Quantitative study of changes in the hippocampus after whole-brain radiotherapy via multisequence magnetic resonance imaging radiomics

Purpose

Multisequence magnetic resonance imaging (MRI) radiomic features were used to analyze dynamic changes in the hippocampus after whole-brain radiotherapy (WBRT), thus providing an objective basis for the early prediction of hippocampal radiation injury.

Methods

Seventy-five patients with brain metastases (BMs) who received WBRT underwent MRI scanning (including T1-weighted imaging [T1WI], contrast-enhanced [CE]-T1WI, T2-weighted imaging [T2WI], T2-weighted Fluid-Attenuated Inversion Recovery imaging [T2 FLAIR] and diffusion weighted imaging [DWI]) before WBRT (MRI_pre), after WBRT (MRI_post, 26.22 ± 13.05 days after the MRI_pre scan), and at follow-up WBRT (MRI_follow, 393.45 ± 210.33 days after the MRI_post scan). Radiomics features were subsequently extracted from delineations of the hippocampus on the different sequences. Changes in the hippocampal volume and radiomics features of the sequences were analyzed in the MRI_post and MRI_follow sequences relative to the MRI_pre sequences. The features were then organized as follows: (1) Group₁ features included those features that were significantly different among MRI_pre, MRI_post, and MRI_follow scans; and (2) Group₂ features included those features that were significantly different between MRI_pre and MRI_follow scans and between MRI_post and MRI_follow scans.

Results

(1) The average MRI_post and MRI_follow hippocampal volumes were 3.32 ± 0.49 cm³ and 2.95±0.45 cm³, respectively, which were 1.68 % and 12.51% lower than the MRI_pre volume (3.41 ± 0.49 cm³), respectively (p < 0.05). (2) Radiomics analysis revealed that 88 features were significantly different (p < 0.05) across the MRI_pre, MRI_post, and MRI_follow scans. The T2WI sequence contained the greatest number of significant features (n = 42). Among Group₁ features (n = 57), enrichment was observed in T2WI (n = 34) and T1WI (n = 22). The feature exhibiting the highest rate of change was GLCM-ClusterShade (range: 83.87–281.62 %). All 12 significant change features in CE-T1WI were observed in Group₂. Although the overall timing difference for T2 FLAIR was not significant (p = 0.064), DWI contained a single Group₂ feature (p = 0.032). Within Group₂, GLCM-ClusterTendency exhibited the largest rate of change (range: 37.16–51.27 %).

Conclusions

Compared with volume, multisequence MRI radiomics features more directly reflect dynamic microscopic hippocampal changes across MRI_pre, MRI_post, and MRI_follow time points. T2WI and T1WI captured early sustained radiomics alterations, whereas CE-T1WI reflected delayed changes, thus serving as potential biomarkers for the monitoring of hippocampal dynamics following WBRT.