Development of a tool for the construction of "ground truth" for complex color images with text

Aquesta memoria resumeix el treball de final de carrera d’Enginyeria Superior d’Informàtica. Explicarà les principals raons que han motivat el projecte així com exemples que il·lustren l’aplicació resultant. En aquest cas el software intentarà resoldre la actual necessitat que hi ha de tenir dades de Ground Truth per als algoritmes de segmentació de text per imatges de color complexes. Tots els procesos seran explicats en els diferents capítols partint de la definició del problema, la planificació, els requeriments i el disseny fins a completar la il·lustració dels resultats del programa i les dades de Ground Truth resultants.

How to improve the formal analytic reasoning and scientific motivation in the intellectual training of medical students

A review article of the The New England Journal of Medicine refers that almost a century ago, Abraham Flexner, a research scholar at the Carnegie Foundation for the Advancement of Teaching, undertook an assessment of medical education in 155 medical schools in operation in the United States and Canada. Flexner’s report emphasized the nonscientific approach of American medical schools to preparation for the profession, which contrasted with the university-based system of medical education in Germany. At the core of Flexner’s view was the notion that formal analytic reasoning, the kind of thinking integral to the natural sciences, should hold pride of place in the intellectual training of physicians. This idea was pioneered at Harvard University, the University of Michigan, and the University of Pennsylvania in the 1880s, but was most fully expressed in the educational program at Johns Hopkins University, which Flexner regarded as the ideal for medical education. (...)

Segmentació d'imatge de ressonància magnètica de pit utilitzant atlas probabilístic

La localització d'òrgans és un tòpic important en l'àmbit de la imatge mèdica per l'ajuda del tractament i diagnosi del càncer. Un exemple es pot trobar en la cal•libració de models farmacoquinètics. Aquesta pot ésser realitzada utilitzant un teixit de referència, on, per exemple en imatges de ressonància magnètica de pit, una correcta segmentació del múscul pectoral és necessària per a la detecció de signes de malignitat. Els mètodes de segmentació basat en atlas han estat altament avaluats en imatge de ressonància magnètica de cervell, obtenint resultats satisfactoris. En aquest projecte, en col•laboració amb el el Diagnostic Image Analysis Group de la Radboud University Nijmegen Medical Centre i la supervisió del Dr. N.Karssemeijer, es presenta la primera aproximació d'un mètode de segmentació basat en atlas per segmentar els diferents teixits visibles en imatges de ressonància magnètica (T1) del pit femení. L'atlas consisteix en 5 estructures (teixit greixòs, teixit dens, cor, pulmons i múscul pectoral) i ha estat utilitzat en un algorisme de segmentació Bayesià per tal de delinear les esmentades estructures. A més a més, s'ha dut a terme una comparació entre un mètode de registre global i un de local, utilitzats tant en la construcció de l'atlas com en la fase de segmentació, essent el primer el que ha presentat millors resultats en termes d'eficiència i precisió. Per a l'avaluació, s'ha dut a terme una comparació visual i numèrica entre les segmentacions obtingudes i les realitzades manualment pels experts col•laboradors. Pel que fa a la numèrica, s'ha emprat el coeficient de similitud de Dice ( mesura que dóna valors entre 0 i 1, on 0 significa no similitud i 1 similitud màxima) i s'ha obtingut una mitjana general de 0.8. Aquest resultat confirma la validesa del mètode presentat per a la segmentació d'imatges de ressonància magnètica del pit.

Mejora diagnóstica de hepatopatías de afectación difusa mediante técnicas de inteligencia artificial

The automatic diagnostic discrimination is an application of artificial intelligence techniques that can solve clinical cases based on imaging. Diffuse liver diseases are diseases of wide prominence in the population and insidious course, yet early in its progression. Early and effective diagnosis is necessary because many of these diseases progress to cirrhosis and liver cancer. The usual technique of choice for accurate diagnosis is liver biopsy, an invasive and not without incompatibilities one. It is proposed in this project an alternative non-invasive and free of contraindications method based on liver ultrasonography. The images are digitized and then analyzed using statistical techniques and analysis of texture. The results are validated from the pathology report. Finally, we apply artificial intelligence techniques as Fuzzy k-Means or Support Vector Machines and compare its significance to the analysis Statistics and the report of the clinician. The results show that this technique is significantly valid and a promising alternative as a noninvasive diagnostic chronic liver disease from diffuse involvement. Artificial Intelligence classifying techniques significantly improve the diagnosing discrimination compared to other statistics.

Detection of matchings in a sequence of underwater images through texture analysis

This paper presents an approach to ameliorate the reliability of the correspondence points relating two consecutive images of a sequence. The images are especially difficult to handle, since they have been acquired by a camera looking at the sea floor while carried by an underwater robot. Underwater images are usually difficult to process due to light absorption, changing image radiance and lack of well-defined features. A new approach based on gray-level region matching and selective texture analysis significantly improves the matching reliability

Automatic classification of breast density

A recent trend in digital mammography is computer-aided diagnosis systems, which are computerised tools designed to assist radiologists. Most of these systems are used for the automatic detection of abnormalities. However, recent studies have shown that their sensitivity is significantly decreased as the density of the breast increases. This dependence is method specific. In this paper we propose a new approach to the classification of mammographic images according to their breast parenchymal density. Our classification uses information extracted from segmentation results and is based on the underlying breast tissue texture. Classification performance was based on a large set of digitised mammograms. Evaluation involves different classifiers and uses a leave-one-out methodology. Results demonstrate the feasibility of estimating breast density using image processing and analysis techniques

Incongruence between test statistics and P values in medical papers

Given an observed test statistic and its degrees of freedom, one may compute the observed P value with most statistical packages. It is unknown to what extent test statistics and P values are congruent in published medical papers. Methods:We checked the congruence of statistical results reported in all the papers of volumes 409–412 of Nature (2001) and a random sample of 63 results from volumes 322–323 of BMJ (2001). We also tested whether the frequencies of the last digit of a sample of 610 test statistics deviated from a uniform distribution (i.e., equally probable digits).Results: 11.6% (21 of 181) and 11.1% (7 of 63) of the statistical results published in Nature and BMJ respectively during 2001 were incongruent, probably mostly due to rounding, transcription, or type-setting errors. At least one such error appeared in 38% and 25% of the papers of Nature and BMJ, respectively. In 12% of the cases, the significance level might change one or more orders of magnitude. The frequencies of the last digit of statistics deviated from the uniform distribution and suggested digit preference in rounding and reporting.Conclusions: this incongruence of test statistics and P values is another example that statistical practice is generally poor, even in the most renowned scientific journals, and that quality of papers should be more controlled and valued

Locating and extracting the textual content from complex colour images using techniques inspired by human perception

Los sistemas de radio cognitivos son una solución a la deficiente distribución del espectro inalámbrico de frecuencias. Usando acceso dinámico al medio, los usuarios secundarios pueden comunicarse en canales de frecuencia disponibles, mientras los usuarios asignados no están usando dichos canales. Un buen sistema de mensajería de control es necesario para que los usuarios secundarios no interfieran con los usuarios primarios en las redes de radio cognitivas. Para redes en donde los usuarios son heterogéneos en frecuencia, es decir, no poseen los mismos canales de frecuencia para comunicarse, el grupo de canales utilizado para transmitir información de control debe elegirse cuidadosamente. Por esta razón, en esta tesis se estudian las ideas básicas de los esquemas de mensajería de control usados en las redes de radio cognitivas y se presenta un esquema adecuado para un control adecuado para usuarios heterogéneos en canales de frecuencia. Para ello, primero se presenta una nueva taxonomía para clasificar las estrategias de mensajería de control, identificando las principales características que debe cumplir un esquema de control para sistemas heterogéneos en frecuencia. Luego, se revisan diversas técnicas matemáticas para escoger el mínimo número de canales por los cuales se transmite la información de control. Después, se introduce un modelo de un esquema de mensajería de control que use el mínimo número de canales y que utilice las características de los sistemas heterogéneos en frecuencia. Por último, se comparan diversos esquemas de mensajería de control en términos de la eficiencia de transmisión.

Searching patterns in painting images with computer vision techniques

This paper presents a pattern recognition method focused on paintings images. The purpose is construct a system able to recognize authors or art styles based on common elements of his work (here called patterns). The method is based on comparing images that contain the same or similar patterns. It uses different computer vision techniques, like SIFT and SURF, to describe the patterns in descriptors, K-Means to classify and simplify these descriptors, and RANSAC to determine and detect good results. The method are good to find patterns of known images but not so good if they are not.

Medicine and Science in a New Medical-surgical Context: The Royal College of Surgery of Barcelona (1760–1843)

Taking the Royal College of Barcelona (1760 -1843) as a case study this paper shows the development of modern surgery in Spain initiated by Bourbon Monarchy founding new kinds of institutions through their academic activities of spreading scientific knowledge. Antoni Gimbernat was the most famousinternationally recognised Spanish surgeon. He was trained as a surgeon at the Royal College of Surgery in Cadiz and was later appointed as professor of theAnatomy in the College of Barcelona. He then became Royal Surgeon of King Carlos IV and with that esteemed position in Madrid he worked resiliently to improve the quality of the Royal colleges in Spain. Learning human bodystructure by performing hands-on dissections in the anatomical theatre has become a fundamental element of modern medical education. Gimbernat favoured the study of natural sciences, the new chemistry of Lavoisier and experimental physics in the academic programs of surgery. According to the study of a very relevant set of documents preserved in the library, the so-called “juntas literarias”, among the main subjects debated in the clinical sessions was the concept of human beings and diseases in relation to the development of the new experimental sciences. These documents showed that chemistry andexperimental physics were considered crucial tools to understand the unexplained processes that occurred in the diseased and healthy human bodyand in a medico-surgical context. It is important to stress that through these manuscripts we can examine the role and the reception of the new sciences applied to healing arts.

Automated Segmentation of Cerebral Vasculature with Aneurysms in 3DRA and TOF-MRA using Geodesic Active Regions: an Evaluation Study

Purpose: To evaluate the suitability of an improved version of an automatic segmentation method based on geodesic active regions (GAR) for segmenting cerebral vasculature with aneurysms from 3D X-ray reconstruc-tion angiography (3DRA) and time of °ight magnetic resonance angiography (TOF-MRA) images available in the clinical routine.Methods: Three aspects of the GAR method have been improved: execution time, robustness to variability in imaging protocols and robustness to variability in image spatial resolutions. The improved GAR was retrospectively evaluated on images from patients containing intracranial aneurysms in the area of the Circle of Willis and imaged with two modalities: 3DRA and TOF-MRA. Images were obtained from two clinical centers, each using di®erent imaging equipment. Evaluation included qualitative and quantitative analyses ofthe segmentation results on 20 images from 10 patients. The gold standard was built from 660 cross-sections (33 per image) of vessels and aneurysms, manually measured by interventional neuroradiologists. GAR has also been compared to an interactive segmentation method: iso-intensity surface extraction (ISE). In addition, since patients had been imaged with the two modalities, we performed an inter-modality agreement analysis with respect to both the manual measurements and each of the two segmentation methods. Results: Both GAR and ISE di®ered from the gold standard within acceptable limits compared to the imaging resolution. GAR (ISE, respectively) had an average accuracy of 0.20 (0.24) mm for 3DRA and 0.27 (0.30) mm for TOF-MRA, and had a repeatability of 0.05 (0.20) mm. Compared to ISE, GAR had a lower qualitative error in the vessel region and a lower quantitative error in the aneurysm region. The repeatabilityof GAR was superior to manual measurements and ISE. The inter-modality agreement was similar between GAR and the manual measurements. Conclusions: The improved GAR method outperformed ISE qualitatively as well as quantitatively and is suitable for segmenting 3DRA and TOF-MRA images from clinical routine.

Summarization of specialized discourse: the case of medical articles in Spanish

In this article, we present the current state of our work on a linguistically-motivated model for automatic summarization of medical articles in Spanish. The model takes into account the results of an empirical study which reveals that, on the one hand, domain-specific summarization criteria can often be derived from the summaries of domain specialists, and, on the other hand, adequate summarization strategies must be multidimensional, i.e., cover various types of linguistic clues. We take into account the textual, lexical, discursive, syntactic and communicative dimensions. This is novel in the field of summarization. The experiments carried out so far indicate that our model is suitable to provide high quality summarizations.

Are tax subsidies for private medical insurance self-financing? Evidence from a microsimulation model for outpatient and inpatient episodes

This paper analyses whether or not tax subsidies to private medicalinsurance are self-financing by means of a structural approach. Weconstruct a simulation routine based on a microeconometric discretechoice model that allows us to evaluate the impact of premium changeson the utilisation of outpatient and inpatient health care services. Wesimulate the 1999 Spanish tax reform that abolished the tax deductionfor expenditures on private health insurance using a representativesample of the Catalan population. Prior to this reform, foregone taxrevenue arising from deductions after the purchase of private insuranceamounted to 69.2 M. per year. In contrast, the elimination of thesubsidies to private policies is estimated to generate an extra costfor the public sector of about 8.9 M. per year.