Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Feb 26;12(3):242.
doi: 10.3390/bioengineering12030242.

Simplatab: An Automated Machine Learning Framework for Radiomics-Based Bi-Parametric MRI Detection of Clinically Significant Prostate Cancer

Dimitrios I Zaridis  1   2   3 , Vasileios C Pezoulas  2 , Eugenia Mylona  1   2 , Charalampos N Kalantzopoulos  1   2 , Nikolaos S Tachos  1   2 , Nikos Tsiknakis  4 , George K Matsopoulos  3 , Daniele Regge  5 , Nikolaos Papanikolaou  6 , Manolis Tsiknakis  7   8 , Kostas Marias  7   8 , Dimitrios I Fotiadis  1   2
Affiliations

Simplatab: An Automated Machine Learning Framework for Radiomics-Based Bi-Parametric MRI Detection of Clinically Significant Prostate Cancer

Dimitrios I Zaridis et al. Bioengineering (Basel). .

Abstract

Background: Prostate cancer (PCa) diagnosis using MRI is often challenged by lesion variability.

Methods: This study introduces Simplatab, an open-source automated machine learning (AutoML) framework designed for, but not limited to, automating the entire machine Learning pipeline to facilitate the detection of clinically significant prostate cancer (csPCa) using radiomics features. Unlike existing AutoML tools such as Auto-WEKA, Auto-Sklearn, ML-Plan, ATM, Google AutoML, and TPOT, Simplatab offers a comprehensive, user-friendly framework that integrates data bias detection, feature selection, model training with hyperparameter optimization, explainable AI (XAI) analysis, and post-training model vulnerabilities detection. Simplatab requires no coding expertise, provides detailed performance reports, and includes robust data bias detection, making it particularly suitable for clinical applications.

Results: Evaluated on a large pan-European cohort of 4816 patients from 12 clinical centers, Simplatab supports multiple machine learning algorithms. The most notable features that differentiate Simplatab include ease of use, a user interface accessible to those with no coding experience, comprehensive reporting, XAI integration, and thorough bias assessment, all provided in a human-understandable format.

Conclusions: Our findings indicate that Simplatab can significantly enhance the usability, accountability, and explainability of machine learning in clinical settings, thereby increasing trust and accessibility for AI non-experts.

Keywords: AutoML; MRI; artificial intelligence; automated machine learning framework; open source; prostate cancer; radiomics.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure A1
Figure A1
Data bias detection by client age group.
Figure A2
Figure A2
Heatmap with the SHAP values (left) and importance of each feature for model decision (right) of the XGBoost model.
Figure A3
Figure A3
Data bias detection by customer gender (male/female).
Figure A4
Figure A4
Heatmap with the SHAP values (left) and the importance of each feature for model decision (right) for the XGBoost model.
Figure 1
Figure 1
Schematic representation of Simplatab AutoML framework.
Figure 2
Figure 2
(A) Desktop app, (B) introduction page, (C) introduction page for individuals with vision impairment, and (D) the parameter selection from the front-end.
Figure 3
Figure 3
Bias assessment using nine metrics with respect to different MR vendors (Siemens, Phillips, General Electric, and Toshiba) and target class (csPCa) for the retrospective and the prospective sets.
Figure 4
Figure 4
AUC-ROC (left) and precision–recall curves (right) for the prospective dataset.
Figure 5
Figure 5
Heatmap plot with the SHAP values for each feature ordered by importance, correlated with the XGBoost outcome, for the external dataset.
Figure 6
Figure 6
Feature importance in the XGBoost model, for the external dataset.
See this image and copyright information in PMC

References

    1. Rebello R.J., Oing C., Knudsen K.E., Loeb S., Johnson D.C., Reiter R.E., Gillessen S., Van der Kwast T., Bristow R.G. Prostate cancer. Nat. Rev. Dis. Primers. 2021;7:9. doi: 10.1038/s41572-020-00243-0. - DOI - PubMed
    1. Greenberg J.W., Koller C.R., Casado C., Triche B.L., Krane L.S. A narrative review of biparametric MRI (bpMRI) implementation on screening, detection, and the overall accuracy for prostate cancer. Ther. Adv. Urol. 2022;14:17562872221096377. doi: 10.1177/17562872221096377. - DOI - PMC - PubMed
    1. Tamada T., Kido A., Yamamoto A., Takeuchi M., Miyaji Y., Moriya T., Sone T. Comparison of Biparametric and Multiparametric MRI for Clinically Significant Prostate Cancer Detection with PI-RADS Version 2.1. J. Magn. Reson. Imaging. 2021;53:283–291. doi: 10.1002/jmri.27283. - DOI - PubMed
    1. Xu L., Zhang G., Shi B., Liu Y., Zou T., Yan W., Xiao Y., Xue H., Feng F., Lei J., et al. Comparison of biparametric and multiparametric MRI in the diagnosis of prostate cancer. Cancer Imaging. 2019;19:90. doi: 10.1186/s40644-019-0274-9. - DOI - PMC - PubMed
    1. Hietikko R., Kilpeläinen T.P., Kenttämies A., Ronkainen J., Ijäs K., Lind K., Marjasuo S., Oksala J., Oksanen O., Saarinen T., et al. Expected impact of MRI-related interreader variability on ProScreen prostate cancer screening trial: A pre-trial validation study. Cancer Imaging. 2020;20:72. doi: 10.1186/s40644-020-00351-w. - DOI - PMC - PubMed

LinkOut - more resources