Patients with 1p/19q co-deleted low grade glioma (LGGs) have better prognosis and react better to certain treatments than patients with intact 1p/19q LGG. Currently, information about the 1p/19q co-deletion status is obtained by means of an invasive procedure called biopsy. As an alternative, non-invasive techniques to extract this information from medical images are being studied. Recent research suggests that local binary patterns (LBPs), a textural image descriptor, are an important feature which can predict the 1p/19q co-deletion from MRI scans. In this project we report the effect of including LBP information in a convolutional neural network (CNN) to predict the 1p/19q co-deletion status in patients suffering from a presumed LGG using pre-operative MRI scans. A combination of convolutional filters was designed and included in the CNN, resulting into local binary convolutional neural networks (LBCNNs). Three LBP descriptors, each of them representing a different textural scale, were studied, as well as the combination of the three. A default CNN without LBPs was also studied. To validate the designed filters and to study more sophisticated LBPs images like the uniform LBPs, pre-computed LBP images were directly input to the CNN. An in-house multi-institution MRI dataset consisting of 284 patients who had undergone a biopsy or resection before the treatment, and with available pre-operative T1-weighted post contrast and T2-weighted scans was used to train the different network architectures. An independent dataset consisting of 129 patients was used to validate the results. The performance of the LBCNNs was compared to the performance of the CNN. The performance of the CNN and LBCNNs was similar, reporting an area under the receiver operating characteristic curve (AUC) ranging from 0.816 to 0.872 for the different architectures. These findings suggest that the CNN can extract information relative to LBPs by itself. In addition, pre-computed uniform LBPs report similar metrics (AUC: 0.819), suggesting that they do not add new information.

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

Introduction: Magnetic Resonance Imaging is a commonly used technique for the initial diagnosis of gliomas. T1, T2, T2-FLAIR, and post-contrast T1 with gadolinium-based contrast agents (GBCAs) can show tumor characteristics. However, using this contrast agent poses a risk to patients with kidney failures, has environmental impact, and increases cost. To address these issues, we aimed to evaluate the potential of deep learning in generating synthetic post-contrast T1 images without using contrast agents. Method: The project investigates the potential of using deep learning (DL) to generate synthetic post-contrast T1 images based on T1, T2, and T2-FLAIR provided by the Erasmus Glioma Database. Exploring different model architectures, loss functions, and input sizes to discover the optimal approach. Results: Results show that individual loss functions, input size, and model complexity slightly impact the accuracy of synthetic post-contrast T1 images. Combining loss functions, however, was the most promising approach for image generation. Models trained with ℒm could generate low detail enhancement. Resulting in 0.0478±0.0076, 0.0139±0.0036, and 0.879±0.024 for MAE, MSE, and SSIM, respectively. Conclusion: The study's findings indicate that DL is promising for generating synthetic post-contrast T1 images without using GBCAs. However, further research is required to generate realistic synthetic post-contrast T1 images. The study, however, provides a basis for future work and highlights the importance of reducing the use of GBCAs in clinical practice.