Impact of SUSAN Denoising and ComBat Harmonization on Machine Learning Model Performance for Malignant Brain Neoplasms

References

1. 1.↵
   1. Bathla G,
   2. Dhruba DD,
   3. Soni N

   , et al. AI-based classification of three common malignant tumors in neuro-oncology: a multi-institutional comparison of machine learning and deep learning methods. J Neuroradiol 2024;51:258–64 doi:10.1016/j.neurad.2023.08.007 pmid:37652263

   CrossRefPubMed
2. 2.↵
   1. Bathla G,
   2. Priya S,
   3. Liu Y, et al

   . Radiomics-based differentiation between glioblastoma and primary central nervous system lymphoma: a comparison of diagnostic performance across different MRI sequences and machine learning techniques. Eur Radiol 2021;31:8703–13 doi:10.1007/s00330-021-07845-6 pmid:33890149

   CrossRefPubMed
3. 3.↵
   1. Priya S,
   2. Liu Y,
   3. Ward C, et al

   . Radiomic based machine learning performance for a three class problem in neuro-oncology: time to test the waters? Cancers (Basel) 2021;13:2568 doi:10.3390/cancers13112568 pmid:34073840

   CrossRefPubMed
4. 4.↵
   1. Soni N,
   2. Priya S,
   3. Bathla G

   . Texture analysis in cerebral gliomas: a review of the literature. AJNR Am J Neuroradiol 2019;40:928–34 doi:10.3174/ajnr.A6075 pmid:31122918

   Abstract/FREE Full Text
5. 5.↵
   1. Joo B,
   2. Ahn SS,
   3. An C, et al

   . Fully automated radiomics-based machine learning models for multiclass classification of single brain tumors: glioblastoma, lymphoma, and metastasis. J Neuroradiol 2023;50:388–95 doi:10.1016/j.neurad.2022.11.001 pmid:36370829

   CrossRefPubMed
6. 6.↵
   1. Bologna M,
   2. Corino V,
   3. Mainardi L

   . Technical note: virtual phantom analyses for preprocessing evaluation and detection of a robust feature set for MRI-radiomics of the brain. Med Phys 2019;46:5116–23 doi:10.1002/mp.13834 pmid:31539450

   CrossRefPubMed
7. 7.↵
   1. Mayerhoefer ME,
   2. Szomolanyi P,
   3. Jirak D, et al

   . Effects of MRI acquisition parameter variations and protocol heterogeneity on the results of texture analysis and pattern discrimination: an application-oriented study. Med Phys 2009;36:1236–43 doi:10.1118/1.3081408 pmid:19472631

   CrossRefPubMed
8. 8.↵
   1. Buch K,
   2. Kuno H,
   3. Qureshi MM, et al

   . Quantitative variations in texture analysis features dependent on MRI scanning parameters: a phantom model. J Appl Clin Med Phys 2018;19:253–64 doi:10.1002/acm2.12482 pmid:30369010

   CrossRefPubMed
9. 9.↵
   1. Lee J,
   2. Steinmann A,
   3. Ding Y, et al

   . Radiomics feature robustness as measured using an MRI phantom. Sci Rep 2021;11:3973 doi:10.1038/s41598-021-83593-3 pmid:33597610

   CrossRefPubMed
10. 10.↵
    1. Orlhac F,
    2. Lecler A,
    3. Savatovski J, et al

    . How can we combat multicenter variability in MR radiomics? Validation of a correction procedure. Eur Radiol 2021;31:2272–80 doi:10.1007/s00330-020-07284-9 pmid:32975661

    CrossRefPubMed
11. 11.↵
    1. Li Y,
    2. Ammari S,
    3. Balleyguier C, et al

    . Impact of preprocessing and harmonization methods on the removal of scanner effects in brain MRI radiomic features. Cancers (Basel) 2021;13:3000 doi:10.3390/cancers13123000 pmid:34203896

    CrossRefPubMed
12. 12.↵
    1. Um H,
    2. Tixier F,
    3. Bermudez D, et al

    . Impact of image preprocessing on the scanner dependence of multi-parametric MRI radiomic features and covariate shift in multi-institutional glioblastoma datasets. Phys Med Biol 2019;64:165011 doi:10.1088/1361-6560/ab2f44 pmid:31272093

    CrossRefPubMed
13. 13.↵
    1. Moradmand H,
    2. Aghamiri SM,
    3. Ghaderi R

    . Impact of image preprocessing methods on reproducibility of radiomic features in multimodal magnetic resonance imaging in glioblastoma. J Appl Clin Med Phys 2020;21:179–90 doi:10.1002/acm2.12795 pmid:31880401

    CrossRefPubMed
14. 14.↵
    1. Smith SM,
    2. Brady JM

    . SUSAN: a new approach to low level image processing. Int J Comput Vis 1997;23:45–78 doi:10.1023/A:1007963824710

    CrossRefPubMed
15. 15.↵
    1. Stamoulou E,
    2. Manikio GC,
    3. Tsiknakis M, et al

    . ComBat harmonization for multicenter MRI based radiomics features. In: Proceedings of the 2021 IEEE International Conference on Imaging Systems and Techniques (IST). August 24-25, 2021. New York, New York doi:10.1109/IST50367.2021.9745836

    CrossRef
16. 16.↵
    1. Orlhac F,
    2. Eertink JJ,
    3. Cottereau AS, et al

    . A guide to ComBat harmonization of imaging biomarkers in multicenter studies. J Nucl Med 2022;63:172–79 doi:10.2967/jnumed.121.262464 pmid:34531263

    Abstract/FREE Full Text
17. 17.↵
    1. Yin Y,
    2. Zhang X,
    3. Williams R, et al

    . LOGISMOS–layered optimal graph image segmentation of multiple objects and surfaces: cartilage segmentation in the knee joint. IEEE Trans Med Imaging 2010;29:2023–37 doi:10.1109/TMI.2010.2058861 pmid:20643602

    CrossRefPubMedWeb of Science
18. 18.↵
    1. van Griethuysen JJM,
    2. Fedorov A,
    3. Parmar C, et al

    . Computational radiomics system to decode the radiographic phenotype. Cancer Res 2017;77:e104–07 doi:10.1158/0008-5472.CAN-17-0339 pmid:29092951

    Abstract/FREE Full Text
19. 19.↵
    1. Fortin JP,
    2. Parker D,
    3. Tunç B, et al

    . Harmonization of multi-site diffusion tensor imaging data. Neuroimage 2017;161:149–170 doi:10.1016/j.neuroimage.2017.08.047 pmid:28826946

    CrossRefPubMed
20. 20.↵
    1. Bathla G,
    2. Dhruba DD,
    3. Liu Y, et al

    . Differentiation between glioblastoma and metastatic disease on conventional MRI imaging using 3D-convolutional neural networks: model development and validation. Acad Radiol 2024;31:2041–49 doi:10.1016/j.acra.2023.10.044

    CrossRef
21. 21.↵
    1. Hand DJ,
    2. Till RJ

    . A simple generalisation of the area under the ROC curve for multiple class classification problems. Machine Learning 2001;45:171–86 doi:10.1023/A:1010920819831

    CrossRef
22. 22.↵
    R. Team. R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing; 2014
23. 23.↵
    1. Ford J,
    2. Dogan N,
    3. Young L, et al

    . Quantitative radiomics: impact of pulse sequence parameter selection on MRI-based textural features of the brain. Contrast Media Mol Imaging 2018;2018:1729071 doi:10.1155/2018/172907]1

    CrossRefPubMed
24. 24.↵
    1. Carré A,
    2. Klausner G,
    3. Edjlali M, et al

    . Standardization of brain MR images across machines and protocols: bridging the gap for MRI-based radiomics. Sci Rep 2020;10:12340 doi:10.1038/s41598-020-69298-z pmid:32704007

    CrossRefPubMed
25. 25.↵
    1. Salome P,
    2. Sforazzini F,
    3. Grugnara G, et al

    . MR intensity normalization methods impact sequence specific radiomics prognostic model performance in primary and recurrent high-grade glioma. Cancers (Basel) 2023;15:965 doi:10.3390/cancers15030965 pmid:36765922

    CrossRefPubMed
26. 26.↵
    1. Cackowski S,
    2. Barber E,
    3. Christen T

    . comBat versus cycleGAN for multi-center MR images harmonization. 2021. https://www.semanticscholar.org/paper/comTable. Accessed February 15, 2024
27. 27.↵
    1. Mali SA,
    2. Ibrahim A,
    3. Woodruff HC

    , et al. Making radiomics more reproducible across scanner and imaging protocol variations: a review of harmonization methods. J Pers Med 2021;11:842 doi:10.3390/jpm11090842 pmid:34575619

    CrossRefPubMed