Uso di 3d slicer in ambito di ricerca clinica: Una revisione critica delle esperienze di riferimento

Negli ultimi 20 anni il progresso tecnologico ha segnato un profondo cambiamento in svariati ambiti tra i quali quello della Sanità in cui hanno preso vita apparecchiature diagnostiche, cosiddette “digitali native”, come la Tomografia Computerizzata (TC), la Tomografia ad Emissione di Positroni (PET), la Risonanza Magnetica Nucleare (RMN), l’Ecografia. A differenza delle diagnostiche tradizionali, come ad esempio la Radiologia convenzionale, che forniscono come risultato di un esame un’immagine bidimensionale ricavata dalla semplice proiezione di una struttura anatomica indagata, questi nuovi sistemi sono in grado di generare scansioni tomografiche. Disporre di immagini digitali contenenti dati tridimensionali rappresenta un enorme passo in avanti per l’indagine diagnostica, ma per poterne estrapolare e sfruttare i preziosi contenuti informativi occorrono i giusti strumenti che, data la natura delle acquisizioni, vanno ricercati nel mondo dell’Informatica. A tal proposito il seguente elaborato si propone di presentare un software package per la visualizzazione, l’analisi e l’elaborazione di medical images chiamato 3D Slicer che rappresenta un potente strumento di cui potersi avvalere in differenti contesti medici. Nel primo capitolo verrà proposta un’introduzione al programma; Seguirà il secondo capitolo con una trattazione più tecnica in cui verranno approfondite alcune funzionalità basilari del software e altre più specifiche; Infine nel terzo capitolo verrà preso in esame un intervento di endoprotesica vascolare e come grazie al supporto di innovativi sistemi di navigazione chirurgica sia possibile avvalersi di 3D Slicer anche in ambiente intraoperatorio

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.

Compressed sensing in digital tomosynthesis reconstruction

In this work we study a model for the breast image reconstruction in Digital Tomosynthesis, that is a non-invasive and non-destructive method for the three-dimensional visualization of the inner structures of an object, in which the data acquisition includes measuring a limited number of low-dose two-dimensional projections of an object by moving a detector and an X-ray tube around the object within a limited angular range. The problem of reconstructing 3D images from the projections provided in the Digital Tomosynthesis is an ill-posed inverse problem, that leads to a minimization problem with an object function that contains a data fitting term and a regularization term. The contribution of this thesis is to use the techniques of the compressed sensing, in particular replacing the standard least squares problem of data fitting with the problem of minimizing the 1-norm of the residuals, and using as regularization term the Total Variation (TV). We tested two different algorithms: a new alternating minimization algorithm (ADM), and a version of the more standard scaled projected gradient algorithm (SGP) that involves the 1-norm. We perform some experiments and analyse the performance of the two methods comparing relative errors, iterations number, times and the qualities of the reconstructed images. In conclusion we noticed that the use of the 1-norm and the Total Variation are valid tools in the formulation of the minimization problem for the image reconstruction resulting from Digital Tomosynthesis and the new algorithm ADM has reached a relative error comparable to a version of the classic algorithm SGP and proved best in speed and in the early appearance of the structures representing the masses.