Open-radiomics: a collection of standardized datasets and a technical protocol for reproducible radiomics machine learning pipelines

Abstract Background As an important branch of machine learning pipelines in medical imaging, radiomics faces two major challenges namely reproducibility and accessibility. In this work, we introduce open-radiomics, a set of radiomics datasets along with a comprehensive radiomics pipeline based on ou...

Full description

Saved in:
Bibliographic Details
Main Authors: Khashayar Namdar, Matthias W. Wagner, Birgit B. Ertl-Wagner, Farzad Khalvati
Format: Article
Language:English
Published: BMC 2025-08-01
Series:BMC Medical Imaging
Subjects:
Online Access:https://doi.org/10.1186/s12880-025-01855-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849332194167750656
author Khashayar Namdar
Matthias W. Wagner
Birgit B. Ertl-Wagner
Farzad Khalvati
author_facet Khashayar Namdar
Matthias W. Wagner
Birgit B. Ertl-Wagner
Farzad Khalvati
author_sort Khashayar Namdar
collection DOAJ
description Abstract Background As an important branch of machine learning pipelines in medical imaging, radiomics faces two major challenges namely reproducibility and accessibility. In this work, we introduce open-radiomics, a set of radiomics datasets along with a comprehensive radiomics pipeline based on our proposed technical protocol to investigate the effects of radiomics feature extraction on the reproducibility of the results. Methods We curated large-scale radiomics datasets based on three open-source datasets; BraTS 2020 for high-grade glioma (HGG) versus low-grade glioma (LGG) classification and survival analysis, BraTS 2023 for O6-methylguanine-DNA methyltransferase (MGMT) classification, and non-small cell lung cancer (NSCLC) survival analysis from the Cancer Imaging Archive (TCIA). We used the BraTS 2020 open-source Magnetic Resonance Imaging (MRI) dataset to demonstrate how our proposed technical protocol could be utilized in radiomics-based studies. The cohort includes 369 adult patients with brain tumors (76 LGG, and 293 HGG). Using PyRadiomics library for LGG vs. HGG classification, we created 288 radiomics datasets; the combinations of 4 MRI sequences, 3 binWidths, 6 image normalization methods, and 4 tumor subregions. We used Random Forest classifiers, and for each radiomics dataset, we repeated the training-validation-test (60%/20%/20%) experiment with different data splits and model random states 100 times (28,800 test results) and calculated the Area Under the Receiver Operating Characteristic Curve (AUROC). Results Unlike binWidth and image normalization, the tumor subregion and imaging sequence significantly affected performance of the models. T1 contrast-enhanced sequence and the union of Necrotic and the non-enhancing tumor core subregions resulted in the highest AUROCs (average test AUROC 0.951, 95% confidence interval of (0.949, 0.952)). Although several settings and data splits (28 out of 28800) yielded test AUROC of 1, they were irreproducible. Conclusions Our experiments demonstrate the sources of variability in radiomics pipelines (e.g., tumor subregion) can have a significant impact on the results, which may lead to superficial perfect performances that are irreproducible. Clinical trial number Not applicable.
format Article
id doaj-art-e6071b010297412fa8fc744a5507fec7
institution Kabale University
issn 1471-2342
language English
publishDate 2025-08-01
publisher BMC
record_format Article
series BMC Medical Imaging
spelling doaj-art-e6071b010297412fa8fc744a5507fec72025-08-20T03:46:17ZengBMCBMC Medical Imaging1471-23422025-08-0125111810.1186/s12880-025-01855-2Open-radiomics: a collection of standardized datasets and a technical protocol for reproducible radiomics machine learning pipelinesKhashayar Namdar0Matthias W. Wagner1Birgit B. Ertl-Wagner2Farzad Khalvati3Department of Diagnostic & Interventional Radiology, The Hospital for Sick Children (SickKids)Department of Diagnostic & Interventional Radiology, The Hospital for Sick Children (SickKids)Department of Diagnostic & Interventional Radiology, The Hospital for Sick Children (SickKids)Department of Diagnostic & Interventional Radiology, The Hospital for Sick Children (SickKids)Abstract Background As an important branch of machine learning pipelines in medical imaging, radiomics faces two major challenges namely reproducibility and accessibility. In this work, we introduce open-radiomics, a set of radiomics datasets along with a comprehensive radiomics pipeline based on our proposed technical protocol to investigate the effects of radiomics feature extraction on the reproducibility of the results. Methods We curated large-scale radiomics datasets based on three open-source datasets; BraTS 2020 for high-grade glioma (HGG) versus low-grade glioma (LGG) classification and survival analysis, BraTS 2023 for O6-methylguanine-DNA methyltransferase (MGMT) classification, and non-small cell lung cancer (NSCLC) survival analysis from the Cancer Imaging Archive (TCIA). We used the BraTS 2020 open-source Magnetic Resonance Imaging (MRI) dataset to demonstrate how our proposed technical protocol could be utilized in radiomics-based studies. The cohort includes 369 adult patients with brain tumors (76 LGG, and 293 HGG). Using PyRadiomics library for LGG vs. HGG classification, we created 288 radiomics datasets; the combinations of 4 MRI sequences, 3 binWidths, 6 image normalization methods, and 4 tumor subregions. We used Random Forest classifiers, and for each radiomics dataset, we repeated the training-validation-test (60%/20%/20%) experiment with different data splits and model random states 100 times (28,800 test results) and calculated the Area Under the Receiver Operating Characteristic Curve (AUROC). Results Unlike binWidth and image normalization, the tumor subregion and imaging sequence significantly affected performance of the models. T1 contrast-enhanced sequence and the union of Necrotic and the non-enhancing tumor core subregions resulted in the highest AUROCs (average test AUROC 0.951, 95% confidence interval of (0.949, 0.952)). Although several settings and data splits (28 out of 28800) yielded test AUROC of 1, they were irreproducible. Conclusions Our experiments demonstrate the sources of variability in radiomics pipelines (e.g., tumor subregion) can have a significant impact on the results, which may lead to superficial perfect performances that are irreproducible. Clinical trial number Not applicable.https://doi.org/10.1186/s12880-025-01855-2RadiomicsOpen-sourceDatasetBrain cancerReproducibility
spellingShingle Khashayar Namdar
Matthias W. Wagner
Birgit B. Ertl-Wagner
Farzad Khalvati
Open-radiomics: a collection of standardized datasets and a technical protocol for reproducible radiomics machine learning pipelines
BMC Medical Imaging
Radiomics
Open-source
Dataset
Brain cancer
Reproducibility
title Open-radiomics: a collection of standardized datasets and a technical protocol for reproducible radiomics machine learning pipelines
title_full Open-radiomics: a collection of standardized datasets and a technical protocol for reproducible radiomics machine learning pipelines
title_fullStr Open-radiomics: a collection of standardized datasets and a technical protocol for reproducible radiomics machine learning pipelines
title_full_unstemmed Open-radiomics: a collection of standardized datasets and a technical protocol for reproducible radiomics machine learning pipelines
title_short Open-radiomics: a collection of standardized datasets and a technical protocol for reproducible radiomics machine learning pipelines
title_sort open radiomics a collection of standardized datasets and a technical protocol for reproducible radiomics machine learning pipelines
topic Radiomics
Open-source
Dataset
Brain cancer
Reproducibility
url https://doi.org/10.1186/s12880-025-01855-2
work_keys_str_mv AT khashayarnamdar openradiomicsacollectionofstandardizeddatasetsandatechnicalprotocolforreproducibleradiomicsmachinelearningpipelines
AT matthiaswwagner openradiomicsacollectionofstandardizeddatasetsandatechnicalprotocolforreproducibleradiomicsmachinelearningpipelines
AT birgitbertlwagner openradiomicsacollectionofstandardizeddatasetsandatechnicalprotocolforreproducibleradiomicsmachinelearningpipelines
AT farzadkhalvati openradiomicsacollectionofstandardizeddatasetsandatechnicalprotocolforreproducibleradiomicsmachinelearningpipelines