INTRODUÇÃO: A referência padrão para determinação do grau tumoral é a avaliação histopatológica. Entretanto, algumas limitações estão associadas com a correta graduação histopatológica dos gliomas: (a) erro inerente da amostra associada a biópsia estereotáxica, sendo que a porção mais maligna do tumor pode não estar incluída na amostra obtida; (b) dificuldade em obter uma gama suficiente de amostras se o tumor for inacessível ao cirurgião;(c) dinâmica própria dos tumores do sistema nervoso central, com diferenciação freqüente em graus de maior malignidade; (d) variabilidade entre patologistas; (e) inabilidade para avaliação de tecido tumoral residual após cirurgia redutora. Embora a ressonância magnética (RM) convencional seja a técnica de maior utilidade no diagnóstico e avaliação de tumores cerebrais, de forma isolada não possui acurácia em predizer o grau tumoral. Técnicas avançadas de RM, tais como caracterização de alterações metabólicas na espectroscopia de prótons (ERM), valores de volume sanguíneo cerebral relativo (VSCr) obtido com a perfusão por RM e imagem de difusão com o cálculo do coeficiente de difusão aparente (CDA), têm sido avaliadas como ferramentas diagnósticas na graduação prospectiva dos gliomas cerebrais. OBJETIVOS: Determinar quais são os parâmetros derivados da perfusão, difusão e espectroscopia que auxiliam a graduação tumoral. Determinar a sensibilidade, especificidade, valor preditivo positivo (VPP) e valor preditivo negativo (VPN) de cada método. Determinar se há alguma correlação entre os parâmetros utilizados na determinação do grau de malignidade tumoral. Determinar se a combinação destas técnicas aumenta a efetividade diagnóstica para graduação tumoral. MÉTODOS: 56 pacientes com tumores de origem glial, sendo 37 glioblastomas multiforme, 2 astrocitoma anaplásico, 1 oligoastrocitoma anaplásico, 3 oligoastrocitomas grau II, 9 astrocitomas grau II e 4 astrocitomas pilocíticos, foram submetidos a RM convencional, difusão, perfusão e ERM em aparelho 1,5 T (GE-Horizon LX9.1). O estudo da difusão foi realizado com sequência SE-EPI com tempo de repetição (TR)/tempo de eco (TE) = 8000/110,8ms. A perfusão foi adquirida com sequência GRE-EPI com TR/TE = 2000/34,7ms. Para o estudo de ERM utilizamos sequência multivoxel com TR/TE=1500/135ms. RESULTADOS: Diferenças significativas foram encontradas entre gliomas de baixo grau (BG) e alto grau (AG), com maiores valores de VSCr, Lip e Lip/Cr nos tumores de AG e maior valor de Cr nos tumores de BG. Tumores de AG apresentaram valores menores de CDA do que os de BG, porém sem diferença significativa. Correlação inversa foi observada entre valores de VSCr e CDA. O melhor parâmetro isolado para graduação tumoral foi o valor do VSCr. A combinação de VSCr e Cr, e VSCr e Lip, mostrou aumento da sensibilidade e especificidade na graduação dos gliomas. CONCLUSÕES: As alterações metabólicas utilizando a razão Lip/Cr, e os valores de Lip e Cr, assim como os valores de VSCr foram úteis na graduação tumoral. O melhor parâmetro para graduação tumoral foi o valor de VSCr. A combinação do VSCr e Cr, e VSCr e Lip aumenta a sensibilidade e especificidade na determinação da graduação dos gliomas / INTRODUCTION: The current reference standard for determining glioma grade is histopathologic assessment. However some limitations are associated with correct histopathologic grading of gliomas: (a) inherent sampling error associated with stereotactic biopsy and the risk of missing the most malignant portion of the tumor in the sampling; (b) difficulty in obtaining a representative range of samples if the tumor is inaccessible to the surgeon; (c) the dynamic nature of central nervous system tumors, with frequent dedifferentiation into more malignant grades; (d) interpathogist variability and (e) inability to evaluate residual tumor tissue after reductive surgery. Although MR imaging is the most useful radiologic technique in the diagnosis and evaluation of common brain tumors, it is not accurate enough in predicting tumor grade. Advanced MR imaging techniques such as characterization of metabolic changes in MR spectroscopy (MRS), relative cerebral blood volume (rCBV) measurements derived from perfusion MR imaging, and diffusion-weighted MR imaging with calculation of apparent diffusion coefficient (ADC), have been evaluated as diagnostic tool in prospective grading of cerebral gliomas. OBJECTIVES: To determine the usefulness of perfusion, diffusion, and spectroscopy values for glioma grading. To determine sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV), of each method. To determine if there is any correlation between parameters used in glioma grading. To determine whether the combination of these techniques can improve the diagnostic effectiveness of glioma grading. METHODS: 56 patients with glial tumors: 37 glioblastoma multiforme, 2 anaplastic astrocytoma, 1 anaplastic oligoastrocytoma, 3 oligoastrocytomas grade II, 9 astrocytomas grade II and 4 pylocitic astrocytomas. Patients underwent conventional MR, diffusion, perfusion and MRS, performed with a 1.5-T unit (GE-Horizon LX9.1). The diffusion-weighted images were acquired by using a SE-EPI imaging sequence with repetition time (TR)/echo time (TE) = 8000/110.8ms. Perfusion-weighted imaging were acquired by using GRE-EPI with TR/TE = 2000/34.7ms. Multivoxel MRS imaging were acquired by using TR/TE=1500/135ms. RESULTS: Significant differences were noted between low-grade (LG) and high-grade (HG) gliomas with higher values of rCBV, Lip, Lip/Cr in HG, and higher values of Cr in LG. HG tumors had lower ADC values than LG, but with no statistical significant difference. An inverse relationship was observed between rCBV and ADC values. The best performing single parameter for glioma grading was rCBV value. Combination of rCBV and Cr, and rCBV and Lip, showed improvement in sensitivity and specificity in grading of gliomas. CONCLUSIONS: Metabolic changes using Lip/Cr ratio and Lip and Cr, and rCBV values were useful in tumor grading. The best parameter for glioma grading was rCBV value. The combination of rCBV and Cr, and rCBV and Lip increased the sensitivity and specificity in determining glioma grade

INTRODUÇÃO: A referência padrão para determinação do grau tumoral é a avaliação histopatológica. Entretanto, algumas limitações estão associadas com a correta graduação histopatológica dos gliomas: (a) erro inerente da amostra associada a biópsia estereotáxica, sendo que a porção mais maligna do tumor pode não estar incluída na amostra obtida; (b) dificuldade em obter uma gama suficiente de amostras se o tumor for inacessível ao cirurgião;(c) dinâmica própria dos tumores do sistema nervoso central, com diferenciação freqüente em graus de maior malignidade; (d) variabilidade entre patologistas; (e) inabilidade para avaliação de tecido tumoral residual após cirurgia redutora. Embora a ressonância magnética (RM) convencional seja a técnica de maior utilidade no diagnóstico e avaliação de tumores cerebrais, de forma isolada não possui acurácia em predizer o grau tumoral. Técnicas avançadas de RM, tais como caracterização de alterações metabólicas na espectroscopia de prótons (ERM), valores de volume sanguíneo cerebral relativo (VSCr) obtido com a perfusão por RM e imagem de difusão com o cálculo do coeficiente de difusão aparente (CDA), têm sido avaliadas como ferramentas diagnósticas na graduação prospectiva dos gliomas cerebrais. OBJETIVOS: Determinar quais são os parâmetros derivados da perfusão, difusão e espectroscopia que auxiliam a graduação tumoral. Determinar a sensibilidade, especificidade, valor preditivo positivo (VPP) e valor preditivo negativo (VPN) de cada método. Determinar se há alguma correlação entre os parâmetros utilizados na determinação do grau de malignidade tumoral. Determinar se a combinação destas técnicas aumenta a efetividade diagnóstica para graduação tumoral. MÉTODOS: 56 pacientes com tumores de origem glial, sendo 37 glioblastomas multiforme, 2 astrocitoma anaplásico, 1 oligoastrocitoma anaplásico, 3 oligoastrocitomas grau II, 9 astrocitomas grau II e 4 astrocitomas pilocíticos, foram submetidos a RM convencional, difusão, perfusão e ERM em aparelho 1,5 T (GE-Horizon LX9.1). O estudo da difusão foi realizado com sequência SE-EPI com tempo de repetição (TR)/tempo de eco (TE) = 8000/110,8ms. A perfusão foi adquirida com sequência GRE-EPI com TR/TE = 2000/34,7ms. Para o estudo de ERM utilizamos sequência multivoxel com TR/TE=1500/135ms. RESULTADOS: Diferenças significativas foram encontradas entre gliomas de baixo grau (BG) e alto grau (AG), com maiores valores de VSCr, Lip e Lip/Cr nos tumores de AG e maior valor de Cr nos tumores de BG. Tumores de AG apresentaram valores menores de CDA do que os de BG, porém sem diferença significativa. Correlação inversa foi observada entre valores de VSCr e CDA. O melhor parâmetro isolado para graduação tumoral foi o valor do VSCr. A combinação de VSCr e Cr, e VSCr e Lip, mostrou aumento da sensibilidade e especificidade na graduação dos gliomas. CONCLUSÕES: As alterações metabólicas utilizando a razão Lip/Cr, e os valores de Lip e Cr, assim como os valores de VSCr foram úteis na graduação tumoral. O melhor parâmetro para graduação tumoral foi o valor de VSCr. A combinação do VSCr e Cr, e VSCr e Lip aumenta a sensibilidade e especificidade na determinação da graduação dos gliomas / INTRODUCTION: The current reference standard for determining glioma grade is histopathologic assessment. However some limitations are associated with correct histopathologic grading of gliomas: (a) inherent sampling error associated with stereotactic biopsy and the risk of missing the most malignant portion of the tumor in the sampling; (b) difficulty in obtaining a representative range of samples if the tumor is inaccessible to the surgeon; (c) the dynamic nature of central nervous system tumors, with frequent dedifferentiation into more malignant grades; (d) interpathogist variability and (e) inability to evaluate residual tumor tissue after reductive surgery. Although MR imaging is the most useful radiologic technique in the diagnosis and evaluation of common brain tumors, it is not accurate enough in predicting tumor grade. Advanced MR imaging techniques such as characterization of metabolic changes in MR spectroscopy (MRS), relative cerebral blood volume (rCBV) measurements derived from perfusion MR imaging, and diffusion-weighted MR imaging with calculation of apparent diffusion coefficient (ADC), have been evaluated as diagnostic tool in prospective grading of cerebral gliomas. OBJECTIVES: To determine the usefulness of perfusion, diffusion, and spectroscopy values for glioma grading. To determine sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV), of each method. To determine if there is any correlation between parameters used in glioma grading. To determine whether the combination of these techniques can improve the diagnostic effectiveness of glioma grading. METHODS: 56 patients with glial tumors: 37 glioblastoma multiforme, 2 anaplastic astrocytoma, 1 anaplastic oligoastrocytoma, 3 oligoastrocytomas grade II, 9 astrocytomas grade II and 4 pylocitic astrocytomas. Patients underwent conventional MR, diffusion, perfusion and MRS, performed with a 1.5-T unit (GE-Horizon LX9.1). The diffusion-weighted images were acquired by using a SE-EPI imaging sequence with repetition time (TR)/echo time (TE) = 8000/110.8ms. Perfusion-weighted imaging were acquired by using GRE-EPI with TR/TE = 2000/34.7ms. Multivoxel MRS imaging were acquired by using TR/TE=1500/135ms. RESULTS: Significant differences were noted between low-grade (LG) and high-grade (HG) gliomas with higher values of rCBV, Lip, Lip/Cr in HG, and higher values of Cr in LG. HG tumors had lower ADC values than LG, but with no statistical significant difference. An inverse relationship was observed between rCBV and ADC values. The best performing single parameter for glioma grading was rCBV value. Combination of rCBV and Cr, and rCBV and Lip, showed improvement in sensitivity and specificity in grading of gliomas. CONCLUSIONS: Metabolic changes using Lip/Cr ratio and Lip and Cr, and rCBV values were useful in tumor grading. The best parameter for glioma grading was rCBV value. The combination of rCBV and Cr, and rCBV and Lip increased the sensitivity and specificity in determining glioma grade

Cervical carcinoma is a major cause of morbidity and mortality among women worldwide. Histological subtype, lymphovascular space invasion and tumor grade could have a prognostic and predictive value for patients’ outcome and the knowledge of these histologic characteristics may influence clinical decision making. However, studies evaluating the diagnostic value of various biopsy techniques regarding these parameters of cervical cancer are scarce. We reviewed 318 cases of cervical carcinoma with available pathology reports from preoperative core needle biopsy (CNB) assessment and from final postoperative evaluation of the hysterectomy specimen. Setting the postoperative comprehensive pathological evaluation as reference, we analysed CNB assessment of histological tumor characteristics. In addition, we performed multivariable logistic regression to identify factors influencing the accuracy in identifying LVSI and tumor grade. CNB was highly accurate in discriminating histological subtype. Sensitivity and specificity were 98.8% and 89% for squamous cell carcinoma, 92.9% and 96.6% for adenocarcinoma, 33.3% and 100% in adenosquamous carcinoma respectively. Neuroendocrine carcinoma was always recognized correctly. The accuracy of the prediction of LVSI was 61.9% and was positively influenced by tumor size in preoperative magnetic resonance imaging and negatively influenced by strong peritumoral inflammation. High tumor grade (G3) was diagnosed accurately in 73.9% of cases and was influenced by histological tumor type. In conclusion, CNB is an accurate sampling technique for histological classification of cervical cancer and represents a reasonable alternative to other biopsy techniques.

Αντικείµενο της διατριβής είναι η ανάπτυξη νέων µεθοδολογιών εκµάθησης και σύγκλισης των Ασαφών Γνωστικών ∆ικτύων που προτείνονται για τη βελτίωση και προσαρµογή της συµπεριφοράς τους, καθώς και για την αύξηση της απόδοσής τους, αναδεικνύοντάς τα σε αποτελεσµατικά δυναµικά συστήµατα µοντελοποίησης. Τα νέα βελτιωµένα Ασαφή Γνωστικά ∆ίκτυα, µέσω της εκµάθησης και προσαρµογής των βαρών τους, έχουν χρησιµοποιηθεί στην ιατρική σε θέµατα διάγνωσης και υποστήριξης στη λήψη απόφασης, καθώς και σε µοντέλα βιοµηχανικών συστηµάτων που αφορούν τον έλεγχο διαδικασιών, µε πολύ ικανοποιητικά αποτελέσµατα. Στη διατριβή αυτή παρουσιάζονται, αξιολογούνται και εφαρµόζονται δύο νέοι αλγόριθµοι εκµάθησης χωρίς επίβλεψη των Ασαφών Γνωστικών ∆ικτύων, οι αλγόριθµοι Active Hebbian Learning (AHL) και Nonlinear Hebbian Learning (NHL), βασισµένοι στον κλασσικό αλγόριθµό εκµάθησης χωρίς επίβλεψη τύπου Hebb των νευρωνικών δικτύων, καθώς και µια νέα προσέγγιση εκµάθησης των Ασαφών Γνωστικών ∆ικτύων βασισµένη στους εξελικτικούς αλγορίθµους και πιο συγκεκριµένα στον αλγόριθµο Βελτιστοποίησης µε Σµήνος Σωµατιδίων και στον ∆ιαφοροεξελικτικό αλγόριθµο. Οι προτεινόµενοι αλγόριθµοι AHL και NHL στηρίζουν νέες µεθοδολογίες εκµάθησης για τα ΑΓ∆ που βελτιώνουν τη λειτουργία, και την αξιοπιστία τους, και που παρέχουν στους εµπειρογνώµονες του εκάστοτε προβλήµατος που αναπτύσσουν το ΑΓ∆, την εκµάθηση των παραµέτρων για τη ρύθµιση των αιτιατών διασυνδέσεων µεταξύ των κόµβων. Αυτοί οι τύποι εκµάθησης που συνοδεύονται από την σωστή γνώση του εκάστοτε προβλήµατος-συστήµατος, συµβάλλουν στην αύξηση της απόδοσης των ΑΓ∆ και διευρύνουν τη χρήση τους. Επιπρόσθετα µε τους αλγορίθµους εκµάθησης χωρίς επίβλεψη τύπου Hebb για τα ΑΓ∆, αναπτύσσονται και προτείνονται νέες τεχνικές εκµάθησης των ΑΓ∆ βασισµένες στους εξελικτικούς αλγορίθµους. Πιο συγκεκριµένα, προτείνεται µια νέα µεθοδολογία για την εφαρµογή του εξελικτικού αλγορίθµου Βελτιστοποίησης µε Σµήνος Σωµατιδίων στην εκµάθηση των Ασαφών Γνωστικών ∆ικτύων και πιο συγκεκριµένα στον καθορισµό των βέλτιστων περιοχών τιµών των βαρών των Ασαφών Γνωστικών ∆ικτύων. Με τη µεθοδο αυτή λαµβάνεται υπόψη η γνώση των εµπειρογνωµόνων για τον σχεδιασµό του µοντέλου µε τη µορφή περιορισµών στους κόµβους που µας ενδιαφέρουν οι τιµές των καταστάσεών τους, που έχουν οριστοί ως κόµβοι έξοδοι του συστήµατος, και για τα βάρη λαµβάνονται υπόψη οι περιοχές των ασαφών συνόλων που έχουν συµφωνήσει όλοι οι εµπειρογνώµονες. Έτσι θέτoντας περιορισµούς σε όλα τα βάρη και στους κόµβους εξόδου και καθορίζοντας µια κατάλληλη αντικειµενική συνάρτηση για το εκάστοτε πρόβληµα, προκύπτουν κατάλληλοι πίνακες βαρών (appropriate weight matrices) που µπορούν να οδηγήσουν το σύστηµα σε επιθυµητές περιοχές λειτουργίας και ταυτόχρονα να ικανοποιούν τις ειδικές συνθήκες- περιορισµούς του προβλήµατος. Οι δύο νέες µέθοδοι εκµάθησης χωρίς επίβλεψη που έχουν προταθεί για τα ΑΓ∆ χρησιµοποιούνται και εφαρµόζονται µε επιτυχία σε δυο πολύπλοκα προβλήµατα από το χώρο της ιατρικής, στο πρόβληµα λήψης απόφασης στην ακτινοθεραπεία και στο πρόβληµα κατηγοριοποίησης των καρκινικών όγκων της ουροδόχου κύστης σε πραγµατικές κλινικές περιπτώσεις. Επίσης όλοι οι προτεινόµενοι αλγόριθµοι εφαρµόζονται σε µοντέλα βιοµηχανικών συστηµάτων που αφορούν τον έλεγχο διαδικασιών µε πολύ ικανοποιητικά αποτελέσµατα. Οι αλγόριθµοι αυτοί, όπως προκύπτει από την εφαρµογή τους σε συγκεκριµένα προβλήµατα, βελτιώνουν το µοντέλο του ΑΓ∆, συµβάλλουν σε ευφυέστερα συστήµατα και διευρύνουν τη δυνατότητα εφαρµογής τους σε πραγµατικά και πολύπλοκα προβλήµατα. Η κύρια συνεισφορά αυτής της διατριβής είναι η ανάπτυξη νέων µεθοδολογιών εκµάθησης και σύγκλισης των Ασαφών Γνωστικών ∆ικτύων προτείνοντας δυο νέους αλγορίθµους µη επιβλεπόµενης µάθησης τύπου Hebb, τον αλγόριθµο Active Hebbian Learning και τον αλγόριθµο Nonlinear Hebbian Learning για την προσαρµογή των βαρών των διασυνδέσεων µεταξύ των κόµβων των Ασαφών Γνωστικών ∆ικτύων, καθώς και εξελικτικούς αλγορίθµους βελτιστοποιώντας συγκεκριµένες αντικειµενικές συναρτήσεις για κάθε εξεταζόµενο πρόβληµα. Τα νέα βελτιωµένα Ασαφή Γνωστικά ∆ίκτυα µέσω των αλγορίθµων προσαρµογής των βαρών τους έχουν χρησιµοποιηθεί για την ανάπτυξη ενός ∆ιεπίπεδου Ιεραρχικού Συστήµατος για την υποστήριξη λήψης απόφασης στην ακτινοθεραπεία, για την ανάπτυξη ενός διαγνωστικού εργαλείου για την κατηγοριοποίηση του βαθµού κακοήθειας των καρκινικών όγκων της ουροδόχου κύστης, καθώς και για την επίλυση βιοµηχανικών προβληµάτων για τον έλεγχο διαδικασιών. / The main contribution of this Dissertation is the development of new learning and convergence methodologies for Fuzzy Cognitive Maps that are proposed for the improvement and adaptation of their behaviour, as well as for the increase of their performance, electing them in effective dynamic systems of modelling. The new improved Fuzzy Cognitive Maps, via the learning and adaptation of their weights, have been used in medicine for diagnosis and decision-making, as well as to alleviate the problem of the potential uncontrollable convergence to undesired states in models of industrial process control systems, with very satisfactory results. In this Dissertation are presented, validated and implemented two new learning algorithms without supervision for Fuzzy Cognitive Maps, the algorithms Active Hebbian Learning (AHL) and Nonlinear Hebbian Learning (NHL), based on the classic unsupervised Hebb-type learning algorithm of neural networks, as well as a new approach of learning for Fuzzy Cognitive Maps based on the evolutionary algorithms and more specifically on the algorithm of Particles Swarm Optimization and on the Differential Evolution algorithm. The proposed algorithms AHL and NHL support new learning methodologies for FCMs that improve their operation, efficiency and reliability, and that provide in the experts of each problem that develop the FCM, the learning of parameters for the regulation (fine-tuning) of cause-effect relationships (weights) between the concepts. These types of learning that are accompanied with the right knowledge of each problem-system, contribute in the increase of performance of FCMs and extend their use. Additionally to the unsupervised learning algorithms of Hebb-type for the FCMs, are developed and proposed new learning techniques of FCMs based on the evolutionary algorithms. More specifically, it is proposed a new learning methodology for the application of evolutionary algorithm of Particle Swarm Optimisation in the adaptation of FCMs and more concretely in the determination of the optimal regions of weight values of FCMs. With this method it is taken into consideration the experts’ knowledge for the modelling with the form of restrictions in the concepts that interest us their values, and are defined as output concepts, and for weights are received the arithmetic values of the fuzzy regions that have agreed all the experts. Thus considering restrictions in all weights and in the output concepts and determining a suitable objective function for each problem, result appropriate weight matrices that can lead the system to desirable regions of operation and simultaneously satisfy specific conditions of problem. The first two proposed methods of unsupervised learning that have been suggested for the FCMs are used and applied with success in two complicated problems in medicine, in the problem of decision-making in the radiotherapy process and in the problem of tumor characterization for urinary bladder in real clinical cases. Also all the proposed algorithms are applied in models of industrial systems that concern the control of processes with very satisfactory results. These algorithms, as it results from their application in concrete problems, improve the model of FCMs, they contribute in more intelligent systems and they extend their possibility of application in real and complex problems. The main contribution of the present Dissertation is to develop new learning and convergence methodologies for Fuzzy Cognitive Maps proposing two new unsupervised learning algorithms, the algorithm Active Hebbian Learning and the algorithm Nonlinear Hebbian Learning for the adaptation of weights of the interconnections between the concepts of Fuzzy Cognitive Maps, as well as Evolutionary Algorithms optimizing concrete objective functions for each examined problem. New improved Fuzzy Cognitive Maps via the algorithms of weight adaptation have been used for the development of an Integrated Two-level hierarchical System for the support of decision-making in the radiotherapy, for the development of a new diagnostic tool for tumour characterization of urinary bladder, as well as for the solution of industrial process control problems.