Advancing noninvasive glioma classification with diffusion radiomics: Exploring the impact of signal intensity normalization

Martha Foltyn-Dumitru; Marianne Schell; Felix Sahm; Tobias Kessler; Wolfgang Wick; Martin Bendszus; Aditya Rastogi; Gianluca Brugnara; Philipp Vollmuth

doi:10.1093/noajnl/vdae043

Advancing noninvasive glioma classification with diffusion radiomics: Exploring the impact of signal intensity normalization

Neurooncol Adv. 2024 Mar 22;6(1):vdae043. doi: 10.1093/noajnl/vdae043. eCollection 2024 Jan-Dec.

Authors

Martha Foltyn-Dumitru^{1

2}, Marianne Schell^{1

2}, Felix Sahm^{3

4}, Tobias Kessler^{5

6}, Wolfgang Wick^{5

6}, Martin Bendszus¹, Aditya Rastogi^{1

2}, Gianluca Brugnara^{1

2}, Philipp Vollmuth^{1

2

7}

Affiliations

¹ Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany.
² Division for Computational Neuroimaging, Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany.
³ Department of Neuropathology, Heidelberg University Hospital, Heidelberg, Germany.
⁴ Clinical Cooperation Unit Neuropathology, German Cancer Consortium (DKTK), German Cancer Research Center (DKFZ), Heidelberg, Germany.
⁵ Department of Neurology and Neurooncology Program, Heidelberg University Hospital, Heidelberg University, Heidelberg, Germany.
⁶ Clinical Cooperation Unit Neurooncology, German Cancer Research Center (DKFZ), Heidelberg, Germany.
⁷ Division for Computational Radiology & Clinical AI, Department of Neuroradiology, Bonn University Hospital, Bonn, Germany.

Abstract

Background: This study investigates the influence of diffusion-weighted Magnetic Resonance Imaging (DWI-MRI) on radiomic-based prediction of glioma types according to molecular status and assesses the impact of DWI intensity normalization on model generalizability.

Methods: Radiomic features, compliant with image biomarker standardization initiative standards, were extracted from preoperative MRI of 549 patients with diffuse glioma, known IDH, and 1p19q-status. Anatomical sequences (T1, T1c, T2, FLAIR) underwent N4-Bias Field Correction (N4) and WhiteStripe normalization (N4/WS). Apparent diffusion coefficient (ADC) maps were normalized using N4 or N4/z-score. Nine machine-learning algorithms were trained for multiclass prediction of glioma types (IDH-mutant 1p/19q codeleted, IDH-mutant 1p/19q non-codeleted, IDH-wild type). Four approaches were compared: Anatomical, anatomical + ADC naive, anatomical + ADC N4, and anatomical + ADC N4/z-score. The University of California San Francisco (UCSF)-glioma dataset (n = 409) was used for external validation.

Results: Naïve-Bayes algorithms yielded overall the best performance on the internal test set. Adding ADC radiomics significantly improved AUC from 0.79 to 0.86 (P = .011) for the IDH-wild-type subgroup, but not for the other 2 glioma subgroups (P > .05). In the external UCSF dataset, the addition of ADC radiomics yielded a significantly higher AUC for the IDH-wild-type subgroup (P ≤ .001): 0.80 (N4/WS anatomical alone), 0.81 (anatomical + ADC naive), 0.81 (anatomical + ADC N4), and 0.88 (anatomical + ADC N4/z-score) as well as for the IDH-mutant 1p/19q non-codeleted subgroup (P < .012 each).

Conclusions: ADC radiomics can enhance the performance of conventional MRI-based radiomic models, particularly for IDH-wild-type glioma. The benefit of intensity normalization of ADC maps depends on the type and context of the used data.

Keywords: IDH mutation; diffusion magnetic resonance imaging; genotype; glioma; magnetic resonance imaging.