Synthetic generation of amyloid PET images by non-linear dimensionality reduction inversion

Privacy issues and data scarcity in PET field call for efficient methods to expand datasets via synthetic generation of new data that cannot be traced back to real patients and that are also realistic. In this thesis, machine learning techniques were applied to 1001 amyloid-beta PET images, which had undergone a diagnosis of Alzheimer’s disease: the evaluations were 540 positive, 457 negative and 4 unknown. Isomap algorithm was used as a manifold learning method to reduce the dimensions of the PET dataset; a numerical scale-free interpolation method was applied to invert the dimensionality reduction map. The interpolant was tested on the PET images via LOOCV, where the removed images were compared with the reconstructed ones with the mean SSIM index (MSSIM = 0.76 ± 0.06). The effectiveness of this measure is questioned, since it indicated slightly higher performance for a method of comparison using PCA (MSSIM = 0.79 ± 0.06), which gave clearly poor quality reconstructed images with respect to those recovered by the numerical inverse mapping. Ten synthetic PET images were generated and, after having been mixed with ten originals, were sent to a team of clinicians for the visual assessment of their realism; no significant agreements were found either between clinicians and the true image labels or among the clinicians, meaning that original and synthetic images were indistinguishable. The future perspective of this thesis points to the improvement of the amyloid-beta PET research field by increasing available data, overcoming the constraints of data acquisition and privacy issues. Potential improvements can be achieved via refinements of the manifold learning and the inverse mapping stages during the PET image analysis, by exploring different combinations in the choice of algorithm parameters and by applying other non-linear dimensionality reduction algorithms. A final prospect of this work is the search for new methods to assess image reconstruction quality.

A Phase Space Box-counting based Method for Arrhythmia Prediction from Electrocardiogram Time Series

Arrhythmia is one kind of cardiovascular diseases that give rise to the number of deaths and potentially yields immedicable danger. Arrhythmia is a life threatening condition originating from disorganized propagation of electrical signals in heart resulting in desynchronization among different chambers of the heart. Fundamentally, the synchronization process means that the phase relationship of electrical activities between the chambers remains coherent, maintaining a constant phase difference over time. If desynchronization occurs due to arrhythmia, the coherent phase relationship breaks down resulting in chaotic rhythm affecting the regular pumping mechanism of heart. This phenomenon was explored by using the phase space reconstruction technique which is a standard analysis technique of time series data generated from nonlinear dynamical system. In this project a novel index is presented for predicting the onset of ventricular arrhythmias. Analysis of continuously captured long-term ECG data recordings was conducted up to the onset of arrhythmia by the phase space reconstruction method, obtaining 2-dimensional images, analysed by the box counting method. The method was tested using the ECG data set of three different kinds including normal (NR), Ventricular Tachycardia (VT), Ventricular Fibrillation (VF), extracted from the Physionet ECG database. Statistical measures like mean (μ), standard deviation (σ) and coefficient of variation (σ/μ) for the box-counting in phase space diagrams are derived for a sliding window of 10 beats of ECG signal. From the results of these statistical analyses, a threshold was derived as an upper bound of Coefficient of Variation (CV) for box-counting of ECG phase portraits which is capable of reliably predicting the impeding arrhythmia long before its actual occurrence. As future work of research, it was planned to validate this prediction tool over a wider population of patients affected by different kind of arrhythmia, like atrial fibrillation, bundle and brunch block, and set different thresholds for them, in order to confirm its clinical applicability.

Substructuring approache in state space models for dynamic system parameters identification

In the recent decade, the request for structural health monitoring expertise increased exponentially in the United States. The aging issues that most of the transportation structures are experiencing can put in serious jeopardy the economic system of a region as well as of a country. At the same time, the monitoring of structures is a central topic of discussion in Europe, where the preservation of historical buildings has been addressed over the last four centuries. More recently, various concerns arose about security performance of civil structures after tragic events such the 9/11 or the 2011 Japan earthquake: engineers looks for a design able to resist exceptional loadings due to earthquakes, hurricanes and terrorist attacks. After events of such a kind, the assessment of the remaining life of the structure is at least as important as the initial performance design. Consequently, it appears very clear that the introduction of reliable and accessible damage assessment techniques is crucial for the localization of issues and for a correct and immediate rehabilitation. The System Identification is a branch of the more general Control Theory. In Civil Engineering, this field addresses the techniques needed to find mechanical characteristics as the stiffness or the mass starting from the signals captured by sensors. The objective of the Dynamic Structural Identification (DSI) is to define, starting from experimental measurements, the modal fundamental parameters of a generic structure in order to characterize, via a mathematical model, the dynamic behavior. The knowledge of these parameters is helpful in the Model Updating procedure, that permits to define corrected theoretical models through experimental validation. The main aim of this technique is to minimize the differences between the theoretical model results and in situ measurements of dynamic data. Therefore, the new model becomes a very effective control practice when it comes to rehabilitation of structures or damage assessment. The instrumentation of a whole structure is an unfeasible procedure sometimes because of the high cost involved or, sometimes, because it’s not possible to physically reach each point of the structure. Therefore, numerous scholars have been trying to address this problem. In general two are the main involved methods. Since the limited number of sensors, in a first case, it’s possible to gather time histories only for some locations, then to move the instruments to another location and replay the procedure. Otherwise, if the number of sensors is enough and the structure does not present a complicate geometry, it’s usually sufficient to detect only the principal first modes. This two problems are well presented in the works of Balsamo [1] for the application to a simple system and Jun [2] for the analysis of system with a limited number of sensors. Once the system identification has been carried, it is possible to access the actual system characteristics. A frequent practice is to create an updated FEM model and assess whether the structure fulfills or not the requested functions. Once again the objective of this work is to present a general methodology to analyze big structure using a limited number of instrumentation and at the same time, obtaining the most information about an identified structure without recalling methodologies of difficult interpretation. A general framework of the state space identification procedure via OKID/ERA algorithm is developed and implemented in Matlab. Then, some simple examples are proposed to highlight the principal characteristics and advantage of this methodology. A new algebraic manipulation for a prolific use of substructuring results is developed and implemented.

Space charge and dielectric response measurements to assess insulation aging of low-voltage cables used in nuclear power plants

The current design life of nuclear power plant (NPP) could potentially be extended to 80 years. During this extended plant life, all safety and operationally relevant Instrumentation & Control (I&C) systems are required to meet their designed performance requirements to ensure safe and reliable operation of the NPP, both during normal operation and subsequent to design base events. This in turn requires an adequate and documented qualification and aging management program. It is known that electrical insulation of I&C cables used in safety related circuits can degrade during their life, due to the aging effect of environmental stresses, such as temperature, radiation, vibration, etc., particularly if located in the containment area of the NPP. Thus several condition monitoring techniques are required to assess the state of the insulation. Such techniques can be used to establish a residual lifetime, based on the relationship between condition indicators and ageing stresses, hence, to support a preventive and effective maintenance program. The object of this thesis is to investigate potential electrical aging indicators (diagnostic markers) testing various I&C cable insulations subjected to an accelerated multi-stress (thermal and radiation) aging.

Parallelization of the algorithm WHAM with NVIDIA CUDA.

The aim of my thesis is to parallelize the Weighting Histogram Analysis Method (WHAM), which is a popular algorithm used to calculate the Free Energy of a molucular system in Molecular Dynamics simulations. WHAM works in post processing in cooperation with another algorithm called Umbrella Sampling. Umbrella Sampling has the purpose to add a biasing in the potential energy of the system in order to force the system to sample a specific region in the configurational space. Several N independent simulations are performed in order to sample all the region of interest. Subsequently, the WHAM algorithm is used to estimate the original system energy starting from the N atomic trajectories. The parallelization of WHAM has been performed through CUDA, a language that allows to work in GPUs of NVIDIA graphic cards, which have a parallel achitecture. The parallel implementation may sensibly speed up the WHAM execution compared to previous serial CPU imlementations. However, the WHAM CPU code presents some temporal criticalities to very high numbers of interactions. The algorithm has been written in C++ and executed in UNIX systems provided with NVIDIA graphic cards. The results were satisfying obtaining an increase of performances when the model was executed on graphics cards with compute capability greater. Nonetheless, the GPUs used to test the algorithm is quite old and not designated for scientific calculations. It is likely that a further performance increase will be obtained if the algorithm would be executed in clusters of GPU at high level of computational efficiency. The thesis is organized in the following way: I will first describe the mathematical formulation of Umbrella Sampling and WHAM algorithm with their apllications in the study of ionic channels and in Molecular Docking (Chapter 1); then, I will present the CUDA architectures used to implement the model (Chapter 2); and finally, the results obtained on model systems will be presented (Chapter 3).

Study of a new method for high energy top tagging at the ATLAS experiment

Since its discovery, top quark has represented one of the most investigated field in particle physics. The aim of this thesis is the reconstruction of hadronic top with high transverse momentum (boosted) with the Template Overlap Method (TOM). Because of the high energy, the decay products of boosted tops are partially or totally overlapped and thus they are contained in a single large radius jet (fat-jet). TOM compares the internal energy distributions of the candidate fat-jet to a sample of tops obtained by a MC simulation (template). The algorithm is based on the definition of an overlap function, which quantifies the level of agreement between the fat-jet and the template, allowing an efficient discrimination of signal from the background contributions. A working point has been decided in order to obtain a signal efficiency close to 90% and a corresponding background rejection at 70%. TOM performances have been tested on MC samples in the muon channel and compared with the previous methods present in literature. All the methods will be merged in a multivariate analysis to give a global top tagging which will be included in ttbar production differential cross section performed on the data acquired in 2012 at sqrt(s)=8 TeV in high phase space region, where new physics processes could be possible. Due to its peculiarity to increase the pT, the Template Overlap Method will play a crucial role in the next data taking at sqrt(s)=13 TeV, where the almost totality of the tops will be produced at high energy, making the standard reconstruction methods inefficient.