Retinal Image Analysis Using Machine Vision

The topic of this thesis is studying how lesions in retina caused by diabetic retinopathy can be detected from color fundus images by using machine vision methods. Methods for equalizing uneven illumination in fundus images, detecting regions of poor image quality due toinadequate illumination, and recognizing abnormal lesions were developed duringthe work. The developed methods exploit mainly the color information and simpleshape features to detect lesions. In addition, a graphical tool for collecting lesion data was developed. The tool was used by an ophthalmologist who marked lesions in the images to help method development and evaluation. The tool is a general purpose one, and thus it is possible to reuse the tool in similar projects.The developed methods were tested with a separate test set of 128 color fundus images. From test results it was calculated how accurately methods classify abnormal funduses as abnormal (sensitivity) and healthy funduses as normal (specificity). The sensitivity values were 92% for hemorrhages, 73% for red small dots (microaneurysms and small hemorrhages), and 77% for exudates (hard and soft exudates). The specificity values were 75% for hemorrhages, 70% for red small dots, and 50% for exudates. Thus, the developed methods detected hemorrhages accurately and microaneurysms and exudates moderately.

Classifying minimally disabled multiple sclerosis patients from resting state functional connectivity.

Multiple sclerosis (MS), a variable and diffuse disease affecting white and gray matter, is known to cause functional connectivity anomalies in patients. However, related studies published to-date are post hoc; our hypothesis was that such alterations could discriminate between patients and healthy controls in a predictive setting, laying the groundwork for imaging-based prognosis. Using functional magnetic resonance imaging resting state data of 22 minimally disabled MS patients and 14 controls, we developed a predictive model of connectivity alterations in MS: a whole-brain connectivity matrix was built for each subject from the slow oscillations (<0.11Hz) of region-averaged time series, and a pattern recognition technique was used to learn a discriminant function indicating which particular functional connections are most affected by disease. Classification performance using strict cross-validation yielded a sensitivity of 82% (above chance at p<0.005) and specificity of 86% (p<0.01) to distinguish between MS patients and controls. The most discriminative connectivity changes were found in subcortical and temporal regions, and contralateral connections were more discriminative than ipsilateral connections. The pattern of decreased discriminative connections can be summarized post hoc in an index that correlates positively (ρ=0.61) with white matter lesion load, possibly indicating functional reorganisation to cope with increasing lesion load. These results are consistent with a subtle but widespread impact of lesions in white matter and in gray matter structures serving as high-level integrative hubs. These findings suggest that predictive models of resting state fMRI can reveal specific anomalies due to MS with high sensitivity and specificity, potentially leading to new non-invasive markers.

Self-Organising Maps and Correlation Analysis as a Tool to Explore Patterns in Excitation-Emission Matrix Data Sets and to Discriminate Dissolved Organic Matter Fluorescence Components

Dissolved organic matter (DOM) is a complex mixture of organic compounds, ubiquitous in marine and freshwater systems. Fluorescence spectroscopy, by means of Excitation-Emission Matrices (EEM), has become an indispensable tool to study DOM sources, transport and fate in aquatic ecosystems. However the statistical treatment of large and heterogeneous EEM data sets still represents an important challenge for biogeochemists. Recently, Self-Organising Maps (SOM) has been proposed as a tool to explore patterns in large EEM data sets. SOM is a pattern recognition method which clusterizes and reduces the dimensionality of input EEMs without relying on any assumption about the data structure. In this paper, we show how SOM, coupled with a correlation analysis of the component planes, can be used both to explore patterns among samples, as well as to identify individual fluorescence components. We analysed a large and heterogeneous EEM data set, including samples from a river catchment collected under a range of hydrological conditions, along a 60-km downstream gradient, and under the influence of different degrees of anthropogenic impact. According to our results, chemical industry effluents appeared to have unique and distinctive spectral characteristics. On the other hand, river samples collected under flash flood conditions showed homogeneous EEM shapes. The correlation analysis of the component planes suggested the presence of four fluorescence components, consistent with DOM components previously described in the literature. A remarkable strength of this methodology was that outlier samples appeared naturally integrated in the analysis. We conclude that SOM coupled with a correlation analysis procedure is a promising tool for studying large and heterogeneous EEM data sets.

Supervised localimage feature detection

This thesis is about detection of local image features. The research topic belongs to the wider area of object detection, which is a machine vision and pattern recognition problem where an object must be detected (located) in an image. State-of-the-art object detection methods often divide the problem into separate interest point detection and local image description steps, but in this thesis a different technique is used, leading to higher quality image features which enable more precise localization. Instead of using interest point detection the landmark positions are marked manually. Therefore, the quality of the image features is not limited by the interest point detection phase and the learning of image features is simplified. The approach combines both interest point detection and local description into one phase for detection. Computational efficiency of the descriptor is therefore important, leaving out many of the commonly used descriptors as unsuitably heavy. Multiresolution Gabor features has been the main descriptor in this thesis and improving their efficiency is a significant part. Actual image features are formed from descriptors by using a classifierwhich can then recognize similar looking patches in new images. The main classifier is based on Gaussian mixture models. Classifiers are used in one-class classifier configuration where there are only positive training samples without explicit background class. The local image feature detection method has been tested with two freely available face detection databases and a proprietary license plate database. The localization performance was very good in these experiments. Other applications applying the same under-lying techniques are also presented, including object categorization and fault detection.

Similarity measure based classification

Luokittelujärjestelmää suunniteltaessa tarkoituksena on rakentaa systeemi, joka pystyy ratkaisemaan mahdollisimman tarkasti tutkittavan ongelma-alueen. Hahmontunnistuksessa tunnistusjärjestelmän ydin on luokitin. Luokittelun sovellusaluekenttä on varsin laaja. Luokitinta tarvitaan mm. hahmontunnistusjärjestelmissä, joista kuvankäsittely toimii hyvänä esimerkkinä. Myös lääketieteen parissa tarkkaa luokittelua tarvitaan paljon. Esimerkiksi potilaan oireiden diagnosointiin tarvitaan luokitin, joka pystyy mittaustuloksista päättelemään mahdollisimman tarkasti, onko potilaalla kyseinen oire vai ei. Väitöskirjassa on tehty similaarisuusmittoihin perustuva luokitin ja sen toimintaa on tarkasteltu mm. lääketieteen paristatulevilla data-aineistoilla, joissa luokittelutehtävänä on tunnistaa potilaan oireen laatu. Väitöskirjassa esitetyn luokittimen etuna on sen yksinkertainen rakenne, josta johtuen se on helppo tehdä sekä ymmärtää. Toinen etu on luokittimentarkkuus. Luokitin saadaan luokittelemaan useita eri ongelmia hyvin tarkasti. Tämä on tärkeää varsinkin lääketieteen parissa, missä jo pieni tarkkuuden parannus luokittelutuloksessa on erittäin tärkeää. Väitöskirjassa ontutkittu useita eri mittoja, joilla voidaan mitata samankaltaisuutta. Mitoille löytyy myös useita parametreja, joille voidaan etsiä juuri kyseiseen luokitteluongelmaan sopivat arvot. Tämä parametrien optimointi ongelma-alueeseen sopivaksi voidaan suorittaa mm. evoluutionääri- algoritmeja käyttäen. Kyseisessä työssä tähän on käytetty geneettistä algoritmia ja differentiaali-evoluutioalgoritmia. Luokittimen etuna on sen joustavuus. Ongelma-alueelle on helppo vaihtaa similaarisuusmitta, jos kyseinen mitta ei ole sopiva tutkittavaan ongelma-alueeseen. Myös eri mittojen parametrien optimointi voi parantaa tuloksia huomattavasti. Kun käytetään eri esikäsittelymenetelmiä ennen luokittelua, tuloksia pystytään parantamaan.

Evaluation of an electronic nose to assess fruit ripeness

The main goal of our study was to see whether an artificial olfactory system can be used as a nondestructive instrument to measure fruit maturity. In order to make an objective comparison, samples measured with our electronic nose prototype were later characterized using fruit quality techniques. The cultivars chosen for the study were peaches, nectarines, apples, and pears. With peaches and nectarines, a PCA analysis on the electronic nose measurements helped to guess optimal harvest dates that were in good agreement with the ones obtained with fruit quality techniques. A good correlation between sensor signals and some fruit quality indicators was also found. With pears, the study addressed the possibility of classifying samples regarding their ripeness state after different cold storage and shelf-life periods. A PCA analysis showed good separation between samples measured after a shelf-life period of seven days and samples with four or less days. Finally, the electronic nose monitored the shelf-life ripening of apples. A good correlation between electronic nose signals and firmness, starch index, and acidity parameters was found. These results prove that electronic noses have the potential of becoming a reliable instrument to assess fruit ripeness.

Keraamisten laattojen luokittelu väripiirteiden avulla

Vaikka keraamisten laattojen valmistusprosessi onkin täysin automatisoitu, viimeinen vaihe eli laaduntarkistus ja luokittelu tehdään yleensä ihmisvoimin. Automaattinen laaduntarkastus laattojen valmistuksessa voidaan perustella taloudellisuus- ja turvallisuusnäkökohtien avulla. Tämän työn tarkoituksena on kuvata tutkimusprojektia keraamisten laattojen luokittelusta erilaisten väripiirteiden avulla. Oleellisena osana tutkittiin RGB- ja spektrikuvien välistä eroa. Työn teoreettinen osuus käy läpi aiemmin aiheesta tehdyn tutkimuksen sekä antaa taustatietoa konenäöstä, hahmontunnistuksesta, luokittelijoista sekä väriteoriasta. Käytännön osan aineistona oli 25 keraamista laattaa, jotka olivat viidestä eri luokasta. Luokittelussa käytettiin apuna k:n lähimmän naapurin (k-NN) luokittelijaa sekä itseorganisoituvaa karttaa (SOM). Saatuja tuloksia verrattiin myös ihmisten tekemään luokitteluun. Neuraalilaskenta huomattiin tärkeäksi työkaluksi spektrianalyysissä. SOM:n ja spektraalisten piirteiden avulla saadut tulokset olivat lupaavia ja ainoastaan kromatisoidut RGB-piirteet olivat luokittelussa parempia kuin nämä.

Self-Organising Maps and Correlation Analysis as a Tool to Explore Patterns in Excitation-Emission Matrix Data Sets and to Discriminate Dissolved Organic Matter Fluorescence Components

Dissolved organic matter (DOM) is a complex mixture of organic compounds, ubiquitous in marine and freshwater systems. Fluorescence spectroscopy, by means of Excitation-Emission Matrices (EEM), has become an indispensable tool to study DOM sources, transport and fate in aquatic ecosystems. However the statistical treatment of large and heterogeneous EEM data sets still represents an important challenge for biogeochemists. Recently, Self-Organising Maps (SOM) has been proposed as a tool to explore patterns in large EEM data sets. SOM is a pattern recognition method which clusterizes and reduces the dimensionality of input EEMs without relying on any assumption about the data structure. In this paper, we show how SOM, coupled with a correlation analysis of the component planes, can be used both to explore patterns among samples, as well as to identify individual fluorescence components. We analysed a large and heterogeneous EEM data set, including samples from a river catchment collected under a range of hydrological conditions, along a 60-km downstream gradient, and under the influence of different degrees of anthropogenic impact. According to our results, chemical industry effluents appeared to have unique and distinctive spectral characteristics. On the other hand, river samples collected under flash flood conditions showed homogeneous EEM shapes. The correlation analysis of the component planes suggested the presence of four fluorescence components, consistent with DOM components previously described in the literature. A remarkable strength of this methodology was that outlier samples appeared naturally integrated in the analysis. We conclude that SOM coupled with a correlation analysis procedure is a promising tool for studying large and heterogeneous EEM data sets.

Innate Immune Sensing of Fusarium culmorum by Mouse Dendritic Cells.

Chronic inhalation of grain dust is associated with asthma and chronic bronchitis in grain worker populations. Exposure to fungal particles was postulated to be an important etiologic agent of these pathologies. Fusarium species frequently colonize grain and straw and produce a wide array of mycotoxins that impact human health, necessitating an evaluation of risk exposure by inhalation of Fusarium and its consequences on immune responses. Data showed that Fusarium culmorum is a frequent constituent of aerosols sampled during wheat harvesting in the Vaud region of Switzerland. The aim of this study was to examine cytokine/chemokine responses and innate immune sensing of F. culmorum in bone-marrow-derived dendritic cells and macrophages. Overall, dendritic cells and macrophages responded to F. culmorum spores but not to its secreted components (i.e., mycotoxins) by releasing large amounts of macrophage inflammatory protein (MIP)-1α, MIP-1β, MIP-2, monocyte chemoattractant protein (MCP)-1, RANTES, and interleukin (IL)-12p40, intermediate amounts of tumor necrosis factor (TNF), IL-6, IL-12p70, IL-33, granulocyte colony-stimulating factor (G-CSF), and interferon gamma-induced protein (IP-10), but no detectable amounts of IL-4 and IL-10, a pattern of mediators compatible with generation of Th1 or Th17 antifungal protective immune responses rather than with Th2-dependent allergic responses. The sensing of F. culmorum spores by dendritic cells required dectin-1, the main pattern recognition receptor involved in β-glucans detection, but likely not MyD88 and TRIF-dependent Toll-like receptors. Taken together, our results indicate that F. culmorum stimulates potently innate immune cells in a dectin-1-dependent manner, suggesting that inhalation of F. culmorum from grain dust may promote immune-related airway diseases in exposed worker populations.

Sidelobe elimination for generalized synthetic discriminant functions by a two-filter correlation and subsequent postprocessing of the intensity distributions

One of the most important problems in optical pattern recognition by correlation is the appearance of sidelobes in the correlation plane, which causes false alarms. We present a method that eliminate sidelobes of up to a given height if certain conditions are satisfied. The method can be applied to any generalized synthetic discriminant function filter and is capable of rejecting lateral peaks that are even higher than the central correlation. Satisfactory results were obtained in both computer simulations and optical implementation.

New kernel functions and learning methods for text and data mining

Recent advances in machine learning methods enable increasingly the automatic construction of various types of computer assisted methods that have been difficult or laborious to program by human experts. The tasks for which this kind of tools are needed arise in many areas, here especially in the fields of bioinformatics and natural language processing. The machine learning methods may not work satisfactorily if they are not appropriately tailored to the task in question. However, their learning performance can often be improved by taking advantage of deeper insight of the application domain or the learning problem at hand. This thesis considers developing kernel-based learning algorithms incorporating this kind of prior knowledge of the task in question in an advantageous way. Moreover, computationally efficient algorithms for training the learning machines for specific tasks are presented. In the context of kernel-based learning methods, the incorporation of prior knowledge is often done by designing appropriate kernel functions. Another well-known way is to develop cost functions that fit to the task under consideration. For disambiguation tasks in natural language, we develop kernel functions that take account of the positional information and the mutual similarities of words. It is shown that the use of this information significantly improves the disambiguation performance of the learning machine. Further, we design a new cost function that is better suitable for the task of information retrieval and for more general ranking problems than the cost functions designed for regression and classification. We also consider other applications of the kernel-based learning algorithms such as text categorization, and pattern recognition in differential display. We develop computationally efficient algorithms for training the considered learning machines with the proposed kernel functions. We also design a fast cross-validation algorithm for regularized least-squares type of learning algorithm. Further, an efficient version of the regularized least-squares algorithm that can be used together with the new cost function for preference learning and ranking tasks is proposed. In summary, we demonstrate that the incorporation of prior knowledge is possible and beneficial, and novel advanced kernels and cost functions can be used in algorithms efficiently.

NLRP12 is a neutrophil-specific, negative regulator of in vitro cell migration but does not modulate LPS- or infection-induced NF-κB or ERK signalling.

NOD-like receptors (NLR) are a family of cytosolic pattern recognition receptors that include many key drivers of innate immune responses. NLRP12 is an emerging member of the NLR family that is closely related to the well-known inflammasome scaffold, NLRP3. Since its discovery, various functions have been proposed for NLRP12, including the positive regulation of dendritic cell (DC) and neutrophil migration and the inhibition of NF-κB and ERK signalling in DC and macrophages. We show here that NLRP12 is poorly expressed in murine macrophages and DC, but is strongly expressed in neutrophils. Using myeloid cells from WT and Nlrp12(-/)(-) mice, we show that, contrary to previous reports, NLRP12 does not suppress LPS- or infection-induced NF-κB or ERK activation in myeloid cells, and is not required for DC migration in vitro. Surprisingly, we found that Nlrp12 deficiency caused increased rather than decreased neutrophil migration towards the chemokine CXCL1 and the neutrophil parasite Leishmania major, revealing NLRP12 as a negative regulator of directed neutrophil migration under these conditions.

Sensing Gram-negative bacteria: a phylogenetic perspective.

Gram-negative bacteria represent a major group of pathogens that infect all eukaryotes from plants to mammals. Gram-negative microbe-associated molecular patterns include lipopolysaccharides and peptidoglycans, major immunostimulatory determinants across phyla. Recent advances have furthered our understanding of Gram-negative detection beyond the well-defined pattern recognition receptors such as TLR4. A B-type lectin receptor for LPS and Lysine-motif containing receptors for peptidoglycans were recently added to the plant arsenal. Caspases join the ranks of mammalian cytosolic immune detectors by binding LPS, and make TLR4 redundant for septic shock. Fascinating bacterial evasion mechanisms lure the host into tolerance or promote inter-bacterial competition. Our review aims to cover recent advances on bacterial messages and host decoding systems across phyla, and highlight evolutionarily recurrent strategies.

Correcció postural esportiva utilitzant un sensor Kinect

Aquest projecte s’emmarca dins de l’àmbit de la visió per computador, concretament en la utilització de dades de profunditat obtingudes a través d’un emissor i sensor de llum infraroja.El propòsit principal d’aquest projecte és mostrar com adaptar aquestes tecnologies, a l’abast de qualsevol particular, de forma que un usuari durant la pràctica d’una activitat esportiva concreta, rebi informació visual continua dels moviments i gestos incorrectes que està realitzant, en base a uns paràmetres prèviament establerts.L’objectiu d’aquest projecte consisteix en fer una lectura constant en temps real d’una persona practicant una selecció de diverses activitats esportives estàtiques utilitzant un sensor Kinect. A través de les dades obtingudes pel sensor Kinect i utilitzant les llibreries de “skeleton traking” proporcionades per Microsoft s’haurà d’interpretar les dades posturals obtingudes per cada tipus d’esport i indicar visualment i d’una manera intuïtiva els errors que està cometent en temps real, de manera que es vegi clarament a quina part del seu cos realitza un moviment incorrecte per tal de poder corregir-lo ràpidament. El entorn de desenvolupament que s’utilitza per desenvolupar aquesta aplicació es Microsoft Viusal Studio 2010.El llenguatge amb el qual es treballarà sobre Microsoft Visual Studio 2010 és C#