; significance level P < 0.05.

Results

When using only reproducible features compared with all features, the performance of the SVR on the external test set significantly improved ( r = 0.43 vs. r = 0.18 and MAE = 22.6 vs. MAE = 28.2). For the RFR, the performance on the external test set deteriorated when using only reproducible instead of all radiomics features ( r = 0.33 vs. r = 0.44, P = 0.29 and MAE = 21.9 vs. MAE = 20.5, P = 0.10).

Conclusion

Using only reproducible radiomics features improves the external performance of some, but not all machine learning models, and did not automatically lead to an improvement of the external performance of the overall best radiomics model. Level of Evidence 3. Technical Efficacy Stage 2.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingHumansRetrospective StudiesReproducibility of ResultsFemaleMaleMiddle AgedMachine LearningImage Processing, Computer-AssistedAdultAgedImage Interpretation, Computer-AssistedBone MarrowAlgorithmsRadiomics

Stichwörter der Autor:innen

feature selectiongeneralizabilitymachine learningmulticenterradiomicsreproducibility

Autor:innen und Institutionen

  • Division of Radiology, German Cancer Research Center (DKFZ) Heidelberg, Heidelberg, Germany.
  • Diagnostic and Interventional Radiology, University Hospital Heidelberg, Heidelberg, Germany.
  • Division of Biostatistics, German Cancer Research Center (DKFZ) Heidelberg, Heidelberg, Germany.
  • Division of Medical Image Computing, German Cancer Research Center (DKFZ) Heidelberg, Heidelberg, Germany.
  • German Cancer Consortium (DKTK), Partner Site Heidelberg, Heidelberg, Germany.
  • Heidelberg Myeloma Center, Department of Medicine, University Hospital Heidelberg, Heidelberg, Germany.

ORCID-Profile: Markus Wennmann, Fabian Bauer

Zitieren

APA

Wennmann, M., Rotkopf, L. T., Bauer, F., Hielscher, T., Kächele, J., Mai, E. K., Weinhold, N., Raab, M. S., Goldschmidt, H., Weber, T. F., Schlemmer, H. P., Delorme, S., Maier-Hein, K., & Neher, P. (2025). Reproducible Radiomics Features from Multi‐MRI‐Scanner Test–Retest‐Study: Influence on Performance and Generalizability of Models. Journal of Magnetic Resonance Imaging. https://doi.org/10.1002/jmri.29442

Vancouver

Wennmann M, Rotkopf LT, Bauer F, Hielscher T, Kächele J, Mai EK, et al. Reproducible Radiomics Features from Multi‐MRI‐Scanner Test–Retest‐Study: Influence on Performance and Generalizability of Models. Journal of Magnetic Resonance Imaging. 2025. doi:10.1002/jmri.29442

BibTeX
@article{Wennmann2025,
  author = {Wennmann, Markus and Rotkopf, Lukas T and Bauer, Fabian and Hielscher, Thomas and Kächele, Jessica and Mai, Elias K and Weinhold, Niels and Raab, Marc-Steffen and Goldschmidt, Hartmut and Weber, Tim F and Schlemmer, Heinz-Peter and Delorme, Stefan and Maier-Hein, Klaus and Neher, Peter},
  title = {Reproducible Radiomics Features from Multi‐MRI‐Scanner Test–Retest‐Study: Influence on Performance and Generalizability of Models},
  journal = {Journal of Magnetic Resonance Imaging},
  year = {2025},
  doi = {10.1002/jmri.29442}
}
Kostenlos starten →