<p>Bakterije koje kolonizuju želudac (Gastrospirillum spp. i Helicobacter spp.) su izolovane kod čoveka i nekoliko animalnih vrsta, uključujući i svinje. Gastritis je rezultat prirodne ili eksperimentalno izazvane infekcije sa H. pylori kod čoveka i konvencionalnih prasića. Kod obe vrste (čovek i svinja), infekcija sa H. pylori pokreće inflamatorni odgovor organizma, međutim postoje razlike u ćelijskoj populaciji u inflamatornom infiltratu. Cilj istraživanja ove disertaciji je identifikacija bakterije Helicobacter spp., različite morfologije (Helicobacter-like organisms and Gastrospirillum-like organisms), kao i patohistolo&scaron;ki pregled i evaluacija gastritisa svinja uzgajanih na intenzivni i ekstenzivni način. Uzeti su uzorci mukoze pars oesophagea, fundusa i pilorusa. Za identifikaciju bakterije Helicobacter spp. kori&scaron;ćene su dve metode bojenja: Loefflermethylene blue i modifikovana Giemsa. Za histolo&scaron;ko ispitivanje, uzorci su obojeni i hematoksilin eozinom (H&amp;E). Stepen gastritisa je određen prema Sidnejskom sistemu za klasifikaciju gastritisa. U humanoj a i u veterinarskoj patologiji, dobro je poznata činjenica o različitoj patogenosti različitih bakterija Helicobacter vrsta. Helicobacter bakterije izolovane iz želuca svinja pripadaju različitim vrstama ovog roda i međusobno se bitno razlikuju kako po patogenosti, tako i po virulentnosti. Tako na primer, Helicobacter&ndash;like bakterije koje su okarakterisane kao visoko patogene, mogu izazvati ulceracije ezofagealnog ili glandularnog dela želuca, gastritis ozbiljnog stepena i formiranje limfoidnih folikula. Rezultati na&scaron;eg istraživanja pokazuju da je stepen gastritisa veći u piloričnoj mukozi HLO-pozitivnih svinja u poređenju sa vrednostima GLO-pozitivnih svinja. Nije postojala pozitivna korelacija između infekcije bakterijama GLO morfologije i ulceracija. Za razliku od perzistentnih infekcija sa H. pylori kod ljudi kod kojih je te&scaron;ka glandularna atrofija udružena sa intestinalnom metaplazijom veoma česta, kod ispitivanih svinja iz</p><p><br /><br />intenzivnog i ekstenzivnog načina uzgoja nisu potvrđeni slučajevi atrofičnog gastritisa i intestinalne metaplazije. Konvencionalne svinje mogu poslužiti kao animalni model infekcije sa H. pylori jer su svinje u funkcionalnom smislu monogastrične životinje po anatomskim i fiziolo&scaron;kim karakteristikama, vrlo slične čoveku. Takođe, patogeneza infekcije je veoma slična kao kod čoveka. Navedene činjenice podržavaju mogućnost upotrebe ovog modela u daljem istraživanju patogeneze nastanka Helicobacter spp. gastritisa. Rezultati ovog istraživanja pružaju dodatni dokaz da HLO mogu biti faktor koji igra krucijalnu ulogu u patogenezi gastritisa kod svinja.&nbsp;<br />Datum</p> / <p>Bacteria that colonize the stomach (Helicobacter spp. and Gastrospirillum spp.) are isolated from humans and several animal species, including pigs. Gastritis is the result of a natural or experimental induced infection with H. pylori in humans and conventionally pigs. In both, humans and pigs, the infection with H. pylori elicited inflammatory response, but there are differences between populations of inflammatory cells. The aims of this dissertation are to identify&nbsp; spp. with two different morphology (Helicobacter-like organisms and Gastrospirillumlike organisms), as well as histolopathological examination and evaluation of gastritis score of gastric mucosa of pigs in intensive and extensive production. Biopsy samples were taken from the pars oesophagea, fundic and pyloric mucosa. For identification of Helicobacter species morphology we used two stain methods: Loeffler-methylene blue and modified Giemsa. All tissue sections were stained with hematoxylin and eosin (H&amp;E) for histopathological evaluation. The severity of gastritis was scored to the Sydney System for the classification of gastritis. In human as well as in veterinary pathology, the fact of the different pathogenicity of various Helicobacter species is well known. The Helicobacter spp. isolated from stomach mucosa of pigs which belong to different genus, differ significantly in both, pathogenicity and virulence. Helicobacter pylori-like bacteria characterised as high pathogenic, has been associated with ulceration of the oesophageal or glandular portion of the stomach, severe gastritis and formation of lymphoid follicles. On the contrast, infection with Helicobacter heilmannii, which has been shown to have low pathogenicity was accompanied by only mild gastritis and no ulceration. The results of current study suggested that the average gastritis score was higher in HLO-positive pyloric mucosa, compared</p><p><br /><br />with the GLO-positive pyloric mucosa. There was signifficance between HLO-positive and HLO-negative pyloric mucosa in both, intensive and extensive production. There was no correlation between GLO-positive mucosa and ulceration. In contrast to persistent H. pylori infection in humans in which severe glandular atrophy associated with intestinal metaplasia is very common, in examined pigs from intensive and extensive breeding, no samples exhibited histological features characteristic for atrophic gastritis and intestinal metaplasia have been confirmed in pigs of both production systems. The conventional piglets as an animal model of the human H. pylori infection offers advantages of a functional monogastric animal with gastric anatomic and physiologic characteristics similar to those of humans. Moreover, the infection and pathogenesis is similar to that in humans. These facts support the usefulness of this model in further research on the pathogenic mechanisms of Helicobacter spp. associated gastritis. Our findings provide further evidence that HLO can be one of the factors that playing a crucial role in the pathogenesis of gastritis in pigs.<br />Accepted</p>

Syfte – Syftet med studien är att bidra till en ökad förståelse för samband mellan effektivitetsmått och lagerservicenivå. För att uppnå syftet har studien dels undersöktklassificeringskriteriums användbarhet i lagerverksamhet, dels olika dimensioneringsmetoders påverkan på effektivitetsmått. För att besvara syftet har två frågeställningar formulerats:(3) Hur kan en artikelklassificering nyttjas för att planera lagerhållning?(4) Hur påverkar olika dimensioneringsmetoder en verksamhets olika logistiska effektivitetsmått? Metod – En fallstudie genomfördes för att verifiera det teoretiska ramverket, där teorier kopplade till ämnesområdet samlats in samt litteraturstudie utförts för att besvara studiens frågeställningar. I genomförandet av fallstudien samlades empiri in med hjälp av historiska data från affärssystemet, vilket tillsammans med teori utgjorde grunden för analysen. Resultat – Studien fann att en flerdimensionell artikelklassificering kan nyttjas som underlag om kriterium utses efter lämpligt ändamål. Av de statistiska metoderna visade SERV2 störst förändring på lagernivåerna och var även den metod som skapade störst effekt på effektivitetsmåtten och därmed genererade störst resultatförbättring. Studienpåvisades en koppling mellan sänkt servicenivå och sänkt kapitalbindning och även mellan sänkt servicenivå och en ökad lageromsättningshastighet. Implikationer – Studien erbjuder en samlad bild på hur en ABC- analys kan tillämpas samt nyttjas för att planera lagerhållning. Vidare erbjuder studien en bild av hur de statistiska dimensioneringsteknikerna kan påverka olika logistiska effektivitetsmått. Studien kan användas som underlag för företaget samt stöd för vidare arbeten och projekt. Begränsningar – Avgränsningar i studien är på verksamhets-, mått och mätprocessnivå. På verksamhetsnivå har följande studie avgränsats till området logistik. På måttnivåberörs de interna mått som bedöms via outboundmåtten. Effektivitetsmåtten sombehandlas är kapitalbindning, servicenivå och lageromsättningshastighet. Forslund &amp; Mattsson (2017) presenterar en mätprocess på fem steg, där studien endast omfattar steg fyra, vilken är ”mäta”. Nyckelord – Effektivitetsmått, Lagerservicenivå, Artikelklassificering, Dimensioneringsmetoder / Purpose – The purpose of the thesis is to contribute to a greater understanding of the correlation between logistics metrics and service level. To fulfill the purpose, the thesis has partly studied the usefulness of criteria for classification in warehouse operations, partly studied the impact of different stock dimensioning methods on metrics. To answer the purpose, two research questions has been formulated:(1) How can an item classification be used to plan inventory? (2) How does different stock dimensioning techniques affect a company’s different logistical metrics?  Method – A case study was conducted to verify the theoretical framework, where theories related to the subject area were collected and a literature study was performed to answer the study's research questions. While conducting the case study, empirical data were collected using historical data from the business system, which together with literature, constituted the groundwork of the analysis. Findings – The thesis found that a double ABC- analysis can be used as a good basis if criteria are chosen with regards to the suitable purpose. Of the statistical methods, SERV2 showed the largest change in inventory levels and was also the method that created the greatest effect on the metrics and thus, generated the greatest improvement in profit. The thesis demonstrated a link between reduced service level and reduced tied up capital, and between reduced service level and an increased inventory turnover rate. Implications – The thesis offers an overview of how an ABC- analysis can be applied and used to plan inventory. Furthermore, the thesis shows how the statistical dimensioning techniques can affect different logistical efficiency measures. The study can be used as framework for the case company as well as support for new projects. Limitations – Delimitations in the thesis are at a business, measure, and measure process level. At a business level, the thesis has been limited to the area of logistics. Where focus is on the internal measurements that are being assessed by outbound measurements. The metrics that are included in the study are tied up capital, service leveland inventory turnover rate, where the tied-up capital is limited to capital in stock. Forslund &amp; Mattsson (2017) present a five-step measurement process, where the thesis only covers step four, which is “measurement”. Keywords – Metrics, Service level, Criteria for classification, Stock dimensioning techniques

Com o aumento da capacidade de armazenamento, as bases de dados são cada vez maiores e, em muitas situações, apenas um pequeno subconjunto de itens de dados pode ser rotulado. Isto acontece devido ao processo de rotulagem ser frequentemente caro, demorado e necessitar do envolvimento de especialistas humanos. Com isso, diversos algoritmos semissupervisionados foram propostos, mostrando que é possível obter bons resultados empregando conhecimento prévio, relativo à pequena fração de dados rotulados. Dentre esses algoritmos, os que têm ganhado bastante destaque na área têm sido aqueles baseados em redes. Tal interesse, justifica-se pelas vantagens oferecidas pela representação via redes, tais como, a possibilidade de capturar a estrutura topológica dos dados, representar estruturas hierárquicas, bem como modelar manifolds no espaço multi-dimensional. No entanto, existe uma grande quantidade de dados representados em tabelas atributo-valor, nos quais não se poderia aplicar os algoritmos baseados em redes sem antes construir uma rede a partir desses dados. Como a geração das redes, assim como sua relação com o desempenho dos algoritmos têm sido pouco estudadas, esta tese investigou esses aspectos e propôs novos métodos para construção de redes, considerando características ainda não exploradas na literatura. Foram propostos três métodos para construção de redes com diferentes topologias: 1) S-kNN (Sequential k Nearest Neighbors), que gera redes regulares; 2) GBILI (Graph Based on the Informativeness of Labeled Instances) e RGCLI (Robust Graph that Considers Labeled Instances), que exploram os rótulos disponíveis gerando redes com distribuição de grau lei de potência; 3) GBLP (Graph Based on Link Prediction), que se baseia em medidas de predição de links gerando redes com propriedades mundo-pequeno. As estratégias de construção de redes propostas foram analisadas por meio de medidas de teoria dos grafos e redes complexas e validadas por meio da classificação semissupervisionada. Os métodos foram aplicados em benchmarks da área e também na classificação de gêneros musicais e segmentação de imagens. Os resultados mostram que a topologia da rede influencia diretamente os algoritmos de classificação e as estratégias propostas alcançam boa acurácia. / With the increase capacity of storage, databases are getting larger and, in many situations, only a small subset of data items can be labeled. This happens because the labeling process is often expensive, time consuming and requires the involvement of human experts. Hence, several semi-supervised algorithms have been proposed, showing that it is possible to achieve good results by using prior knowledge. Among these algorithms, those based on graphs have gained prominence in the area. Such interest is justified by the benefits provided by the representation via graphs, such as the ability to capture the topological structure of the data, represent hierarchical structures, as well as model manifold in high dimensional spaces. Nevertheless, most of available data is represented by attribute-value tables, making necessary the study of graph construction techniques in order to convert these tabular data into graphs for applying such algorithms. As the generation of the weight matrix and the sparse graph, and their relation to the performance of the algorithms have been little studied, this thesis investigated these aspects and proposed new methods for graph construction with characteristics litle explored in the literature yet. We have proposed three methods for graph construction with different topologies: 1) S-kNN (Sequential k Nearest Neighbors) that generates regular graphs; 2) GBILI (Graph Based on the informativeness of Labeled Instances) and RGCLI (Robust Graph that Considers Labeled Instances), which exploit the labels available generating power-law graphs; 3) GBLP (Graph Based on Link Prediction), which are based on link prediction measures and generates small-world graphs. The strategies proposed were analyzed by graph theory and complex networks measures and validated in semi-supervised classification tasks. The methods were applied in benchmarks of the area and also in the music genre classification and image segmentation. The results show that the topology of the graph directly affects the classification algorithms and the proposed strategies achieve good accuracy.

Com o aumento da capacidade de armazenamento, as bases de dados são cada vez maiores e, em muitas situações, apenas um pequeno subconjunto de itens de dados pode ser rotulado. Isto acontece devido ao processo de rotulagem ser frequentemente caro, demorado e necessitar do envolvimento de especialistas humanos. Com isso, diversos algoritmos semissupervisionados foram propostos, mostrando que é possível obter bons resultados empregando conhecimento prévio, relativo à pequena fração de dados rotulados. Dentre esses algoritmos, os que têm ganhado bastante destaque na área têm sido aqueles baseados em redes. Tal interesse, justifica-se pelas vantagens oferecidas pela representação via redes, tais como, a possibilidade de capturar a estrutura topológica dos dados, representar estruturas hierárquicas, bem como modelar manifolds no espaço multi-dimensional. No entanto, existe uma grande quantidade de dados representados em tabelas atributo-valor, nos quais não se poderia aplicar os algoritmos baseados em redes sem antes construir uma rede a partir desses dados. Como a geração das redes, assim como sua relação com o desempenho dos algoritmos têm sido pouco estudadas, esta tese investigou esses aspectos e propôs novos métodos para construção de redes, considerando características ainda não exploradas na literatura. Foram propostos três métodos para construção de redes com diferentes topologias: 1) S-kNN (Sequential k Nearest Neighbors), que gera redes regulares; 2) GBILI (Graph Based on the Informativeness of Labeled Instances) e RGCLI (Robust Graph that Considers Labeled Instances), que exploram os rótulos disponíveis gerando redes com distribuição de grau lei de potência; 3) GBLP (Graph Based on Link Prediction), que se baseia em medidas de predição de links gerando redes com propriedades mundo-pequeno. As estratégias de construção de redes propostas foram analisadas por meio de medidas de teoria dos grafos e redes complexas e validadas por meio da classificação semissupervisionada. Os métodos foram aplicados em benchmarks da área e também na classificação de gêneros musicais e segmentação de imagens. Os resultados mostram que a topologia da rede influencia diretamente os algoritmos de classificação e as estratégias propostas alcançam boa acurácia. / With the increase capacity of storage, databases are getting larger and, in many situations, only a small subset of data items can be labeled. This happens because the labeling process is often expensive, time consuming and requires the involvement of human experts. Hence, several semi-supervised algorithms have been proposed, showing that it is possible to achieve good results by using prior knowledge. Among these algorithms, those based on graphs have gained prominence in the area. Such interest is justified by the benefits provided by the representation via graphs, such as the ability to capture the topological structure of the data, represent hierarchical structures, as well as model manifold in high dimensional spaces. Nevertheless, most of available data is represented by attribute-value tables, making necessary the study of graph construction techniques in order to convert these tabular data into graphs for applying such algorithms. As the generation of the weight matrix and the sparse graph, and their relation to the performance of the algorithms have been little studied, this thesis investigated these aspects and proposed new methods for graph construction with characteristics litle explored in the literature yet. We have proposed three methods for graph construction with different topologies: 1) S-kNN (Sequential k Nearest Neighbors) that generates regular graphs; 2) GBILI (Graph Based on the informativeness of Labeled Instances) and RGCLI (Robust Graph that Considers Labeled Instances), which exploit the labels available generating power-law graphs; 3) GBLP (Graph Based on Link Prediction), which are based on link prediction measures and generates small-world graphs. The strategies proposed were analyzed by graph theory and complex networks measures and validated in semi-supervised classification tasks. The methods were applied in benchmarks of the area and also in the music genre classification and image segmentation. The results show that the topology of the graph directly affects the classification algorithms and the proposed strategies achieve good accuracy.

Цель работы – исследование задачи классификации фракции щебня, вывозимого с карьера, на основе моделей компьютерного зрения, по изображениям с внешних камер. Объектом исследования является изображения с камер кузова грузовика, заполненного щебнем, вывозимым с карьера. Рассматриваются основные модели компьютерного зрения, позволяющие детектировать и классифицировать фракцию щебня. Рассмотрены модели семейства YOLO, оценены метрики классификации применяемых моделей. Определена наиболее эффективная модель. / The aim of the work is to study the problem of classifying the fraction of crushed stone taken out of the quarry, based on computer vision models, using images from external cameras. The object of the study is images from the cameras of a truck body filled with crushed stone taken out of the quarry. The main models of computer vision that allow detecting and classifying the fraction of crushed stone are considered. The models of the YOLO family are considered, the classification metrics of the applied models are estimated. The most effective model is determined.

Topic of the work: study of the problem of classification of crushed stone fractions based on neural networks. Relevance: development of a neural network model for classifying the type of crushed stone fractions taken out of the quarry is due to the need to automate this process in order to improve the quality and speed of analysis, reduce the load on the operator. The object of the study is the problem of classifying digital images of crushed stone fractions in the back of a truck. The subject of the study is the architecture of neural networks for detection and classification of images using computer vision methods. Objective: study of the problem of classification of crushed stone fractions based on convolutional neural networks from images from an external camera. / Тема работы: исследование задачи классификации фракции щебня на основе нейронных сетей. Актуальность: разработка модели нейронной сети для классификации вида фракций щебня, вывозимого с карьера обусловлена необходимостью автоматизации данного процесса с целью повышения качества и скорости анализа, снижения нагрузки на оператора. Объект исследования – задача классификации цифровых изображений фракций щебня в кузове грузовика. Предмет исследования – архитектуры нейронных сетей для детекции и классификации изображений, с использованием методов компьютерного зрения. Цель: исследование задачи классификации фракции щебня на основе сверточных нейронных сетей по изображениям с внешней камеры.

This master's thesis is divided into three parts. In the first part I described P2P lending, its characteristics, basic concepts and practical implications. I also compared P2P market in the Czech Republic, UK and USA. The second part consists of theoretical basics for chosen methods of machine learning, which are naive bayes classifier, classification tree, random forest and logistic regression. I also described methods to evaluate the quality of classification models listed above. The third part is a practical one and shows the complete workflow of creating classification model, from data preparation to evaluation of model.

En los ultimos años el número de casos de ceguera se ha reducido significativamente. A pesar de este hecho, la Organización Mundial de la Salud estima que un 80% de los casos de pérdida de visión (285 millones en 2010) pueden ser evitados si se diagnostican en sus estadios más tempranos y son tratados de forma efectiva. Para cumplir esta propuesta se pretende que los servicios de atención primaria incluyan un seguimiento oftalmológico de sus pacientes así como fomentar campañas de cribado en centros proclives a reunir personas de alto riesgo. Sin embargo, estas soluciones exigen una alta carga de trabajo de personal experto entrenado en el análisis de los patrones anómalos propios de cada enfermedad. Por lo tanto, el desarrollo de algoritmos para la creación de sistemas de cribado automáticos juga un papel vital en este campo. La presente tesis persigue la identificacion automática del daño retiniano provocado por dos de las patologías más comunes en la sociedad actual: la retinopatía diabética (RD) y la degenaración macular asociada a la edad (DMAE). Concretamente, el objetivo final de este trabajo es el desarrollo de métodos novedosos basados en la extracción de características de la imagen de fondo de ojo y clasificación para discernir entre tejido sano y patológico. Además, en este documento se proponen algoritmos de pre-procesado con el objetivo de normalizar la alta variabilidad existente en las bases de datos publicas de imagen de fondo de ojo y eliminar la contribución de ciertas estructuras retinianas que afectan negativamente en la detección del daño retiniano. A diferencia de la mayoría de los trabajos existentes en el estado del arte sobre detección de patologías en imagen de fondo de ojo, los métodos propuestos a lo largo de este manuscrito evitan la necesidad de segmentación de las lesiones o la generación de un mapa de candidatos antes de la fase de clasificación. En este trabajo, Local binary patterns, perfiles granulométricos y la dimensión fractal se aplican de manera local para extraer información de textura, morfología y tortuosidad de la imagen de fondo de ojo. Posteriormente, esta información se combina de diversos modos formando vectores de características con los que se entrenan avanzados métodos de clasificación formulados para discriminar de manera óptima entre exudados, microaneurismas, hemorragias y tejido sano. Mediante diversos experimentos, se valida la habilidad del sistema propuesto para identificar los signos más comunes de la RD y DMAE. Para ello se emplean bases de datos públicas con un alto grado de variabilidad sin exlcuir ninguna imagen. Además, la presente tesis también cubre aspectos básicos del paradigma de deep learning. Concretamente, se presenta un novedoso método basado en redes neuronales convolucionales (CNNs). La técnica de transferencia de conocimiento se aplica mediante el fine-tuning de las arquitecturas de CNNs más importantes en el estado del arte. La detección y localización de exudados mediante redes neuronales se lleva a cabo en los dos últimos experimentos de esta tesis doctoral. Cabe destacar que los resultados obtenidos mediante la extracción de características "manual" y posterior clasificación se comparan de forma objetiva con las predicciones obtenidas por el mejor modelo basado en CNNs. Los prometedores resultados obtenidos en esta tesis y el bajo coste y portabilidad de las cámaras de adquisión de imagen de retina podrían facilitar la incorporación de los algoritmos desarrollados en este trabajo en un sistema de cribado automático que ayude a los especialistas en la detección de patrones anomálos característicos de las dos enfermedades bajo estudio: RD y DMAE. / In last years, the number of blindness cases has been significantly reduced. Despite this promising news, the World Health Organisation estimates that 80% of visual impairment (285 million cases in 2010) could be avoided if diagnosed and treated early. To accomplish this purpose, eye care services need to be established in primary health and screening campaigns should be a common task in centres with people at risk. However, these solutions entail a high workload for trained experts in the analysis of the anomalous patterns of each eye disease. Therefore, the development of algorithms for automatic screening system plays a vital role in this field. This thesis focuses on the automatic identification of the retinal damage provoked by two of the most common pathologies in the current society: diabetic retinopathy (DR) and age-related macular degeneration (AMD). Specifically, the final goal of this work is to develop novel methods, based on fundus image description and classification, to characterise the healthy and abnormal tissue in the retina background. In addition, pre-processing algorithms are proposed with the aim of normalising the high variability of fundus images and removing the contribution of some retinal structures that could hinder in the retinal damage detection. In contrast to the most of the state-of-the-art works in damage detection using fundus images, the methods proposed throughout this manuscript avoid the necessity of lesion segmentation or the candidate map generation before the classification stage. Local binary patterns, granulometric profiles and fractal dimension are locally computed to extract texture, morphological and roughness information from retinal images. Different combinations of this information feed advanced classification algorithms formulated to optimally discriminate exudates, microaneurysms, haemorrhages and healthy tissues. Through several experiments, the ability of the proposed system to identify DR and AMD signs is validated using different public databases with a large degree of variability and without image exclusion. Moreover, this thesis covers the basics of the deep learning paradigm. In particular, a novel approach based on convolutional neural networks is explored. The transfer learning technique is applied to fine-tune the most important state-of-the-art CNN architectures. Exudate detection and localisation tasks using neural networks are carried out in the last two experiments of this thesis. An objective comparison between the hand-crafted feature extraction and classification process and the prediction models based on CNNs is established. The promising results of this PhD thesis and the affordable cost and portability of retinal cameras could facilitate the further incorporation of the developed algorithms in a computer-aided diagnosis (CAD) system to help specialists in the accurate detection of anomalous patterns characteristic of the two diseases under study: DR and AMD. / En els últims anys el nombre de casos de ceguera s'ha reduït significativament. A pesar d'este fet, l'Organització Mundial de la Salut estima que un 80% dels casos de pèrdua de visió (285 milions en 2010) poden ser evitats si es diagnostiquen en els seus estadis més primerencs i són tractats de forma efectiva. Per a complir esta proposta es pretén que els servicis d'atenció primària incloguen un seguiment oftalmològic dels seus pacients així com fomentar campanyes de garbellament en centres regentats per persones d'alt risc. No obstant això, estes solucions exigixen una alta càrrega de treball de personal expert entrenat en l'anàlisi dels patrons anòmals propis de cada malaltia. Per tant, el desenrotllament d'algoritmes per a la creació de sistemes de garbellament automàtics juga un paper vital en este camp. La present tesi perseguix la identificació automàtica del dany retiniano provocat per dos de les patologies més comunes en la societat actual: la retinopatia diabètica (RD) i la degenaración macular associada a l'edat (DMAE) . Concretament, l'objectiu final d'este treball és el desenrotllament de mètodes novedodos basats en l'extracció de característiques de la imatge de fons d'ull i classificació per a discernir entre teixit sa i patològic. A més, en este document es proposen algoritmes de pre- processat amb l'objectiu de normalitzar l'alta variabilitat existent en les bases de dades publiques d'imatge de fons d'ull i eliminar la contribució de certes estructures retinianas que afecten negativament en la detecció del dany retiniano. A diferència de la majoria dels treballs existents en l'estat de l'art sobre detecció de patologies en imatge de fons d'ull, els mètodes proposats al llarg d'este manuscrit eviten la necessitat de segmentació de les lesions o la generació d'un mapa de candidats abans de la fase de classificació. En este treball, Local binary patterns, perfils granulometrics i la dimensió fractal s'apliquen de manera local per a extraure informació de textura, morfologia i tortuositat de la imatge de fons d'ull. Posteriorment, esta informació es combina de diversos modes formant vectors de característiques amb els que s'entrenen avançats mètodes de classificació formulats per a discriminar de manera òptima entre exsudats, microaneurismes, hemorràgies i teixit sa. Per mitjà de diversos experiments, es valida l'habilitat del sistema proposat per a identificar els signes més comuns de la RD i DMAE. Per a això s'empren bases de dades públiques amb un alt grau de variabilitat sense exlcuir cap imatge. A més, la present tesi també cobrix aspectes bàsics del paradigma de deep learning. Concretament, es presenta un nou mètode basat en xarxes neuronals convolucionales (CNNs) . La tècnica de transferencia de coneixement s'aplica per mitjà del fine-tuning de les arquitectures de CNNs més importants en l'estat de l'art. La detecció i localització d'exudats per mitjà de xarxes neuronals es du a terme en els dos últims experiments d'esta tesi doctoral. Cal destacar que els resultats obtinguts per mitjà de l'extracció de característiques "manual" i posterior classificació es comparen de forma objectiva amb les prediccions obtingudes pel millor model basat en CNNs. Els prometedors resultats obtinguts en esta tesi i el baix cost i portabilitat de les cambres d'adquisión d'imatge de retina podrien facilitar la incorporació dels algoritmes desenrotllats en este treball en un sistema de garbellament automàtic que ajude als especialistes en la detecció de patrons anomálos característics de les dos malalties baix estudi: RD i DMAE. / Colomer Granero, A. (2018). Fundus image analysis for automatic screening of ophthalmic pathologies [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/99745