MRI Delta Radiomics to Track Early Changes in Tumor Following Radiation: Application in Glioblastoma Mouse Model

Abstract

Background/Objectives: Glioblastoma (GBM) is an aggressive and lethal primary brain tumor with a poor prognosis, with a 5-year survival rate of approximately 5%. Despite advances in oncologic treatments, including surgery, radiotherapy, and chemotherapy, survival outcomes have remained stagnant, largely due to the failure of conventional therapies to address the tumor's inherent heterogeneity. Radiomics, a rapidly emerging field, provides an opportunity to extract features from MRI scans, offering new insights into tumor biology and treatment response. This study evaluates the potential of delta radiomics, the study of changes in radiomic features over time in response to treatment or disease progression, exploring the potential of delta radiomics to track temporal radiation changes in tumor morphology and microstructure. Methods: A cohort of 50 female CD1 nude mice was injected intracranially with G7 glioblastoma cells and divided into irradiated (IR) and non-irradiated (non-IR) groups. MRI scans were performed at baseline (week 11) and post-radiation (weeks 12 and 14), and radiomic features, including shape, histogram, and texture parameters, were extracted and analyzed to capture radiation-induced changes. The most robust features were those identified through intra-observer reproducibility assessment, ensuring reliability in feature selection. A machine learning model was developed to classify irradiated tumors based on delta radiomic features, and statistical analyses were conducted to evaluate feature feasibility, stability, and predictive performance. Results: Our findings demonstrate that delta radiomics effectively captured significant temporal variations in tumor characteristics. Delta radiomics features exhibited distinct patterns across different time points in the IR group, enabling machine learning models to achieve a high accuracy. Conclusions: Delta radiomics offers a robust, non-invasive method for monitoring the treatment of glioblastoma (GBM) following radiation therapy. Future research should prioritize the application of MRI delta radiomics to effectively capture short-term changes resulting from intratumoral radiation effects. This advancement has the potential to significantly enhance treatment monitoring and facilitate the development of personalized therapeutic strategies.

Keywords: MRI; delta radiomics; glioblastoma; machine learning; radiation therapy; tumor morphology and texture analysis.

Figure 1

Experimental protocol. At week zero, 50 mice were orthotopically implanted with G7 glioblastoma cells. Mice were divided into two groups (non-IR and IR) and were imaged in different time points (weeks 11, 12, and 13).

Figure 2

Schematic diagram of the radiomics analysis pipeline steps after injecting the G7 model. The procedures include image acquisition, applying normalization image filter, tumor segmentation, radiomic features (shape, histogram, and texture) extraction, and then delta radiomics features analysis using predictive model construction and validation.

Figure 3

Tumor regions were manually outlined from T2-weighted slices where they were visible. (a) Illustrates tumor growth for both the IR and non-IR groups across three time points (weeks 11, 12, and 13), revealing no significant difference between the two groups (unpaired t-test). (b,c) Present a comparison of tumor growth between the non-IR and IR groups at various time points.

Figure 4

Shows the percentage of radiomics features extracted from inter observers between pre-radiation groups, high ICC values (ICCs > 0.8) were selected as robust radiomics features.

Figure 5

Illustrating the p-value analysis (p < 0.05) of delta radiomic features across different IR groups at various time points: (a) week 11 compared to week 12 and (b) week 12 compared to week 13.

Figure 6

The analysis of ROC performance for machine learning models is conducted between two sets of IR groups: (a) during weeks 11 and 12 and (b) during weeks 12 and 13.