A neural network architecture for understanding discrete three-dimensional scenes in medical imaging.

Magnetic resonance and computed tomography produce sets of tomograms which are termed discrete 3D scenes. Usually, discrete 3D scenes are analyzed in two dimensions by observing each tomogram on a screen so that the three-dimensional information contained in the scene can be recovered only partially and qualitatively. The three-dimensional reconstruction of the shape of biological structures from discrete 3D scenes would allow a complete and quantitative recovery of the available information, but this task has proved hard for conventional processing techniques. In this paper we present a system architecture based on neural networks for the fully automated segmentation and recognition of structures of interest in discrete 3D scenes. The system includes a retina and two main processing modules, an Attention-Focuser System and a Region-Finder System, which have been implemented by using feed-forward nets trained with the back-propagation algorithm. This architecture has been tested on computer-simulated structures and has been applied to the reconstruction of the spinal cord and the brain from sets of tomograms.     

Subchronic toxicity of a medium-chain chlorinated paraffin in the rat

Groups of ten male and female weanling Sprague-Dawley rats were fed diet containing 0, 5, 50, 500 or 5000 ppm of a medium-chain chlorinated paraffin (C14-17, 52% chlorination) for a period of 13 weeks. Increased relative liver weight was observed at 500 and 5000 ppm in females and at 5000 ppm in males. Relative kidney weight was increased at 5000 ppm in both sexes. Serum cholesterol was increased in the females in a dose-related manner starting at 50 ppm. At 5000 ppm, animals of both sexes had elevated hepatic UDP-glucuronosyltransferase activity while only females showed increased aminopyrine N-demethylase activity. Increased urinary N-acetylglucosaminidase activity occurred at 5000 ppm in females. Increased urinary ascorbic acid excretion monitored at week 12 and a decreased hepatic vitamin A level were detected in females receiving the 500 ppm diet and male and female rats at 5000 ppm. Mild, adaptive histopathological changes were detected in the liver of rats of both sexes at 500 and 5000 ppm, and in the thyroid of males and females starting at 500 and 50 ppm respectively. Minimal changes were observed in the kidney proximal tubules of male rats fed the 5000 ppm diet and in the inner medulla tubules of female rats fed the 500 and 5000 ppm diets. These data indicate that the medium-chain chlorinated paraffin produces biochemical and histological changes at dietary levels of greater than or = 50 ppm in females and greater than or = 500 ppm in males.     

Results of a 90-day toxicity study on 1,2,3- and 1,1,2-trichloropropane administered via the drinking water

Trichloropropanes have been identified as environmental contaminants in sediments of the Great Lakes region of North America. Since these chemicals had the potential to find their way into drinking water, a 90-day feeding study was carried out in order to determine their subchronic toxicity. Groups of 10 male and 10 female weanling Sprague-Dawley rats were supplied drinking water ad libitum, containing 1,2,3- or 1,1,2-trichloropropane at concentrations of 1, 10, 100 or 1000 mg/L for 13 weeks. Emulphor (0.5%) was used to solubilize the chemicals. At the end of the study, the animals were killed and examined for gross and microscopic changes. Heart, liver, brain, kidney and spleen were excised and weighed. Blood was collected and subjected to a comprehensive hematological analysis. Serum was collected and profiled for changes in 12 biochemical parameters and a portion of liver was used to determine mixed function oxidase activity. Although three animals died during the study, their deaths could not be related to treatment. Decreased growth rate was observed in both sexes of the group receiving 1000 mg/L 1,2,3-trichloropropane. There was an increase in liver, kidney and brain weights (relative to body weight) in rats of both sexes fed 1000 mg/L 1,2,3-trichloropropane. Fatty livers were observed in some of the treated animals but a clear dose-relationship was not evident. An elevation in serum cholesterol was observed in female rats fed the highest dose of 1,2,3-trichloropropane. This chemical also induced hepatic aminopyrine demethylase and aniline hydroxylase activities in male rats at the highest dose. Administration of both isomers produced only mild histological changes in the liver, thyroid and kidney of rats at the highest dose. The changes in the liver consisted of an increase in cytoplasmic eosinophilia in the periportal area together with vesiculation of biliary epithelial nuclei. Morphological changes were characterized by increased anisokaryosis in the proximal epithelium and occasional pyknosis associated with the accumulation of large eosinophilic inclusions. Changes in the thyroid consisted of a mild reduction in follicular size associated with an increased epithelial height. In general, these changes were more severe in the males than females, but were still mild overall. It was concluded that the no-effect level for both chemicals was 100 mg/L (15–20 mg/kg bw/day) and based on effects on growth rate and other changes, the 1,2,3- isomer was judged to be slightly more toxic than the 1,1,2- isomer.     

A 931 + 2T-->C transition in one COL1A2 allele causes exon 16 skipping in PRO alpha 2(I) mRNA and produces moderately severe OI

The breast clinic in the university Hospital Kuala Lumpur was started in August 1993 to cater for the increasing number of women seeking treatment for breast complaints. A four-month survey carried out from January to April 1994 found that Chinese women are more "breast conscious" than Malay and Indian women. The majority of patients were in the reproductive age group. Benign breast diseases form the majority of cases of breast diseases seen. The pick-up rate for new cases of breast cancer was 3.1%. Fine needle aspiration biopsy had a 100% sensitivity during the four-month study, and was a quick method of obtaining a diagnosis.     

Image super resolution model enabled by wavelet lifting with optimized deep convolutional neural network

This paper plans to develop an intelligent super resolution model with the linkage of Wavelet lifting scheme and Deep learning algorithm. Before initiating the resolution procedure, the entire HR images are converted into Low Resolution (LR) images using bicubic interpolation-based downsampling and upsampling. Further, the Wavelet lifting scheme helps to generate the four subbands of each image like LR wavelet Sub-Bands for LR images, and High Resolution (HR) wavelet Sub-Bands for HR images. The residual image is generated by taking the difference between the LR wavelet Sub-Bands and HR wavelet Sub-Bands images. The proposed model involves two main phases: Training phase and Testing. The training phase trains the residual image of all images by Deep Convolutional Neural Network with LR wavelet Sub-Bands as input and residual image as target. On the other hand, in testing phase, the LR wavelet Sub-Bands query image is subjected to Deep Convolutional Neural Network, which outputs the concerned residual image. This generated residual image is summed with LR wavelet Sub-Bands image, followed by inverse wavelet lifting scheme to obtain the final super resolution image. The main contribution of this paper is to improve the conventional Deep Convolutional Neural Network by optimizing the number of hidden layer, and hidden neurons using modified Whale Optimization Algorithm called Average Fitness Enabled Whale Optimization Algorithm by considering the objective of maximizing the Peak Signal-to-Noise Ratio. Finally, the proposed method achieves an improved quality of the results which is comparable the existing models.     

A semantic approach to remove incoherent items from a user profile and improve the accuracy of a recommender system

Recommender systems usually suggest items by exploiting all the previous interactions of the users with a system (e.g., in order to decide the movies to recommend to a user, all the movies she previously purchased are considered). This canonical approach sometimes could lead to wrong results due to several factors, such as a change in user preferences over time, or the use of her account by third parties. This kind of incoherence in the user profiles defines a lower bound on the error the recommender systems may achieve when they generate suggestions for a user, an aspect known in literature as magic barrier. This paper proposes a novel dynamic coherence-based approach to define the user profile used in the recommendation process. The main aim is to identify and remove, from the previously evaluated items, those not semantically adherent to the others, in order to make a user profile as close as possible to the user’s real preferences, solving the aforementioned problems. Moreover, reshaping the user profile in such a way leads to great advantages in terms of computational complexity, since the number of items considered during the recommendation process is highly reduced. The performed experiments show the effectiveness of our approach to remove the incoherent items from a user profile, increasing the recommendation accuracy.     

Digital autoradiography: film and electronic multitracer techniques for heart imaging

A multitracer digital film autoradiography (DFA) and a single-tracer multiwire proportional chamber autoradiography (MWPCA) have been developed for the simultaneous study of regional myocardial blood flow and metabolism in the canine heart. Radioactive indicators of flow (plastic microspheres), metabolism (deoxy-2-D-glucose labeled either with (14)C or (3)H), and flow and metabolism ((201)T1), were used in the same experiment. Multiple tracers were discriminated by film autoradiography on the basis of their properties (particulate or nonparticulate, short or long half-life), and by multiple film exposure. A multiwire chamber was used for (3)H detection. Perfusional and metabolic maps were obtained in transverse microslices of the heart (40 mum thick) by digital image processing. The operation, the advantages and limits of the single techniques as well as their combined use are described. The two techniques are complementary: DFA, although time consuming and proportionality limited, allows the use of multiple tracers and it is mandatory for particulate tracer detection due to its high spatial resolution; MWPCA, in spite of a lower resolution provides a very fast and proportional detection as compared to DFA, but limited to only one tracer at the time.     

Interplay between upsampling and regularization for provider fairness in recommender systems

User Modeling and User-Adapted Interaction - Considering the impact of recommendations on item providers is one of the duties of multi-sided recommender systems. Item providers are key stakeholders...     

The Interplay between Autonomic Nervous System and Inflammation across Systemic Autoimmune Diseases

The autonomic nervous system (ANS) and the immune system are deeply interrelated. The ANS regulates both innate and adaptive immunity through the sympathetic and parasympathetic branches, and an imbalance in this system can determine an altered inflammatory response as typically observed in chronic conditions such as systemic autoimmune diseases. Rheumatoid arthritis, systemic lupus erythematosus, and systemic sclerosis all show a dysfunction of the ANS that is mutually related to the increase in inflammation and cardiovascular risk. Moreover, an interaction between ANS and the gut microbiota has direct effects on inflammation homeostasis. Recently vagal stimulation techniques have emerged as an unprecedented possibility to reduce ANS dysfunction, especially in chronic diseases characterized by pain and a decreased quality of life as well as in chronic inflammation.