Background: Glioma is a type of brain, originating from glial cells that support nerve cells, such as astrocytes and dendrocytes. It varies in type and severity, often resulting in a low life expectancy due to its aggressive nature. Since the implementation of the 2016 WHO Central Nervous System tumor classification, Isocitrate Dehydrogenase (IDH) mutation status has been used as a marker to distinguish the severity of the gliomas. This research explores the correlation between Arterial Spin Labeling (ASL) and Dynamic Susceptibility Contrast (DSC) MRI techniques to determine IDH mutation status in non-enhancing gliomas. Methods: This project used 34 iGene patient dataset. To overlay ASL to DSC, both images were registered to the FLAIR images as the registration reference. The statistical analysis was done by dividing the tumor region for both ASL and DSC into three areas: hypo-perfusion, iso-perfusion, and hyperperfusion. Then, the images were flattened from 3D to 1D data and the statistical analysis was done with Spearman’s correlation. The correlation between those three areas for two imaging techniques resulted in nine cases. To test the interclass significance, the Mann Whitney-U test was used. Results: This project found a higher mismatch area between ASL-CBF and DSC-rCBV in the IDHwildtype group compared to the IDH-mutant group. Additionally, the mismatch area in IDH-wildtype shows a lower Spearman’s coefficient, suggesting different information captured by those two imaging techniques. It reveals significant findings that both ASL-CBF and DSC-rCBV can be valuable in distinguishing IDH mutation statuses, with notable differences in perfusion characteristics between IDH-mutant and IDH-wildtype gliomas. Conclusion: Voxel-wise correlation between ASL-CBF and DSC-rCBV can be a potential marker to distinguish IDH-mutant from IDH-wildtype.

Introduction: Gliomas are the most common primary malignant brain tumours with a very poor survival. Resistance to chemotherapy and radiotherapy often occurs in these tumours due to hypoxia, which can be caused by different oxygenation parameters. Multiple magnetic resonance imaging (MRI) techniques are able to assess these oxygenation parameters. Since multiple artificial intelligence (AI) approaches exist to fuse these oxygenation images together, the goal of this research is to find and implement an AI approach to generate a combined representation of multiple oxygenation parameters acquired by MRI so hypoxia within brain tumours can be detected and located.
Literature study: Multiple MR imaging techniques that are able to measure different oxygenation parameters have been reviewed in the literature study. In addition, an overview was given of different AI approaches for combining the acquired information of the discussed MR imaging techniques. Based on the literature findings, hierarchical clustering was the most promising AI approach for this research purpose.
Methods: A specific MR imaging protocol was designed to assess information regarding tumour oxygenation within patients with brain tumours. After registration of the acquired images to the same space, the voxels of healthy brain tissues in these images were used for performing hierarchical clustering multiple times to identify the optimal parameter settings of the algorithm. Then the clustering was performed multiple times with different data types in order to achieve a decrease of required computational power. After segmentation of the tumour area in the MR images, the clustering was applied to the tumour voxels to generate a spatial map of the tumour showing the location of the clusters representing different states of oxygenation. Evaluation of the clusters was performed by visualizing the distribution of the oxygenation parameter values within the different clusters.
Results: Three patients were included and underwent MR imaging. Results showed that ward linkage and Euclidean distance resulted in the highest clustering performance when performing hierarchical clustering on data of healthy brain tissue. Changing the data type of input data did not lead to a decrease in required computational power. Applying the hierarchical clustering with the optimal parameter settings on tumour voxels resulted in spatial maps of the different clusters within the tumour. Evaluation of the distribution of the oxygenation parameter values showed differences among different clusters within the patients. However, within two patients the number of clusters present within the tumour, changed when including different MR images in the clustering analysis.
Conclusion: This research showed that hierarchical clustering is an AI approach which is able to identify clusters with a different distribution of oxygenation parameter values acquired by MR imaging. Visualizing these different clusters in a spatial map results in a combined representation of these oxygenation parameters. Despite the promising results, future work is needed to investigate other clustering methods regarding this research purpose, the importance of each individual MR technique, and a validation method of what type of oxygenation the clusters represent