Privacy By Design e Data Protection Officer: aspetti normativi e buone prassi nel trattamento dei dati personali.

La Tesi tratta i concetti di Privacy e Protezione dei Dati personali, contestualizzandone il quadro normativo e tecnologico con particolare riferimento ai contesti emergenti rappresentati – per un verso – dalla proposta di nuovo Regolamento generale sulla protezione dei dati personali (redatto dal Parlamento Europeo e dal Consiglio dell’Unione Europea), – per un altro – dalla metodologia di progettazione del Privacy by Design e – per entrambi – dalla previsione di un nuovo attore: il responsabile per la protezione dei dati personali (Privacy Officer). L’elaborato si articola su tre parti oltre introduzione, conclusioni e riferimenti bibliografici. La prima parte descrive il concetto di privacy e le relative minacce e contromisure (tradizionali ed emergenti) con riferimento ai contesti di gestione (aziendale e Big Data) e al quadro normativo vigente. La seconda Parte illustra in dettaglio i principi e le prassi del Privacy by Design e la figura del Privacy Officer formalmente riconosciuta dal novellato giuridico. La terza parte illustra il caso di studio nel quale vengono analizzate tramite una tabella comparativa minacce e contromisure rilevabili in un contesto aziendale.

Application of active and transfer learning to wound image segmentation

Wound management is a fundamental task in standard clinical practice. Automated solutions already exist for humans, but there is a lack of applications on wound management for pets. The importance of a precise and efficient wound assessment is helpful to improve diagnosis and to increase the effectiveness of treatment plans for the chronic wounds. The goal of the research was to propose an automated pipeline capable of segmenting natural light-reflected wound images of animals. Two datasets composed by light-reflected images were used in this work: Deepskin dataset, 1564 human wound images obtained during routine dermatological exams, with 145 manual annotated images; Petwound dataset, a set of 290 wound photos of dogs and cats with 0 annotated images. Two implementations of U-Net Convolutioal Neural Network model were proposed for the automated segmentation. Active Semi-Supervised Learning techniques were applied for human-wound images to perform segmentation from 10% of annotated images. Then the same models were trained, via Transfer Learning, adopting an Active Semi- upervised Learning to unlabelled animal-wound images. The combination of the two training strategies proved their effectiveness in generating large amounts of annotated samples (94% of Deepskin, 80% of PetWound) with the minimal human intervention. The correctness of automated segmentation were evaluated by clinical experts at each round of training thus we can assert that the results obtained in this thesis stands as a reliable solution to perform a correct wound image segmentation. The use of Transfer Learning and Active Semi-Supervied Learning allows to minimize labelling effort from clinicians, even requiring no starting manual annotation at all. Moreover the performances of the model with limited number of parameters suggest the implementation of smartphone-based application to this topic, helping the future standardization of light-reflected images as acknowledge medical images.