Background
This study investigates the influence of diffusion-weighted MRI (DWI) 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 IBSI 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-wildtype). Four approaches were compared: anatomical, anatomical + ADC naive, anatomical + ADC N4, and anatomical + ADC N4/z-score. The 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-wildtype subgroup, but not for the other two glioma subgroups (p>0.05). In the external UCSF dataset, the addition of ADC radiomics yielded a significantly higher AUC for the IDH-wildtype 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-wildtype glioma. The benefit of intensity normalization of ADC maps depends on the type and context of the used data.