Non-evolutive pattern recognition techniques: An application in medical image diagnostics

Lo studio dell’intelligenza artificiale si pone come obiettivo la risoluzione di una classe di problemi che richiedono processi cognitivi difficilmente codificabili in un algoritmo per essere risolti. Il riconoscimento visivo di forme e figure, l’interpretazione di suoni, i giochi a conoscenza incompleta, fanno capo alla capacità umana di interpretare input parziali come se fossero completi, e di agire di conseguenza. Nel primo capitolo della presente tesi sarà costruito un semplice formalismo matematico per descrivere l’atto di compiere scelte. Il processo di “apprendimento” verrà descritto in termini della massimizzazione di una funzione di prestazione su di uno spazio di parametri per un ansatz di una funzione da uno spazio vettoriale ad un insieme finito e discreto di scelte, tramite un set di addestramento che descrive degli esempi di scelte corrette da riprodurre. Saranno analizzate, alla luce di questo formalismo, alcune delle più diffuse tecniche di artificial intelligence, e saranno evidenziate alcune problematiche derivanti dall’uso di queste tecniche. Nel secondo capitolo lo stesso formalismo verrà applicato ad una ridefinizione meno intuitiva ma più funzionale di funzione di prestazione che permetterà, per un ansatz lineare, la formulazione esplicita di un set di equazioni nelle componenti del vettore nello spazio dei parametri che individua il massimo assoluto della funzione di prestazione. La soluzione di questo set di equazioni sarà trattata grazie al teorema delle contrazioni. Una naturale generalizzazione polinomiale verrà inoltre mostrata. Nel terzo capitolo verranno studiati più nel dettaglio alcuni esempi a cui quanto ricavato nel secondo capitolo può essere applicato. Verrà introdotto il concetto di grado intrinseco di un problema. Verranno inoltre discusse alcuni accorgimenti prestazionali, quali l’eliminazione degli zeri, la precomputazione analitica, il fingerprinting e il riordino delle componenti per lo sviluppo parziale di prodotti scalari ad alta dimensionalità. Verranno infine introdotti i problemi a scelta unica, ossia quella classe di problemi per cui è possibile disporre di un set di addestramento solo per una scelta. Nel quarto capitolo verrà discusso più in dettaglio un esempio di applicazione nel campo della diagnostica medica per immagini, in particolare verrà trattato il problema della computer aided detection per il rilevamento di microcalcificazioni nelle mammografie.

Classification algorithms for Intelligent Transport Systems

Intelligent Transport Systems (ITS) consists in the application of ICT to transport to offer new and improved services to the mobility of people and freights. While using ITS, travellers produce large quantities of data that can be collected and analysed to study their behaviour and to provide information to decision makers and planners. The thesis proposes innovative deployments of classification algorithms for Intelligent Transport System with the aim to support the decisions on traffic rerouting, bus transport demand and behaviour of two wheelers vehicles. The first part of this work provides an overview and a classification of a selection of clustering algorithms that can be implemented for the analysis of ITS data. The first contribution of this thesis is an innovative use of the agglomerative hierarchical clustering algorithm to classify similar travels in terms of their origin and destination, together with the proposal for a methodology to analyse drivers’ route choice behaviour using GPS coordinates and optimal alternatives. The clusters of repetitive travels made by a sample of drivers are then analysed to compare observed route choices to the modelled alternatives. The results of the analysis show that drivers select routes that are more reliable but that are more expensive in terms of travel time. Successively, different types of users of a service that provides information on the real time arrivals of bus at stop are classified using Support Vector Machines. The results shows that the results of the classification of different types of bus transport users can be used to update or complement the census on bus transport flows. Finally, the problem of the classification of accidents made by two wheelers vehicles is presented together with possible future application of clustering methodologies aimed at identifying and classifying the different types of accidents.

Modelling, diagnostics and experimental analysis of plasma assisted processes for material treatment

This work presents results from experimental investigations of several different atmospheric pressure plasmas applications, such as Metal Inert Gas (MIG) welding and Plasma Arc Cutting (PAC) and Welding (PAW) sources, as well as Inductively Coupled Plasma (ICP) torches. The main diagnostic tool that has been used is High Speed Imaging (HSI), often assisted by Schlieren imaging to analyse non-visible phenomena. Furthermore, starting from thermo-fluid-dynamic models developed by the University of Bologna group, such plasma processes have been studied also with new advanced models, focusing for instance on the interaction between a melting metal wire and a plasma, or considering non-equilibrium phenomena for diagnostics of plasma arcs. Additionally, the experimental diagnostic tools that have been developed for industrial thermal plasmas have been used also for the characterization of innovative low temperature atmospheric pressure non equilibrium plasmas, such as dielectric barrier discharges (DBD) and Plasma Jets. These sources are controlled by few kV voltage pulses with pulse rise time of few nanoseconds to avoid the formation of a plasma arc, with interesting applications in surface functionalization of thermosensitive materials. In order to investigate also bio-medical applications of thermal plasma, a self-developed quenching device has been connected to an ICP torch. Such device has allowed inactivation of several kinds of bacteria spread on petri dishes, by keeping the substrate temperature lower than 40 degrees, which is a strict requirement in order to allow the treatment of living tissues.

SMARTDIAB: a communication and information technology approach for the intelligent monitoring, management and follow-up of type 1 diabetes patients

SMARTDIAB is a platform designed to support the monitoring, management, and treatment of patients with type 1 diabetes mellitus (T1DM), by combining state-of-the-art approaches in the fields of database (DB) technologies, communications, simulation algorithms, and data mining. SMARTDIAB consists mainly of two units: 1) the patient unit (PU); and 2) the patient management unit (PMU), which communicate with each other for data exchange. The PMU can be accessed by the PU through the internet using devices, such as PCs/laptops with direct internet access or mobile phones via a Wi-Fi/General Packet Radio Service access network. The PU consists of an insulin pump for subcutaneous insulin infusion to the patient and a continuous glucose measurement system. The aforementioned devices running a user-friendly application gather patient's related information and transmit it to the PMU. The PMU consists of a diabetes data management system (DDMS), a decision support system (DSS) that provides risk assessment for long-term diabetes complications, and an insulin infusion advisory system (IIAS), which reside on a Web server. The DDMS can be accessed from both medical personnel and patients, with appropriate security access rights and front-end interfaces. The DDMS, apart from being used for data storage/retrieval, provides also advanced tools for the intelligent processing of the patient's data, supporting the physician in decision making, regarding the patient's treatment. The IIAS is used to close the loop between the insulin pump and the continuous glucose monitoring system, by providing the pump with the appropriate insulin infusion rate in order to keep the patient's glucose levels within predefined limits. The pilot version of the SMARTDIAB has already been implemented, while the platform's evaluation in clinical environment is being in progress.

Application of the specular and diffuse reflection analysis for in vitro diagnostics of dental erosion: correlation with enamel softening, roughness, and calcium release

We present assembly and application of an optical reflectometer for the analysis of dental erosion. The erosive procedure involved acid-induced softening and initial substance loss phases, which are considered to be difficult for visual diagnosis in a clinic. Change of the specular reflection signal showed the highest sensitivity for the detection of the early softening phase of erosion among tested methods. The exponential decrease of the specular reflection intensity with erosive duration was compared to the increase of enamel roughness. Surface roughness was measured by optical analysis, and the observed tendency was correlated with scanning electron microscopy images of eroded enamel. A high correlation between specular reflection intensity and measurement of enamel softening (r(2) ? -0.86) as well as calcium release (r(2) ? -0.86) was found during erosion progression. Measurement of diffuse reflection revealed higher tooth-to-tooth deviation in contrast to the analysis of specular reflection intensity and lower correlation with other applied methods (r(2) = 0.42-0.48). The proposed optical method allows simple and fast surface analysis and could be used for further optimization and construction of the first noncontact and cost-effective diagnostic tool for early erosion assessment in vivo.

Botanical drugs, synergy, and network pharmacology: forth and back to intelligent mixtures

For centuries the science of pharmacognosy has dominated rational drug development until it was gradually substituted by target-based drug discovery in the last fifty years. Pharmacognosy stems from the different systems of traditional herbal medicine and its "reverse pharmacology" approach has led to the discovery of numerous pharmacologically active molecules and drug leads for humankind. But do botanical drugs also provide effective mixtures? Nature has evolved distinct strategies to modulate biological processes, either by selectively targeting biological macromolecules or by creating molecular promiscuity or polypharmacology (one molecule binds to different targets). Widely claimed to be superior over monosubstances, mixtures of bioactive compounds in botanical drugs allegedly exert synergistic therapeutic effects. Despite evolutionary clues to molecular synergism in nature, sound experimental data are still widely lacking to support this assumption. In this short review, the emerging concept of network pharmacology is highlighted, and the importance of studying ligand-target networks for botanical drugs is emphasized. Furthermore, problems associated with studying mixtures of molecules with distinctly different pharmacodynamic properties are addressed. It is concluded that a better understanding of the polypharmacology and potential network pharmacology of botanical drugs is fundamental in the ongoing rationalization of phytotherapy.

Mastitis diagnostics: quantitative PCR for Staphylococcus aureus genotype B in bulk tank milk

A novel real-time quantitative PCR assay for detecting the pathogenic and contagious Staphylococcus aureus genotype B (GTB) in bulk tank milk was developed and evaluated. The detection of this pathogen in bulk tank milk would greatly facilitate its control, as it is responsible for great economic loss in Swiss dairy herds. The assay is based on the simultaneous detection of 3 GTB-typical target sequences, including 2 enterotoxin genes and a polymorphism within the leucotoxin E gene. A variety of mastitis-associated bacteria was used to validate the assays, resulting in an analytical specificity of 100% and high repeatability. The analytical sensitivity in milk was 40 cfu/mL. An exponential association between simulated cow prevalence and quantitative PCR result was observed. An initial field study revealed 1 GTB-positive herd among the 33 studied herds. This novel assay for bulk tank milk analysis is suitable for routine purposes and is expected to be an effective tool for minimizing Staph. aureus GTB in Swiss dairy herds.

[Aortic aneurysms and aortic dissection : Epidemiology, pathophysiology and diagnostics.]

Aortic aneurysms and aortic dissection represent a significant health risk due to the demographic developments and current life styles. The mortality of ruptured aortic aneurysms is up to 80 % and the prevalence of aneurysms varies depending on the localization (thoracic or abdominal). Most commonly affected is the infrarenal abdominal aorta; however, there is evidence that the prevalence is diminishing but in contrast the incidence of thoracic aortic aneurysms is increasing. Aortic dissection is often fatal and is the most common acute aortic disease but the incidence is presumed to be underestimated. The pathogenesis of aortic aneurysms is manifold and is based on an interplay between degenerative, proteolytic and inflammatory processes. An aortic dissection arises from a tear in the intima which results in a separation of the aortic wall layers with infiltration of bleeding and the danger of aortic rupture. Various genetic disorders of connective tissue promote degeneration of the aortic media, most notably Marfan syndrome. Risk factors for aortic aneurysms and aortic dissection are nicotine abuse, arterial hypertension, age and male gender. Aortic aneurysms initially have an uneventful course and as a consequence are mostly discovered incidentally. The clinical course and symptoms of aortic dissection are very much dependent on the section of the aorta affected and the manifestations are manifold. Acute aortic dissection is in 80 % of cases first manifested as sudden extremely severe pain. The diagnostics and subsequent course control can be achieved by a variety of imaging procedures but the modality of choice is computed tomography.

[SPECT/CT diagnostics for skeletal infections]

CLINICAL/METHODICAL ISSUE: Skeletal infections are often a diagnostic and clinical challenge. STANDARD RADIOLOGICAL METHODS: Nuclear imaging modalities used in the diagnostic workup of acute and chronic skeletal infections include three-phase bone scintigraphy and scintigraphy with labelled leucocytes. METHODICAL INNOVATIONS: The introduction of hybrid technologies, such as single photon emission computed tomography/computed tomography (SPECT/CT) has dramatically changed nuclear medical imaging of infections. PERFORMANCE: In general SPECT/CT leads to a considerably more accurate diagnosis than planar or SPECT imaging. ACHIEVEMENTS: Given the integrated acquisition of metabolic, functional and morphological information, SPECT/CT has increased in particular the specificity of three-phase skeletal scanning and scintigraphy with labeled leucocytes.

Coincidence of semilobar holoprosencephaly and Chiari II malformation: correlation of prenatal diagnostics and neuropathologic findings

As holoprosencephaly and Chiari II malformation differ considerably, both in pathogenesis and in phenotypic localization, the coincidence of both entities is extremely rare. The case presented is, to our knowledge, the first published report comprising a combination of a semilobar holoprosencephaly associated with a Chiari II malformation and a myelomeningocele diagnosed prenatally and confirmed by postmortem neuropathologic evaluation. These findings indicate that in the case of pre- and postnatal detection of a myelomeningocele and/or Chiari II malformation, possible additional intracranial malformation, such as a semilobar holoprosencephaly, should also be taken into account and vice versa.

[Interferon-gamma release assays in tuberculosis diagnostics]

Two years ago, CE certified interferon-gamma release assays (IGRA) were launched on the German market (QuantiFERON-TB Gold In-Tube and T-SPOT-TB). Since this time, a multitude of studies have analysed these assays. Guidelines have been elaborated by national expert committees of England, the USA and Switzerland. However, standards of tuberculosis diagnostics and management may vary from country to country. This statement provides practice relevant recommendations for indications, pre-analytics and the interpretation of IGRA test results under different clinical conditions. The IGRA are integrated into existing guidelines for the management of tuberculosis.