La maladie d’Alzheimer est la première cause de démence chez les personnes âgées. Cette maladie est caractérisée par un déclin irréversible des fonctions cognitives. Les patients atteints par la maladie d’Alzheimer ont de sévères pertes de mémoire et ont de grandes difficultés à apprendre de nouvelles informations ce qui pose de gros problèmes dans leur vie quotidienne. À ce jour, cette maladie est diagnostiquée après que d’importantes altérations des structures du cerveaux apparaissent. De plus, aucune thérapie existe permettant de faire reculer ou de stopper la maladie. Le développement de nouvelles méthodes permettant la détection précoce de cette maladie est ainsi nécessaire. En effet, une détection précoce permettrait une meilleure prise en charge des patients atteints de cette maladie ainsi qu’une accélération de la recherche thérapeutique. Nos travaux de recherche portent sur l’utilisation de l’imagerie médicale, avec notamment l’imagerie par résonance magnétique (IRM) qui a démontrée ces dernières années son potentiel pour améliorer la détection et la prédiction de la maladie d’Alzheimer. Afin d’exploiter pleinement ce type d’imagerie, de nombreuses méthodes ont été proposées récemment. Au cours de nos recherches, nous nous sommes intéressés à un type de méthode en particulier qui est basé sur la correspondance de patchs dans de grandes bibliothèques d’images. Nous avons étudié ces méthodes à diverses échelles anatomiques c’est à dire, cerveaux entier, hippocampe, sous-champs de l’hippocampe) avec diverses modalités d’IRM (par exemple, IRM anatomique et imagerie de diffusion). Nous avons amélioré les performances de détection dans les stades les plus précoces avec l’imagerie par diffusion. Nous avons aussi proposé un nouveau schéma de fusion pour combiner IRM anatomique et imagerie de diffusion. De plus, nous avons montré que la correspondance de patchs était améliorée par l’utilisation de filtres dérivatifs. Enfin, nous avons proposé une méthode par graphe permettant de combiner les informations de similarité inter-sujet avec les informations apportées par la variabilité intra-sujet. Les résultats des expériences menées dans cette thèse ont montrées une amélioration des performances de diagnostique et de prognostique de la maladie d’Alzheimer comparé aux méthodes de l’état de l’art. / Alzheimer’s disease (AD) is the most common dementia leading to a neurodegenerative process and causing mental dysfunctions. According to the world health organization, the number of patients having AD will double in 20 years. Neuroimaging studies performed on AD patients revealed that structural brain alterations are advanced when the diagnosis is established. Indeed, the clinical symptoms of AD are preceded by brain changes. This stresses the need to develop new biomarkers to detect the first stages of the disease. The development of such biomarkers can make easier the design of clinical trials and therefore accelerate the development of new therapies. Over the past decades, the improvement of magnetic resonance imaging (MRI) has led to the development of new imaging biomarkers. Such biomarkers demonstrated their relevance for computer-aided diagnosis but have shown limited performances for AD prognosis. Recently, advanced biomarkers were proposed toimprove computer-aided prognosis. Among them, patch-based grading methods demonstrated competitive results to detect subtle modifications at the earliest stages of AD. Such methods have shown their ability to predict AD several years before the conversion to dementia. For these reasons, we have had a particular interest in patch-based grading methods. First, we studied patch-based grading methods for different anatomical scales (i.e., whole brain, hippocampus, and hippocampal subfields). We adapted patch-based grading method to different MRI modalities (i.e., anatomical MRI and diffusion-weighted MRI) and developed an adaptive fusion scheme. Then, we showed that patch comparisons are improved with the use of multi-directional derivative features. Finally, we proposed a new method based on a graph modeling that enables to combine information from inter-subjects’ similarities and intra-subjects’ variability. The conducted experiments demonstrate that our proposed method enable an improvement of AD detection and prediction.

Para avaliar as características clínicas e evolutivas em pacientes com formas cardíacas iniciais assintomáticas da doença de Chagas, realizou-se estudo prospectivo em 108 pacientes com idade entre 18 e 50 anos, atendidos entre abril e novembro de 2002 no ambulatório de doença de Chagas da Universidade Estadual de Londrina. Os pacientes foram submetidos a 1)avaliação clínica, 2)eletrocardiograma (ECG), 3)radiografia de tórax e cálculo do índice cardio-torácico (ICT), 4)eletrocardiografia dinâmica de 24 horas, 5)ecocardiografia bidimensional com Doppler tecidual e 6)dosagem plasmática do peptídeo natriurético tipo B (BNP). Os pacientes foram divididos em 3 grupos: 50 no GI - ECG e ICT normais, 31 no GIIA - ECG com alterações características de doença de Chagas e 25 no GIIB - ECG com alterações não características de doença de Chagas / To evaluate clinical and evolutive features in patients with initial asymptomatic cardiac Chagas' disease, a prospective study was carried out with 108 patients, age 18 and 50, at the Londrina State University Chagas' disease outpatient clinic, from April to November 2002. Patients were submitted to: 1) clinical evaluation, 2) electrocardiography (EKG), 3) chest radiography and cardiothoracic index (CTI), 4)24-hour dynamic electrocardiography, 5) bi-dimensional echocardiography with tissued Doppler imaging and 6) type-B natriuretic peptide (BNP) plasmatic dosage. Patients were divided into 3 groups: GI - normal EKG and CTI (50 patients), GIIA - EKG with typical Chagas' disease alterations (31 patients) and GIIB - EKG with alterations not characteristic of Chagas´ disease (25 patients)

Para avaliar as características clínicas e evolutivas em pacientes com formas cardíacas iniciais assintomáticas da doença de Chagas, realizou-se estudo prospectivo em 108 pacientes com idade entre 18 e 50 anos, atendidos entre abril e novembro de 2002 no ambulatório de doença de Chagas da Universidade Estadual de Londrina. Os pacientes foram submetidos a 1)avaliação clínica, 2)eletrocardiograma (ECG), 3)radiografia de tórax e cálculo do índice cardio-torácico (ICT), 4)eletrocardiografia dinâmica de 24 horas, 5)ecocardiografia bidimensional com Doppler tecidual e 6)dosagem plasmática do peptídeo natriurético tipo B (BNP). Os pacientes foram divididos em 3 grupos: 50 no GI - ECG e ICT normais, 31 no GIIA - ECG com alterações características de doença de Chagas e 25 no GIIB - ECG com alterações não características de doença de Chagas / To evaluate clinical and evolutive features in patients with initial asymptomatic cardiac Chagas' disease, a prospective study was carried out with 108 patients, age 18 and 50, at the Londrina State University Chagas' disease outpatient clinic, from April to November 2002. Patients were submitted to: 1) clinical evaluation, 2) electrocardiography (EKG), 3) chest radiography and cardiothoracic index (CTI), 4)24-hour dynamic electrocardiography, 5) bi-dimensional echocardiography with tissued Doppler imaging and 6) type-B natriuretic peptide (BNP) plasmatic dosage. Patients were divided into 3 groups: GI - normal EKG and CTI (50 patients), GIIA - EKG with typical Chagas' disease alterations (31 patients) and GIIB - EKG with alterations not characteristic of Chagas´ disease (25 patients)