Search

The average error rate in liver cirrhosis classification on B-mode ultrasound images using the traditional pattern recognition approach is still too high. In order to improve the liver cirrhosis classification performance, image correction methods and a convolution neural network (CNN) approach are focused on. The impact of image correction methods on region of interest (ROI) images that are input into the CNN for the purpose of classifying liver cirrhosis based on data from B-mode ultrasound images is investigated. In this paper, image correction methods based on tone curves are developed. The experimental results show positive benefits from the image correction methods by improving the image quality of ROI images. By enhancing the image contrast of ROI images, the image quality improves and thus the generalization ability of the CNN also improves.

In the context of supervised statistical learning, it is typically assumed that the training set comes from the same distribution that draws the test samples. When this is not the case, the behavior of the learned model is unpredictable and becomes dependent upon the degree of similarity between the distribution of the training set and the distribution of the test set. One of the research topics that investigates this scenario is referred to as domain adaptation (DA). Deep neural networks brought dramatic advances in pattern recognition and that is why there have been many attempts to provide good DA algorithms for these models. Herein we take a different avenue and approach the problem from an incremental point of view, where the model is adapted to the new domain iteratively. We make use of an existing unsupervised domain-adaptation algorithm to identify the target samples on which there is greater confidence about their true label. The output of the model is analyzed in different ways to determine the candidate samples. The selected samples are then added to the source training set by self-labeling, and the process is repeated until all target samples are labeled. This approach implements a form of adversarial training in which, by moving the self-labeled samples from the target to the source set, the DA algorithm is forced to look for new features after each iteration. Our results report a clear improvement with respect to the non-incremental case in several data sets, also outperforming other state-of-the-art DA algorithms.

We address two questions concerning eye guidance during visual search in naturalistic scenes. First, search has been described as a task in which visual salience is unimportant. Here, we revisit this question by using a letter-in-scene search task that minimizes any confounding effects that may arise from scene guidance. Second, we investigate how important the different regions of the visual field are for different subprocesses of search (target localization, verification). In Experiment 1, we manipulated both the salience (low vs. high) and the size (small vs. large) of the target letter (a "T"), and we implemented a foveal scotoma (radius: 1°) in half of the trials. In Experiment 2, observers searched for high- and low-salience targets either with full vision or with a central or peripheral scotoma (radius: 2.5°). In both experiments, we found main effects of salience with better performance for high-salience targets. In Experiment 1, search was faster for large than for small targets, and high-salience helped more for small targets. When searching with a foveal scotoma, performance was relatively unimpaired regardless of the target's salience and size. In Experiment 2, both visual-field manipulations led to search time costs, but the peripheral scotoma was much more detrimental than the central scotoma. Peripheral vision proved to be important for target localization, and central vision for target verification. Salience affected eye movement guidance to the target in both central and peripheral vision. Collectively, the results lend support for search models that incorporate salience for predicting eye-movement behavior.

The importance of high-acuity foveal vision to visual search can be assessed by denying foveal vision using the gaze-contingent Moving Mask technique. Foveal vision was necessary to attain normal performance when searching for a target letter in alphanumeric displays, Perception & Psychophysics, 62 (2000) 576-585. In contrast, foveal vision was not necessary to correctly locate and identify medium-sized target objects in natural scenes, Journal of Experimental Psychology: Human Perception and Performance, 40 (2014) 342-360. To explore these task differences, we used grayscale pictures of real-world scenes which included a target letter (Experiment 1: T, Experiment 2: T or L). To reduce between-scene variability with regard to target salience, we developed the Target Embedding Algorithm (T.E.A.) to place the letter in a location for which there was a median change in local contrast when inserting the letter into the scene. The presence or absence of foveal vision was crossed with four target sizes. In both experiments, search performance decreased for smaller targets, and was impaired when searching the scene without foveal vision. For correct trials, the process of target localization remained completely unimpaired by the foveal scotoma, but it took longer to accept the target. We reasoned that the size of the target may affect the importance of foveal vision to the task, but the present data remain ambiguous. In summary, the data highlight the importance of extrafoveal vision for target localization, and the importance of foveal vision for target verification during letter-in-scene search., (Copyright © 2020 Elsevier Ltd. All rights reserved.)

This research aims to improve dietetic-nutritional treatment using state-of-the-art RGB-D sensors and virtual reality (VR) technology. Recent studies show that adherence to treatment can be improved using multimedia technologies. However, there are few studies using 3D data and VR technologies for this purpose. On the other hand, obtaining 3D measurements of the human body and analyzing them over time (4D) in patients undergoing dietary treatment is a challenging field. The main contribution of the work is to provide a framework to study the effect of 4D body model visualization on adherence to obesity treatment. The system can obtain a complete 3D model of a body using low-cost technology, allowing future straightforward transference with sufficient accuracy and realistic visualization, enabling the analysis of the evolution (4D) of the shape during the treatment of obesity. The 3D body models will be used for studying the effect of visualization on adherence to obesity treatment using 2D and VR devices. Moreover, we will use the acquired 3D models to obtain measurements of the body. An analysis of the accuracy of the proposed methods for obtaining measurements with both synthetic and real objects has been carried out.

Across the globe, remote image data is rapidly being collected for the assessment of benthic communities from shallow to extremely deep waters on continental slopes to the abyssal seas. Exploiting this data is presently limited by the time it takes for experts to identify organisms found in these images. With this limitation in mind, a large effort has been made globally to introduce automation and machine learning algorithms to accelerate both classification and assessment of marine benthic biota. One major issue lies with organisms that move with swell and currents, such as kelps. This paper presents an automatic hierarchical classification method local binary classification as opposed to the conventional flat classification to classify kelps in images collected by autonomous underwater vehicles. The proposed kelp classification approach exploits learned feature representations extracted from deep residual networks. We show that these generic features outperform the traditional off-the-shelf CNN features and the conventional hand-crafted features. Experiments also demonstrate that the hierarchical classification method outperforms the traditional parallel multi-class classifications by a significant margin (90.0% vs. 57.6% and 77.2% vs. 59.0%) on Benthoz15 and Rottnest datasets respectively. Furthermore, we compare different hierarchical classification approaches and experimentally show that the sibling hierarchical training approach outperforms the inclusive hierarchical approach by a significant margin. We also report an application of our proposed method to study the change in kelp cover over time for annually repeated AUV surveys.

Images of co-planar points in 3-dimensional space taken from different camera positions are a homography apart. Homographies are at the heart of geometric methods in computer vision and are used in geometric camera calibration, 3D reconstruction, stereo vision and image mosaicking among other tasks. In this paper we show the surprising result that homographies are the apposite tool for relating image colors of the same scene when the capture conditions-illumination color, shading and device-change. Three applications of color homographies are investigated. First, we show that color calibration is correctly formulated as a homography problem. Second, we compare the chromaticity distributions of an image of colorful objects to a database of object chromaticity distributions using homography matching. In the color transfer problem, the colors in one image are mapped so that the resulting image color style matches that of a target image. We show that natural image color transfer can be re-interpreted as a color homography mapping. Experiments demonstrate that solving the color homography problem leads to more accurate calibration, improved color-based object recognition, and we present a new direction for developing natural color transfer algorithms.

The etiological spectrum of ultra-rare developmental disorders remains to be fully defined. Chromatin regulatory mechanisms maintain cellular identity and function, where misregulation may lead to developmental defects. Here, we report pathogenic variations in MSL3, which encodes a member of the chromatin-associated male-specific lethal (MSL) complex responsible for bulk histone H4 lysine 16 acetylation (H4K16ac) in flies and mammals. These variants cause an X-linked syndrome affecting both sexes. Clinical features of the syndrome include global developmental delay, progressive gait disturbance, and recognizable facial dysmorphism. MSL3 mutations affect MSL complex assembly and activity, accompanied by a pronounced loss of H4K16ac levels in vivo. Patient-derived cells display global transcriptome alterations of pathways involved in morphogenesis and cell migration. Finally, we use histone deacetylase inhibitors to rebalance acetylation levels, alleviating some of the molecular and cellular phenotypes of patient cells. Taken together, we characterize a syndrome that allowed us to decipher the developmental importance of MSL3 in humans.

The advance of scene understanding methods based on machine learning relies on the availability of large ground truth datasets, which are essential for their training and evaluation. Construction of such datasets with imagery from real sensor data however typically requires much manual annotation of semantic regions in the data, delivered by substantial human labour. To speed up this process, we propose a framework for semantic annotation of scenes captured by moving camera(s), e.g., mounted on a vehicle or robot. It makes use of an available 3D model of the traversed scene to project segmented 3D objects into each camera frame to obtain an initial annotation of the associated 2D image, which is followed by manual refinement by the user. The refined annotation can be transferred to the next consecutive frame using optical flow estimation. We have evaluated the efficiency of the proposed framework during the production of a labelled outdoor dataset. The analysis of annotation times shows that up to 43% less effort is required on average, and the consistency of the labelling is also improved.

In this work, we use deep neural autoencoders to segment oil spills from Side-Looking Airborne Radar (SLAR) imagery. Synthetic Aperture Radar (SAR) has been much exploited for ocean surface monitoring, especially for oil pollution detection, but few approaches in the literature use SLAR. Our sensor consists of two SAR antennas mounted on an aircraft, enabling a quicker response than satellite sensors for emergency services when an oil spill occurs. Experiments on TERMA radar were carried out to detect oil spills on Spanish coasts using deep selectional autoencoders and RED-nets (very deep Residual Encoder-Decoder Networks). Different configurations of these networks were evaluated and the best topology significantly outperformed previous approaches, correctly detecting 100% of the spills and obtaining an F 1 score of 93.01% at the pixel level. The proposed autoencoders perform accurately in SLAR imagery that has artifacts and noise caused by the aircraft maneuvers, in different weather conditions and with the presence of look-alikes due to natural phenomena such as shoals of fish and seaweed.

In the U.S., there is a growing percentage of chronic pain patients requiring surgery. Chronic pain patients require careful evaluation and planning to achieve appropriate acute pain management. Peri-surgical pain management often requires continuation of previously prescribed chronic pain modalities and careful selection of multimodal acute pain interventions. This article will provide a broad overview of chronic pain, definitions, and current recommendations for the treatment of perioperative pain in patients maintained on opioid therapy.

Constitutional deletions of distal 9q34 encompassing the EHMT1 (euchromatic histone methyltransferase 1) gene, or loss-of-function point mutations in EHMT1, are associated with the 9q34.3 microdeletion syndrome, also known as Kleefstra syndrome [MIM#610253]. We now report further evidence for genomic instability of the subtelomeric 9q34.3 region as evidenced by copy number gains of this genomic interval that include duplications, triplications, derivative chromosomes and complex rearrangements. Comparisons between the observed shared clinical features and molecular analyses in 20 subjects suggest that increased dosage of EHMT1 may be responsible for the neurodevelopmental impairment, speech delay, and autism spectrum disorders revealing the dosage sensitivity of yet another chromatin remodeling protein in human disease. Five patients had 9q34 genomic abnormalities resulting in complex deletion-duplication or duplication-triplication rearrangements; such complex triplications were also observed in six other subtelomeric intervals. Based on the specific structure of these complex genomic rearrangements (CGR) a DNA replication mechanism is proposed confirming recent findings in Caenorhabditis elegans telomere healing. The end-replication challenges of subtelomeric genomic intervals may make them particularly prone to rearrangements generated by errors in DNA replication.

Non-analytical reasoning is thought to play a key role in dermatology diagnosis. Considering its potential importance, surprisingly little work has been done to research whether similar identification processes can be supported in non-experts. We describe here a prototype diagnostic support software, which we have used to examine the ability of medical students (at the beginning and end of a dermatology attachment) and lay volunteers, to diagnose 12 images of common skin lesions. Overall, the non-experts using the software had a diagnostic accuracy of 98% (923/936) compared with 33% for the control group (215/648) (Wilcoxon p < 0.0001). We have demonstrated, within the constraints of a simplified clinical model, that novices' diagnostic scores are significantly increased by the use of a structured image database coupled with matching of index and referent images. The novices achieve this high degree of accuracy without any use of explicit definitions of likeness or rule-based strategies.

The "ABCD" mnemonic to assist non-experts' diagnosis of melanoma is widely promoted; however, there are good reasons to be sceptical about public education strategies based on analytical, rule-based approaches--such as ABCD (i.e. Asymmetry, Border Irregularity, Colour Uniformity and Diameter). Evidence suggests that accurate diagnosis of skin lesions is achieved predominately through non-analytical pattern recognition (via training examples) and not by rule-based algorithms. If the ABCD are to function as a useful public education tool they must be used reliably by untrained novices, with low inter-observer and intra-diagnosis variation, but with maximal inter-diagnosis differences. The three subjective properties (the ABCs of the ABCD) were investigated experimentally: 33 laypersons scored 40 randomly selected lesions (10 lesions × 4 diagnoses: benign naevi, dysplastic naevi, melanomas, seborrhoeic keratoses) for the three properties on visual analogue scales. The results (n = 3,960) suggest that novices cannot use the ABCs reliably to discern benign from malignant lesions.

Previously, we localized the defective gene for the urofacial syndrome (UFS) to a region on chromosome 10q24 by homozygosity mapping. We now report evidence that Heparanse 2 (HPSE2) is the culprit gene for the syndrome. Mutations with a loss of function in the Heparanase 2 (HPSE2) gene were identified in all UFS patients originating from Colombia, the United States, and France. HPSE2 encodes a 592 aa protein that contains a domain showing sequence homology to the glycosyl hydrolase motif in the heparanase (HPSE) gene, but its exact biological function has not yet been characterized. Complete loss of HPSE2 function in UFS patients suggests that HPSE2 may be important for the synergic action of muscles implicated in facial expression and urine voiding.

Common 3D acquisition techniques, such as laser scanning and stereo capture, are realistically only 2.5D in nature. Here we consider the automated completion of hidden or missing portions in 3D scenes originally acquired from 2.5D (or 3D) capture. We propose an approach based on the non-parametric propagation of available scene knowledge from the known (visible) scene areas to these unknown (invisible) 3D regions in conjunction with an initial underlying geometric surface completion.

A case is reported with right-sided abnormalities involving the brain, eyelid, eye, face and chest. The features described are similar to those found in conditions including focal dermal hypoplasia, microphthalmia with linear skin defects, oculocerebrocutaneous syndrome and terminal osseous dysplasia and pigmentary defects. However, none of these conditions, fully explains the collection of abnormalities found in this patient.

Craniofrontonasal syndrome (CFNS) is an X-linked disorder that exhibits a paradoxical sex reversal in phenotypic severity: females characteristically have frontonasal dysplasia, craniosynostosis, and additional minor malformations, but males are usually mildly affected with hypertelorism only. Despite this, males appear underrepresented in CFNS pedigrees, with carrier males encountered infrequently compared with affected females. To investigate these unusual genetic features of CFNS, we exploited the recent discovery of causative mutations in the EFNB1 gene, which encodes ephrin-B1, to survey the molecular alterations in 59 families (39 newly investigated and 20 published elsewhere). We identified the first complete deletions of EFNB1, catalogued 27 novel intragenic mutations, and used Pyrosequencing and analysis of nearby polymorphic alleles to quantify mosaic cases and to determine the parental origin of verified germline mutations. Somatic mosaicism was demonstrated in 6 of 53 informative families, and, of 17 germline mutations in individuals for whom the parental origin of mutation could be demonstrated, 15 arose from the father. We conclude that the major factor accounting for the relative scarcity of carrier males is the bias toward mutations in the paternal germline (which present as affected female offspring) combined with reduced reproductive fitness in affected females. Postzygotic mutations also contribute to the female preponderance, whereas true nonpenetrance in males who are hemizygous for an EFNB1 mutation appears unusual. These results highlight the importance of considering possible origins of mutation in the counseling of families with CFNS and provide a generally applicable approach to the combined analysis of mosaic and germline mutations.

A probable diagnosis of von Hippel-Lindau disease was made in a two generation family in which the proband had a phaeochromocytoma, renal cysts, and multiple cerebral cavernomas. His sister had multiple similar cerebral vascular lesions and his father died from renal carcinoma aged 42. Although the family did not satisfy the conventional diagnostic criteria for von Hippel-Lindau disease, an underlying germline mutation in the von Hippel-Lindau disease tumour suppressor gene was identified in the proband. Molecular genetic analysis not only confirmed the putative diagnosis of the disease in the proband but also showed that the cerebral vascular lesions segregated independently from the von Hippel-Lindau disease mutation. This report exemplifies how molecular genetic investigations can enhance the diagnosis and management of families with suspected von Hippel-Lindau disease, particularly when the manifestations, as in this family, are not typical.

Human centromeres have been extensively studied over the past two decades. Consequently, more is known of centromere structure and organization in humans than in any other higher eukaryote species. Recent advances in the construction of a human (or mammalian) artificial chromosome have fostered increased interest in determining the structure and function of fully functional human centromeres. Here, we present an overview of currently identified human centromeric repetitive DNA families: their discoveries, molecular characterization, and organization with respect to other centromeric repetitive DNA families. A brief examination of some functional based studies is also included.

Factitious disorders are characterized by the intentional feigning or induction of signs and/or symptoms in order to assume the sick role. The spectrum of diseases and symptoms simulated is extensive. Although some patients may seek only the gratifications of the sick role, typically patients seek health care for their afflictions. We report the case of a woman with a history of numerous unexplainable illnesses and laboratory findings who had shigellosis. On routine evaluation, a severe prothrombin coagulopathy was discovered and later determined to be caused by brodifacoum, a "superwarfarin" drug found in potent rodenticides. The patient was successfully treated with daily vitamin K. She continued to deny intentional or accidental ingestion but did consent to psychiatric treatment.

127 patients who were transferred to a regional referral centre for specialist treatment within 48 h of serious injury were reassessed on arrival in the receiving accident and emergency department by a trauma team. 80 transferred patients (63%) required intervention in the accident and emergency department to complete assessment or resuscitation. In view of the well recognised difficulties in managing patients with multiple trauma and the possibility that initially occult injuries may become clinically significant during transport, transferred trauma patients should be reassessed in the accident and emergency department of the receiving hospital by a trauma team consisting of senior medical staff experienced in all aspects of trauma care.

We have localized the DNA sequences required for mitotic centromere function on the human Y chromosome. Analysis of 33 rearranged Y chromosomes allowed the centromere to be placed in interval 8 of a 24-interval deletion map. Although this interval is polymorphic in size, it can be as small as approximately 500kb. It contains alphoid satellite DNA and approximately 300kb of adjacent Yp sequences. Chromosomes with rearrangements in this region were analysed in detail. Two translocation chromosomes and one monocentric isochromosome had breakpoints within the alphoid array. Of 12 suppressed Y centromeres on translocation chromosomes and dicentric isochromosomes that were also analysed two showed deletions one of which only removed alphoid DNA. These results indicate that alphoid DNA is a functional part of the Y chromosome centromere.

We have determined the orientation of the major centromeric alphoid array on the human Y chromosome. A PCR assay was used to analyse the vector-insert junctions of seven YAC clones previously positioned on two independent Y chromosomes. The orientation is the same at all 10 positions measured. This suggests that the alphoid array is a simple unidirectional repeat throughout and that human centromere structure thus differs from the palindromic organisation found in Schizosaccharomyces pombe.

The need for centralized management of acute trauma was evaluated in a 1-year prospective study in Northern Ireland. All patients with an Injury Severity Score > 15 who reached hospital alive were included. The sample population was approximately 1 million people. A total of 239 patients entered the study, of whom 74 died. An audit panel considered that 3-15 per cent of deaths were preventable. There was no significant difference in the preventable mortality rate between any hospital or groups of hospitals. There was a high level of consultant involvement, especially in small hospitals. A system in which patients with acute trauma bypass the nearest hospital to reach a trauma centre may be neither beneficial nor cost-effective in Northern Ireland. Upgrading of the present system with stabilization of the patient and emergency surgery at the nearest hospital before transfer is recommended.

Eighteen yeast artificial chromosome (YAC) clones containing alphoid satellite DNA and adjacent sequences from the human Y chromosome have been identified from three different YAC libraries. Restriction site mapping of the genomic alphoid arrays and the YACs has allowed seven of the alphoid clones to be positioned on the arrays. Three clones extend into flanking sequences. At one edge the alphoid DNA is highly diverged and is flanked by a small block of the 48 base-pair satellite, dispersed moderately repeated sequences and a separate short alphoid array. More distal sequences are Y-specific. At the other edge there is much less divergence and the alphoid DNA is flanked by an Alu sequence and the five base-pair satellite.

We have analysed the sequence organization of the DNA in the pericentric region of the long arm of the human Y chromosome. The structures of one cosmid and three yeast artificial chromosome clones were determined. The region consists of a mosaic of the known 5, 48 and 68 base-pair tandemly repeated sequences and at least five novel repeated sequence families. A long range-map of approximately 3.5 x 10(6) base-pairs of genomic DNA was constructed that placed the clones between about 500 x 10(3) and 850 x 10(3) base-pairs from the long arm edge of the centromeric alphoid DNA array.

The suitability of yeast artificial chromosome vectors (YACs) for cloning human Y chromosome tandemly repeated DNA sequences has been investigated. Clones containing DYZ3 or DYZ5 sequences were found in libraries at about the frequency anticipated on the basis of their abundance in the genome, but clones containing DYZ1 sequences were under-represented and the three clones examined contained junctions between DYZ1 and DYZ2. One DYZ3 clone was quite stable and had a long-range structure corresponding to genomic DNA. All other clones had long-range structures which either did not correspond to genomic DNA, or were too unstable to allow a simple comparison. The effects of the transformation process and host genotype on YAC structural stability were investigated. Gross structural rearrangements were often associated with re-transformation of yeast by a YAC. rad1-deficient yeast strains showed levels of instability similar to wild-type for all YAC clones tested. In rad52-deficient strains, DYZ5 containing YACs were as unstable as in the wild-type host, but DYZ1/DYZ2 or DYZ3 containing YACs were more stable. Thus the use of rad52 hosts for future library construction is recommended, but some sequences will still be unstable.

1. Transport of deuterium oxide from a luminal perfusate containing 1% D2O was studied in Fisher & Gardners (1974) isolated preparation of perfused rat small intestine. 2. The kinetics of appearance of D2O in the intestinal secretion at the serosal surface fitted well to a single exponential function. 3. The steady-state concentration of D2O in this secretion was not significantly different from the concentration in the luminal perfusate. 4. The total tissue water contained D2O at a concentration, on average, 5% lower than that in the luminal perfusate. 5. There is no evidence to suggest discrimination in transport across the intestinal mucosa between H2O and D2O. 6. The kinetics of wash-in of D2O to intestinal secretion show that the ratio of flux out of the lumen to reflux back to the lumen is 1-38;1.