Utilizing Radiomics of Peri-Lesional Edema in T2-FLAIR Subtraction Digital Images to Distinguish High-Grade Glial Tumors From Brain Metastasis

Overview

Journal J Magn Reson Imaging

Date 2024 Sep 10

PMID 39254002

Authors

Emin Demirel

Okan Dilek

Affiliations

Soon will be listed here.

Abstract

Background: Differentiating high-grade glioma (HGG) and isolated brain metastasis (BM) is important for determining appropriate treatment. Radiomics, utilizing quantitative imaging features, offers the potential for improved diagnostic accuracy in this context.

Purpose: To differentiate high-grade (grade 4) glioma and BM using machine learning models from radiomics data obtained from T2-FLAIR digital subtraction images and the peritumoral edema area.

Study Type: Retrospective.

Population: The study included 1287 patients. Of these, 602 were male and 685 were female. Of the 788 HGG patients included in the study, 702 had solitary masses. Of the 499 BM patients included in the study, 112 had solitary masses. Initially, the model was developed and tested on solitary masses. Subsequently, the model was developed and tested separately for all patients (solitary and multiple masses).

Field Strength/sequence: Axial T2-weighted fast spin-echo sequence (T2WI) and T2-weighted fluid-attenuated inversion recovery sequence (T2-FLAIR), using 1.5-T and 3.0-T scanners.

Assessment: Radiomic features were extracted from digitally subtracted T2-FLAIR images in the area of peritumoral edema. The maximum relevance-minimum redundancy (mRMR) method was then used for dimensionality reduction. The naive Bayes algorithm was used in model development. The interpretability of the model was explored using SHapley Additive exPlanations (SHAP).

Statistical Tests: Chi-square test, one-way analysis of variance, and Kruskal-Wallis test were performed. The P values <0.05 were considered statistically significant. The performance metrics include area under curve (AUC), sensitivity (SENS), and specificity (SPEC).

Results: The mean age of HGG patients was 61.4 ± 13.2 years and 61.7 ± 12.2 years for BM patients. In the external validation cohort, the model achieved AUC: 0.991, SENS: 0.983, and SPEC: 0.922. The external cohort results for patients with solitary lesions were AUC: 0.987, SENS: 0.950, and SPEC: 0.922.

Data Conclusion: The artificial intelligence model, developed with radiomics data from the peritumoral edema area in T2-FLAIR digital subtraction images, might be able to differentiate isolated BM from HGG.

Evidence Level: 3 TECHNICAL EFFICACY: Stage 2.

References

Bakas S, Sako C, Akbari H, Bilello M, Sotiras A, Shukla G . The University of Pennsylvania glioblastoma (UPenn-GBM) cohort: advanced MRI, clinical, genomics, & radiomics. Sci Data. 2022; 9(1):453. PMC: 9338035. DOI: 10.1038/s41597-022-01560-7. View

Gillies R, Kinahan P, Hricak H . Radiomics: Images Are More than Pictures, They Are Data. Radiology. 2015; 278(2):563-77. PMC: 4734157. DOI: 10.1148/radiol.2015151169. View

Lemercier P, Paz Maya S, Patrie J, Flors L, Leiva-Salinas C . Gradient of apparent diffusion coefficient values in peritumoral edema helps in differentiation of glioblastoma from solitary metastatic lesions. AJR Am J Roentgenol. 2014; 203(1):163-9. DOI: 10.2214/AJR.13.11186. View

Shin I, Kim H, Ahn S, Sohn B, Bae S, Park J . Development and Validation of a Deep Learning-Based Model to Distinguish Glioblastoma from Solitary Brain Metastasis Using Conventional MR Images. AJNR Am J Neuroradiol. 2021; 42(5):838-844. PMC: 8115383. DOI: 10.3174/ajnr.A7003. View

Trembath D, Davis E, Rao S, Bradler E, Saada A, Midkiff B . Brain Tumor Microenvironment and Angiogenesis in Melanoma Brain Metastases. Front Oncol. 2021; 10:604213. PMC: 7860978. DOI: 10.3389/fonc.2020.604213. View

Wurtemberger U, Rau A, Diebold M, Becker L, Hohenhaus M, Beck J . Advanced diffusion MRI provides evidence for altered axonal microstructure and gradual peritumoral infiltration in GBM in comparison to brain metastases. Clin Neuroradiol. 2024; 34(3):703-711. PMC: 11339137. DOI: 10.1007/s00062-024-01416-0. View

Bae S, An C, Ahn S, Kim H, Han K, Kim S . Robust performance of deep learning for distinguishing glioblastoma from single brain metastasis using radiomic features: model development and validation. Sci Rep. 2020; 10(1):12110. PMC: 7374174. DOI: 10.1038/s41598-020-68980-6. View

Riahi Samani Z, Parker D, Wolf R, Hodges W, Brem S, Verma R . Distinct tumor signatures using deep learning-based characterization of the peritumoral microenvironment in glioblastomas and brain metastases. Sci Rep. 2021; 11(1):14469. PMC: 8280204. DOI: 10.1038/s41598-021-93804-6. View

Lee E, Terbrugge K, Mikulis D, Choi D, Bae J, Lee S . Diagnostic value of peritumoral minimum apparent diffusion coefficient for differentiation of glioblastoma multiforme from solitary metastatic lesions. AJR Am J Roentgenol. 2010; 196(1):71-6. DOI: 10.2214/AJR.10.4752. View

10.

van Griethuysen J, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V . Computational Radiomics System to Decode the Radiographic Phenotype. Cancer Res. 2017; 77(21):e104-e107. PMC: 5672828. DOI: 10.1158/0008-5472.CAN-17-0339. View

11.

Wurtemberger U, Rau A, Reisert M, Kellner E, Diebold M, Erny D . Differentiation of Perilesional Edema in Glioblastomas and Brain Metastases: Comparison of Diffusion Tensor Imaging, Neurite Orientation Dispersion and Density Imaging and Diffusion Microstructure Imaging. Cancers (Basel). 2023; 15(1). PMC: 9817519. DOI: 10.3390/cancers15010129. View

12.

Zhou M, Scott J, Chaudhury B, Hall L, Goldgof D, Yeom K . Radiomics in Brain Tumor: Image Assessment, Quantitative Feature Descriptors, and Machine-Learning Approaches. AJNR Am J Neuroradiol. 2017; 39(2):208-216. PMC: 5812810. DOI: 10.3174/ajnr.A5391. View

13.

Berghoff A, Schur S, Fureder L, Gatterbauer B, Dieckmann K, Widhalm G . Descriptive statistical analysis of a real life cohort of 2419 patients with brain metastases of solid cancers. ESMO Open. 2016; 1(2):e000024. PMC: 5070252. DOI: 10.1136/esmoopen-2015-000024. View

14.

Cho N, Sanvito F, Le V, Oshima S, Teraishi A, Yao J . Quantification of T2-FLAIR Mismatch in Nonenhancing Diffuse Gliomas Using Digital Subtraction. AJNR Am J Neuroradiol. 2024; 45(2):188-197. PMC: 11285991. DOI: 10.3174/ajnr.A8094. View

15.

Price S, Young A, Scotton W, Ching J, Mohsen L, Boonzaier N . Multimodal MRI can identify perfusion and metabolic changes in the invasive margin of glioblastomas. J Magn Reson Imaging. 2015; 43(2):487-94. PMC: 5008200. DOI: 10.1002/jmri.24996. View

16.

Blanchet L, Krooshof P, Postma G, Idema A, Goraj B, Heerschap A . Discrimination between metastasis and glioblastoma multiforme based on morphometric analysis of MR images. AJNR Am J Neuroradiol. 2010; 32(1):67-73. PMC: 7964969. DOI: 10.3174/ajnr.A2269. View

17.

Byrnes T, Barrick T, Bell B, Clark C . Diffusion tensor imaging discriminates between glioblastoma and cerebral metastases in vivo. NMR Biomed. 2010; 24(1):54-60. DOI: 10.1002/nbm.1555. View

18.

Peng H, Long F, Ding C . Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell. 2005; 27(8):1226-38. DOI: 10.1109/TPAMI.2005.159. View

19.

Artzi M, Bressler I, Ben Bashat D . Differentiation between glioblastoma, brain metastasis and subtypes using radiomics analysis. J Magn Reson Imaging. 2019; 50(2):519-528. DOI: 10.1002/jmri.26643. View

20.

Yaniv Z, Lowekamp B, Johnson H, Beare R . SimpleITK Image-Analysis Notebooks: a Collaborative Environment for Education and Reproducible Research. J Digit Imaging. 2017; 31(3):290-303. PMC: 5959828. DOI: 10.1007/s10278-017-0037-8. View