Os requisitos técnicos da qualidade da imagem em mamografia estabelecidos por normas nacionais e internacionais incluem parâmetros de qualidade que podem ser avaliados através da realização de testes periódicos. Estes parâmetros podem ser medidos com a aquisição e leitura de imagens de objetos (phantoms) que simulam as estruturas presentes em uma mamografia. O phantom CDMAM foi confeccionado especificamente para a realização de testes que utilizam um procedimento padrão para se determinar um limiar de contraste para cada diâmetro de disco presentes em suas imagens. No entanto, esta tarefa é bastante trabalhosa e consome tempo, além de estar sujeita a uma significativa dependência do observador, diminuindo a precisão das aferições. Nesse sentido, o propósito deste trabalho é o desenvolvimento de um software que auxilie o profissional na realização dos testes, reduzindo a subjetividade devida aos observadores e correlacionando as leituras automatizadas com o sistema visual humano, sem a necessidade de se efetuar a correção dos resultados, como é realizado em diversos trabalhos encontrados na literatura. Para isso, foram utilizadas imagens obtidas por cinco sistemas CR e um método de detecção baseado na confecção de filtros circulares correlatores. A correlação com a visão humana fundamentou-se nos parâmetros de Weber, que descrevem o comportamento do sistema visual na discriminação do contraste em imagens digitais. A classificação dos discos contidos na imagem do phantom entre visível ou não visível foi efetuada a partir de uma ferramenta de mineração de dados conhecida como WEKA (Waikato Environment for Knowledge Analysis) associada ao algoritmo J48, que promove a construção de modelos de árvore de decisão. O resultado da implementação destas árvores de decisão foi a obtenção de um sistema de auxílio ao especialista que reforça a sua integridade na avaliação a partir de resultados estáveis e de fácil interpretação, atingindo acurácias de até 95%. / Technical requirements of image quality in mammography established by national and international norms include quality parameters which can be achieved by conducting periodic tests. It is recommended that some quality parameters are measured from images acquired by exposing specific phantoms, as CDMAM, in such systems. Nevertheless, this task is hard-working and time consuming, besides to be subject to a significant dependence of the observer, reducing the measurements accuracy. Accordingly, the purpose of this work is the development of a software to assist in the professional testing, reducing the subjectivity due to the observers and correlating the automated readings with the human visual system, without the need to make the correction of the results, as is done in many studies in the literature. For this, we used 57 images obtained for five CR systems and a method of detection based on circular correlators filters. The correlation with human vision was based on the Weber\'s parameters which describe the behavior of the visual system to discriminate the contrast in digital images. The classification of the image discs between visible or not visible was made from a data mining tool known as WEKA (Waikato Environment for Knowledge Analysis) associated with the J48 algorithm which promotes the construction of decision tree models. The result of the decision trees implementation was a system to aid the specialist, reinforcing the integrity of the assessment using stable results, easily interpreted, and reaching accuracies of up to 95%.

Os requisitos técnicos da qualidade da imagem em mamografia estabelecidos por normas nacionais e internacionais incluem parâmetros de qualidade que podem ser avaliados através da realização de testes periódicos. Estes parâmetros podem ser medidos com a aquisição e leitura de imagens de objetos (phantoms) que simulam as estruturas presentes em uma mamografia. O phantom CDMAM foi confeccionado especificamente para a realização de testes que utilizam um procedimento padrão para se determinar um limiar de contraste para cada diâmetro de disco presentes em suas imagens. No entanto, esta tarefa é bastante trabalhosa e consome tempo, além de estar sujeita a uma significativa dependência do observador, diminuindo a precisão das aferições. Nesse sentido, o propósito deste trabalho é o desenvolvimento de um software que auxilie o profissional na realização dos testes, reduzindo a subjetividade devida aos observadores e correlacionando as leituras automatizadas com o sistema visual humano, sem a necessidade de se efetuar a correção dos resultados, como é realizado em diversos trabalhos encontrados na literatura. Para isso, foram utilizadas imagens obtidas por cinco sistemas CR e um método de detecção baseado na confecção de filtros circulares correlatores. A correlação com a visão humana fundamentou-se nos parâmetros de Weber, que descrevem o comportamento do sistema visual na discriminação do contraste em imagens digitais. A classificação dos discos contidos na imagem do phantom entre visível ou não visível foi efetuada a partir de uma ferramenta de mineração de dados conhecida como WEKA (Waikato Environment for Knowledge Analysis) associada ao algoritmo J48, que promove a construção de modelos de árvore de decisão. O resultado da implementação destas árvores de decisão foi a obtenção de um sistema de auxílio ao especialista que reforça a sua integridade na avaliação a partir de resultados estáveis e de fácil interpretação, atingindo acurácias de até 95%. / Technical requirements of image quality in mammography established by national and international norms include quality parameters which can be achieved by conducting periodic tests. It is recommended that some quality parameters are measured from images acquired by exposing specific phantoms, as CDMAM, in such systems. Nevertheless, this task is hard-working and time consuming, besides to be subject to a significant dependence of the observer, reducing the measurements accuracy. Accordingly, the purpose of this work is the development of a software to assist in the professional testing, reducing the subjectivity due to the observers and correlating the automated readings with the human visual system, without the need to make the correction of the results, as is done in many studies in the literature. For this, we used 57 images obtained for five CR systems and a method of detection based on circular correlators filters. The correlation with human vision was based on the Weber\'s parameters which describe the behavior of the visual system to discriminate the contrast in digital images. The classification of the image discs between visible or not visible was made from a data mining tool known as WEKA (Waikato Environment for Knowledge Analysis) associated with the J48 algorithm which promotes the construction of decision tree models. The result of the decision trees implementation was a system to aid the specialist, reinforcing the integrity of the assessment using stable results, easily interpreted, and reaching accuracies of up to 95%.

Η βελτιστοποίηση της ποιότητας των υπηρεσιών στο χώρο της υγείας είναι επιτακτική στις μέρες μας. Στο χώρο της Ακτινοφυσικής συλλέγεται μεγάλος αριθμός δεδομένων από τη χρήση τυποποιημένων Πρωτοκόλλων Ποιοτικών Ελέγχων, τα αποτελέσματα των οποίων θα μπορούσαν να παρέχουν πολύτιμη πληροφορία για όλες τις σχετικές διεργασίες. Η ανάπτυξη εξειδικευμένων προγραμμάτων εκπαίδευσης των επαγγελματιών υγείας καθιστά αναγκαία την πιστοποίησή τους ώστε να διασφαλίζεται η ποιότητα σπουδών που προσφέρουν. Η χρήση του ηλεκτρονικού εργαλείου QS-PRO (Quality System Processes), ενός γενικευμένου εργαλείου λογισμικού για εφαρμογές που σχετίζονται με ποιότητα των υπηρεσιών συνέβαλλε στην ανάπτυξη συστημάτων ποιότητας σε δύο πεδία, αυτό της διασφάλισης ποιότητας στις διαδικασίες Ποιοτικών Ελέγχων στη Μαστογραφία καθώς και της διαχείρισης ποιότητας στο Μεταπτυχιακό Πρόγραμμα Σπουδών στη Βιοϊατρική Τεχνολογία. Συνοπτικά, το εργαλείο διευκόλυνε στην ανάπτυξη μιας δομής διεργασιών και διαδικασιών που τεκμηριώνονται επαρκώς ώστε να χρησιμοποιηθούν για τους σκοπούς ποιότητας που έχουν τεθεί. Συγκεκριμένα, η ηλεκτρονική έκδοση του Ευρωπαϊκού Πρωτοκόλλου Ποιοτικών Ελέγχων στη Μαστογραφία χαρακτηρίζεται από την αποτελεσματική χαρτογράφηση των ολοκληρωμένων συνεδριών ποιοτικών ελέγχων με καθορισμένες μεταβλητές (μετρήσιμες παραμέτρους και αποτελέσματα) που μπορεί να χρησιμοποιηθεί σε ολοκληρωμένα προγράμματα ελέγχων μονάδων μαστογραφίας. Το Εγχειρίδιο Συστήματος Διαχείρισης Ποιότητας για το Μεταπτυχιακό Πρόγραμμα Σπουδών στη Βιοϊατρική Τεχνολογία αποτελεί έναν οδηγό για όλους όσους συμμετέχουν στην υλοποίηση του προγράμματος και μέσα από τις προσδιορισμένες διαδικασίες μέτρησης και βελτίωσης της ικανοποίησης των φοιτητών και των διδασκόντων των συνεργαζόμενων πανεπιστημίων οδηγεί στη βελτίωση του και ταυτόχρονα στην πιστοποίηση του προγράμματος κατά ISO-9001. / Nowadays, optimization of health services is imperative. Large data sets collected through standardised Quality Control Protocols can provide valuable information cornering the related processes. On the other hand, the development of highly specialised educational programs for health professionals has rendered their certification necessary in order to ensure the quality of the offered services. The adoption of the electronic tool QS-PRO (Quality System Processes) - a standard software tool used for quality applications in services- has significantly contributed to the development of quality systems in two fields: Quality Assurance in Quality Control procedures in Mammography and Quality Management of the European Postgraduate Program on Biomedical Engineering. In short, the tool facilitated the creation of a process structure that is well documented in order to be further applied for reaching already-set quality objectives. More specifically, the electronic version of the European Protocol of Quality Control in Mammography features an effective mapping of complete quality control sessions with specified variables (measurable parameters and outcomes) aimed for further use in integrated quality control trials. The Quality System Manual of the European Postgraduate Program on Biomedical Engineering constitutes a comprehensive guide for all course participants; through measurements and improvements in overall satisfaction levels (by students, staff and collaborating institutions) the aim is to improve the program itself and eventually lead to its certification according to ISO-9001 standards.