Magnetic Resonance Imaging-Derived biomarkers of Isocitrate-Dehydrogenase mutation in diffuse gliomas: a conventional MR and Diffusion Weighted Imaging study.

The introduction of molecular criteria into the classification of diffuse gliomas has added interesting practical implications to glioma management. This has created a new clinical need for correlating imaging characteristics with glioma genotypes, also known as radiogenomics or imaging genomics. Whilst many studies have primarily focused on the use of advanced magnetic resonance imaging (MRI) techniques for radiogenomics purposes, conventional MRI sequences still remain the reference point in the study and characterization of brain tumours. Moreover, a different approach may rely on diffusion-weighted imaging (DWI) usage, which is considered a “conventional” sequence in line with recently published directions on glioma imaging. In a non-invasive way, it can provide direct insight into the microscopic physical properties of tissues. Considering that Isocitrate-Dehydrogenase gene mutations may reflect alterations in metabolism, cellularity, and angiogenesis, which may manifest characteristic features on an MRI, the identification of specific MRI biomarkers could be of great interest in managing patients with brain gliomas. My study aimed to evaluate the presence of specific MRI-derived biomarkers of IDH molecular status through conventional MRI and DWI sequences.

Development and characterization of deep learning techniques for neuroimaging data

Deep learning methods are extremely promising machine learning tools to analyze neuroimaging data. However, their potential use in clinical settings is limited because of the existing challenges of applying these methods to neuroimaging data. In this study, first a data leakage type caused by slice-level data split that is introduced during training and validation of a 2D CNN is surveyed and a quantitative assessment of the model’s performance overestimation is presented. Second, an interpretable, leakage-fee deep learning software written in a python language with a wide range of options has been developed to conduct both classification and regression analysis. The software was applied to the study of mild cognitive impairment (MCI) in patients with small vessel disease (SVD) using multi-parametric MRI data where the cognitive performance of 58 patients measured by five neuropsychological tests is predicted using a multi-input CNN model taking brain image and demographic data. Each of the cognitive test scores was predicted using different MRI-derived features. As MCI due to SVD has been hypothesized to be the effect of white matter damage, DTI-derived features MD and FA produced the best prediction outcome of the TMT-A score which is consistent with the existing literature. In a second study, an interpretable deep learning system aimed at 1) classifying Alzheimer disease and healthy subjects 2) examining the neural correlates of the disease that causes a cognitive decline in AD patients using CNN visualization tools and 3) highlighting the potential of interpretability techniques to capture a biased deep learning model is developed. Structural magnetic resonance imaging (MRI) data of 200 subjects was used by the proposed CNN model which was trained using a transfer learning-based approach producing a balanced accuracy of 71.6%. Brain regions in the frontal and parietal lobe showing the cerebral cortex atrophy were highlighted by the visualization tools.

Data driven regularization models of non-linear ill-posed inverse problems in imaging

Imaging technologies are widely used in application fields such as natural sciences, engineering, medicine, and life sciences. A broad class of imaging problems reduces to solve ill-posed inverse problems (IPs). Traditional strategies to solve these ill-posed IPs rely on variational regularization methods, which are based on minimization of suitable energies, and make use of knowledge about the image formation model (forward operator) and prior knowledge on the solution, but lack in incorporating knowledge directly from data. On the other hand, the more recent learned approaches can easily learn the intricate statistics of images depending on a large set of data, but do not have a systematic method for incorporating prior knowledge about the image formation model. The main purpose of this thesis is to discuss data-driven image reconstruction methods which combine the benefits of these two different reconstruction strategies for the solution of highly nonlinear ill-posed inverse problems. Mathematical formulation and numerical approaches for image IPs, including linear as well as strongly nonlinear problems are described. More specifically we address the Electrical impedance Tomography (EIT) reconstruction problem by unrolling the regularized Gauss-Newton method and integrating the regularization learned by a data-adaptive neural network. Furthermore we investigate the solution of non-linear ill-posed IPs introducing a deep-PnP framework that integrates the graph convolutional denoiser into the proximal Gauss-Newton method with a practical application to the EIT, a recently introduced promising imaging technique. Efficient algorithms are then applied to the solution of the limited electrods problem in EIT, combining compressive sensing techniques and deep learning strategies. Finally, a transformer-based neural network architecture is adapted to restore the noisy solution of the Computed Tomography problem recovered using the filtered back-projection method.

Inside standard and hyperspectral low-dose CT variational imaging: parameter identification and material decomposition

The main contribution of this thesis is the proposal of novel strategies for the selection of parameters arising in variational models employed for the solution of inverse problems with data corrupted by Poisson noise. In light of the importance of using a significantly small dose of X-rays in Computed Tomography (CT), and its need of using advanced techniques to reconstruct the objects due to the high level of noise in the data, we will focus on parameter selection principles especially for low photon-counts, i.e. low dose Computed Tomography. For completeness, since such strategies can be adopted for various scenarios where the noise in the data typically follows a Poisson distribution, we will show their performance for other applications such as photography, astronomical and microscopy imaging. More specifically, in the first part of the thesis we will focus on low dose CT data corrupted only by Poisson noise by extending automatic selection strategies designed for Gaussian noise and improving the few existing ones for Poisson. The new approaches will show to outperform the state-of-the-art competitors especially in the low-counting regime. Moreover, we will propose to extend the best performing strategy to the hard task of multi-parameter selection showing promising results. Finally, in the last part of the thesis, we will introduce the problem of material decomposition for hyperspectral CT, which data encodes information of how different materials in the target attenuate X-rays in different ways according to the specific energy. We will conduct a preliminary comparative study to obtain accurate material decomposition starting from few noisy projection data.

Advanced imaging study in cerebrovascular pathology for the personalization of therapy: from the capillary microcirculation to the vessel wall

Objectives: To investigate the use of intravascular optical coherence tomography (IVOCT) for carotid artery stenting (CAS) procedures in patients with atherosclerotic stenosis. Examine possible markers that might identify the onset of new cerebral ischemic lesions on MRI. Specifically, attention was drawn to the morphological features of the used dual layer stent, which could be underestimated during traditional CAS procedures. Secondary goals are to compare the safety and efficacy of different CAS techniques and the accuracy of the vessel analysis software’s on pre-operative CTA examination used to quantify ICA stenosis with the gold standard IVOCT. Material and Methods: Ten patients underwent CAS procedure with flow-arrest technique and IVOCT evaluations prior to and following stent deployment, while five matched patients underwent CAS procedure with distal embolic protection device (EPD) technique. All patients underwent 24-hours 3T MRI examination to check for ischemic lesions; all patients were treated with the same dual-layer stent. Results: Patients with new ischemic lesions demonstrated peculiar stent configuration in the distal end, and a strong Spearman’s rank order correlation was found among the volume of new DWI lesions and the stent configuration in its distal end (Rs: 0.81; p <0.001). No statistically significant differences were observed in the total burden of new ischemic lesions for each technique. The vessel analysis software's on CTA comparison demonstrated a higher diagnostic accuracy in the degree of ICA stenosis compared to the gold standard of IVOCT of the specialized software (ROC curve = 0.63; p = 0.06) compared to the general software (ROC curve = 0.57, p = 0.31). Conclusions: Study’s results support the use of IVOCT to allow recognition of potential features that can predict the onset of new cerebral ischemic lesions. Additionally, IVOCT made it possible to evaluate specialized software's increased accuracy in the pre-operative evaluation of ICA atherosclerotic stenosis.