Development and validation of a visual grading scale for assessing image quality of AP pelvis radiographic images.

OBJECTIVE: The aim of this article was to apply psychometric theory to develop and validate a visual grading scale for assessing the visual perception of digital image quality anteroposterior (AP) pelvis. METHODS: Psychometric theory was used to guide scale development. Seven phantom and seven cadaver images of visually and objectively predetermined quality were used to help assess scale reliability and validity. 151 volunteers scored phantom images, and 184 volunteers scored cadaver images. Factor analysis and Cronbach's alpha were used to assess scale validity and reliability. RESULTS: A 24-item scale was produced. Aggregated mean volunteer scores for each image correlated with the rank order of the visually and objectively predetermined image qualities. Scale items had good interitem correlation (≥0.2) and high factor loadings (≥0.3). Cronbach's alpha (reliability) revealed that the scale has acceptable levels of internal reliability for both phantom and cadaver images (α = 0.8 and 0.9, respectively). Factor analysis suggested that the scale is multidimensional (assessing multiple quality themes). CONCLUSION: This study represents the first full development and validation of a visual image quality scale using psychometric theory. It is likely that this scale will have clinical, training and research applications. ADVANCES IN KNOWLEDGE: This article presents data to create and validate visual grading scales for radiographic examinations. The visual grading scale, for AP pelvis examinations, can act as a validated tool for future research, teaching and clinical evaluations of image quality.

Image processing of false identity documents for forensic intelligence

Forensic intelligence has recently gathered increasing attention as a potential expansion of forensic science that may contribute in a wider policing and security context. Whilst the new avenue is certainly promising, relatively few attempts to incorporate models, methods and techniques into practical projects are reported. This work reports a practical application of a generalised and transversal framework for developing forensic intelligence processes referred to here as the Transversal model adapted from previous work. Visual features present in the images of four datasets of false identity documents were systematically profiled and compared using image processing for the detection of a series of modus operandi (M.O.) actions. The nature of these series and their relation to the notion of common source was evaluated with respect to alternative known information and inferences drawn regarding respective crime systems. 439 documents seized by police and border guard authorities across 10 jurisdictions in Switzerland with known and unknown source level links formed the datasets for this study. Training sets were developed based on both known source level data, and visually supported relationships. Performance was evaluated through the use of intra-variability and inter-variability scores drawn from over 48,000 comparisons. The optimised method exhibited significant sensitivity combined with strong specificity and demonstrates its ability to support forensic intelligence efforts.

Multidetector computed tomography angiography of the celiac trunk and hepatic arterial system: normal anatomy and main variants

Abstract Although digital angiography remains as the gold standard for imaging the celiac arterial trunk and hepatic arteries, multidetector computed tomography in association with digital images processing by software resources represents a useful tool particularly attractive for its non invasiveness. Knowledge of normal anatomy as well as of its variations is helpful in images interpretation and to address surgical planning on a case-by-case basis. The present essay illustrates several types of anatomical variations of celiac trunk, hepatic artery and its main branches, by means of digitally reconstructed computed tomography images, correlating their prevalence in the population with surgical implications.

Microcalcification evaluation in computer assisted diagnosis for digital mammography

In order to develop applications for z;isual interpretation of medical images, the early detection and evaluation of microcalcifications in digital mammograms is verg important since their presence is oftenassociated with a high incidence of breast cancers. Accurate classification into benign and malignant groups would help improve diagnostic sensitivity as well as reduce the number of unnecessa y biopsies. The challenge here is the selection of the useful features to distinguish benign from malignant micro calcifications. Our purpose in this work is to analyse a microcalcification evaluation method based on a set of shapebased features extracted from the digitised mammography. The segmentation of the microcalcificationsis performed using a fixed-tolerance region growing method to extract boundaries of calcifications with manually selected seed pixels. Taking into account that shapes and sizes of clustered microcalcificationshave been associated with a high risk of carcinoma based on digerent subjective measures, such as whether or not the calcifications are irregular, linear, vermiform, branched, rounded or ring like, our efforts were addressed to obtain a feature set related to the shape. The identification of the pammeters concerning the malignant character of the microcalcifications was performed on a set of 146 mammograms with their real diagnosis known in advance from biopsies. This allowed identifying the following shape-based parameters as the relevant ones: Number of clusters, Number of holes, Area, Feret elongation, Roughness, and Elongation. Further experiments on a set of 70 new mammogmms showed that the performance of the classification scheme is close to the mean performance of three expert radiologists, which allows to consider the proposed method for assisting the diagnosis and encourages to continue the investigation in the senseof adding new features not only related to the shape

Feature-based matching of underwater images

This work investigates performance of recent feature-based matching techniques when applied to registration of underwater images. Matching methods are tested versus different contrast enhancing pre-processing of images. As a result of the performed experiments for various dominating in images underwater artifacts and present deformation, the outperforming preprocessing, detection and description methods are proposed

Microstructural Brain Differences Predict Functional Hemodynamic Responses in a Reward Processing Task

Many aspects of human behavior are driven by rewards, yet different people are differentially sensitive to rewards and punishment. In this study, we showthat white matter microstructure inthe uncinate/inferiorfronto-occipitalfasciculus, defined byfractional anisotropy values derived from diffusion tensor magnetic resonance images, correlates with both short-term (indexed by the fMRI blood oxygenation level-dependent response to reward in the nucleus accumbens) and long-term (indexed by the trait measure sensitivity to punishment) reactivityto rewards.Moreover,traitmeasures of reward processingwere also correlatedwith reward-relatedfunctional activation in the nucleus accumbens. The white matter tract revealed by the correlational analysis connects the anterior temporal lobe with the medial and lateral orbitofrontal cortex and also supplies the ventral striatum. The pattern of strong correlations suggests an intimate relationship betweenwhitematter structure and reward-related behaviorthatmay also play a rolein a number of pathological conditions, such as addiction and pathological gambling.

Unsupervised visual object categorization

The number of digital images has been increasing exponentially in the last few years. People have problems managing their image collections and finding a specific image. An automatic image categorization system could help them to manage images and find specific images. In this thesis, an unsupervised visual object categorization system was implemented to categorize a set of unknown images. The system is unsupervised, and hence, it does not need known images to train the system which needs to be manually obtained. Therefore, the number of possible categories and images can be huge. The system implemented in the thesis extracts local features from the images. These local features are used to build a codebook. The local features and the codebook are then used to generate a feature vector for an image. Images are categorized based on the feature vectors. The system is able to categorize any given set of images based on the visual appearance of the images. Images that have similar image regions are grouped together in the same category. Thus, for example, images which contain cars are assigned to the same cluster. The unsupervised visual object categorization system can be used in many situations, e.g., in an Internet search engine. The system can categorize images for a user, and the user can then easily find a specific type of image.

Factors Affecting Consumer’s Illicit Purchase of Copyrighted Digital Work

Peer-to-Peer (P2P) technology has revolutionized file exchange activities besides enhancing processing power distribution. As such, this technology which is nowadays made freely available to all internet users also imposes a threat as it enables the illegal distribution of copyrighted digital work. P2P technology continuously evolves in a greater pace than copyright legislation, leading to compatibility gaps between the applicability of copyright law and the illicit file sharing and downloading. Such issues give high incentives to consumers to practise piracy using P2P systems with a low perception of risk towards prosecution, leading to substantial losses for copyright owners. This study focuses on developing insights for content owners on consumer behaviour towards piracy in Finland, where quantitative analyses are assessed using a data set based on a survey conducted by the Helsinki Institute for IT. The research approach investigates the significance of three fundamental areas in relation to evaluate consumer behaviour as: environmental-related factors, innovation-related factors and consumer-related. each of these are integrates concepts derived in previous theoretical models such as the technology acceptance model, theory of reasoned action, theory of planned behaviour, the issue-risk-judgement model and the Hunt & Vitell’s model.

Color ad spectral image assessment using novel quality and fidelity techniques

The ongoing development of the digital media has brought a new set of challenges with it. As images containing more than three wavelength bands, often called spectral images, are becoming a more integral part of everyday life, problems in the quality of the RGB reproduction from the spectral images have turned into an important area of research. The notion of image quality is often thought to comprise two distinctive areas – image quality itself and image fidelity, both dealing with similar questions, image quality being the degree of excellence of the image, and image fidelity the measure of the match of the image under study to the original. In this thesis, both image fidelity and image quality are considered, with an emphasis on the influence of color and spectral image features on both. There are very few works dedicated to the quality and fidelity of spectral images. Several novel image fidelity measures were developed in this study, which include kernel similarity measures and 3D-SSIM (structural similarity index). The kernel measures incorporate the polynomial, Gaussian radial basis function (RBF) and sigmoid kernels. The 3D-SSIM is an extension of a traditional gray-scale SSIM measure developed to incorporate spectral data. The novel image quality model presented in this study is based on the assumption that the statistical parameters of the spectra of an image influence the overall appearance. The spectral image quality model comprises three parameters of quality: colorfulness, vividness and naturalness. The quality prediction is done by modeling the preference function expressed in JNDs (just noticeable difference). Both image fidelity measures and the image quality model have proven to be effective in the respective experiments.

Adsorption of hidrogen peroxide on the surface of silica - titania mixed oxide obtained by the sol-gel processing method

This work describes the sol-gel mixed oxide SiO2/TiO2 property, ST, as prepared, and submitted to heat treatment a 773 K, STC. SEM and EDS images show, within magnification used, a uniform distribution of the TiO2 particles in SiO2/TiO2 matrix. Both, ST and STC adsorb hydrogen peroxide on the surface and through EPR and UV-Vis diffuse reflectance spectra, it was possible to conclude that the species on the surface is the peroxide molecule attached to the Lewis acid site of titanium particle surface, alphaTi(H2O2)+. As the material is very porous, presumably the hydrogen peroxide molecule is confined in the matrix pores on the surface, a reason why the adsorbed species presents an exceptional long lived stability.

Eye Fundus Image Analysis for Automatic Detection of Diabetic Retinopathy

Diabetes is a rapidly increasing worldwide problem which is characterised by defective metabolism of glucose that causes long-term dysfunction and failure of various organs. The most common complication of diabetes is diabetic retinopathy (DR), which is one of the primary causes of blindness and visual impairment in adults. The rapid increase of diabetes pushes the limits of the current DR screening capabilities for which the digital imaging of the eye fundus (retinal imaging), and automatic or semi-automatic image analysis algorithms provide a potential solution. In this work, the use of colour in the detection of diabetic retinopathy is statistically studied using a supervised algorithm based on one-class classification and Gaussian mixture model estimation. The presented algorithm distinguishes a certain diabetic lesion type from all other possible objects in eye fundus images by only estimating the probability density function of that certain lesion type. For the training and ground truth estimation, the algorithm combines manual annotations of several experts for which the best practices were experimentally selected. By assessing the algorithm’s performance while conducting experiments with the colour space selection, both illuminance and colour correction, and background class information, the use of colour in the detection of diabetic retinopathy was quantitatively evaluated. Another contribution of this work is the benchmarking framework for eye fundus image analysis algorithms needed for the development of the automatic DR detection algorithms. The benchmarking framework provides guidelines on how to construct a benchmarking database that comprises true patient images, ground truth, and an evaluation protocol. The evaluation is based on the standard receiver operating characteristics analysis and it follows the medical practice in the decision making providing protocols for image- and pixel-based evaluations. During the work, two public medical image databases with ground truth were published: DIARETDB0 and DIARETDB1. The framework, DR databases and the final algorithm, are made public in the web to set the baseline results for automatic detection of diabetic retinopathy. Although deviating from the general context of the thesis, a simple and effective optic disc localisation method is presented. The optic disc localisation is discussed, since normal eye fundus structures are fundamental in the characterisation of DR.

Detection of beetle damage in forests by X-ray CT image processing

Some beetle species can have devastating economic impacts on forest and nursery industries. A recent example is Anophophora glabripennis, a species of beetle known in the United States as the ''Asian Longhorrned beetle'', which has damaged many American forests, and is a threat which can unintentionally reach south American countries, including Brazil. This work presents a new method based on X-ray computerized tomography (CT) and image processing for beetle injury detection in forests. Its results show a set of images with correct identification of the location of beetles in living trees as well as damage evaluation with time.

Image analysis for assessing broiler breeder behavior response to thermal environment

The research proposes a methodology for assessing broiler breeder response to changes in rearing thermal environment. The continuous video recording of a flock analyzed may offer compelling evidences of thermal comfort, as well as other indications of welfare. An algorithm for classifying specific broiler breeder behavior was developed. Videos were recorded over three boxes where 30 breeders were reared. The boxes were mounted inside an environmental chamber were ambient temperature varied from cold to hot. Digital images were processed based on the number of pixels, according to their light intensity variation and binary contrast allowing a sequence of behaviors related to welfare. The system used the default of x, y coordinates, where x represents the horizontal distance from the top left of the work area to the point P, and y is the vertical distance. The video images were observed, and a grid was developed for identifying the area the birds stayed and the time they spent at that place. The sequence was analyzed frame by frame confronting the data with specific adopted thermal neutral rearing standards. The grid mask overlapped the real bird image. The resulting image allows the visualization of clusters, as birds in flock behave in certain patterns. An algorithm indicating the breeder response to thermal environment was developed.

Characterization of fiber and vessel elements in pulp suspension images

The thesis is related to the topic of image-based characterization of fibers in pulp suspension during the papermaking process. Papermaking industry is focusing on process control optimization and automatization, which makes it possible to manufacture highquality products in a resource-efficient way. Being a part of the process control, pulp suspension analysis allows to predict and modify properties of the end product. This work is a part of the tree species identification task and focuses on analysis of fiber parameters in the pulp suspension at the wet stage of paper production. The existing machine vision methods for pulp characterization were investigated, and a method exploiting direction sensitive filtering, non-maximum suppression, hysteresis thresholding, tensor voting, and curve extraction from tensor maps was developed. Application of the method to the microscopic grayscale pulp images made it possible to detect curves corresponding to fibers in the pulp image and to compute their morphological characteristics. Performance of the method was evaluated based on the manually produced ground truth data. An accuracy of fiber characteristics estimation, including length, width, and curvature, for the acacia pulp images was found to be 84, 85, and 60% correspondingly.

Evaluation of follicular lymphoid depletion in the Bursa of Fabricius: an alternative methodology using digital image analysis and artificial neural networks

Fifty Bursa of Fabricius (BF) were examined by conventional optical microscopy and digital images were acquired and processed using Matlab® 6.5 software. The Artificial Neuronal Network (ANN) was generated using Neuroshell® Classifier software and the optical and digital data were compared. The ANN was able to make a comparable classification of digital and optical scores. The use of ANN was able to classify correctly the majority of the follicles, reaching sensibility and specificity of 89% and 96%, respectively. When the follicles were scored and grouped in a binary fashion the sensibility increased to 90% and obtained the maximum value for the specificity of 92%. These results demonstrate that the use of digital image analysis and ANN is a useful tool for the pathological classification of the BF lymphoid depletion. In addition it provides objective results that allow measuring the dimension of the error in the diagnosis and classification therefore making comparison between databases feasible.