A CAD system to analyse mammogram images using fully complex-valued relaxation neural network ensembled classifier

This paper presents a new improved classification technique using the Fully Complex-Valued Relaxation Neural Networks (FCRN) based ensemble technique for classifying mammogram images. The system is developed based on three stages of Breast cancer, namely Normal, Benign and Malignant, defined by the MIAS database. Features like Binary object Features, RST Invariant Features, Histogram Features, Texture Features and Spectral Features are extracted from the MIAS database. Extracted features are then given to the proposed FCRN-based ensemble classifier. FCRN networks are ensembled together for improving the classification rate. Receiver Operating Characteristic (ROC) analysis is used for evaluating the system. The results illustrate the superior classification performance of the ensembled FCRN. Performance comparison of various sets of training and testing vectors are provided for FCRN classifier. The resultant ensembled FCRN approximates the desired output more accurately with a lower computational effort.     

Giant cell tumor of the temporal bone – a case report

Background

We aimed to find some new indicators for tonsillectomy (TE) in adults with recurrent tonsillitis (RT) by exploring whether the frequency of tonsillitis episodes and the length of morbidity period are associated with the macroscopic signs of sclerotic process in tonsils and microbiological data assessed by culture, molecular (PCR) and transmission electron microscopy (EM) methods.

Methods

The study involved 62 RT patients admitted for TE (age range 15–35, median 22 years) and 54 healthy volunteers (age range 18–24, median 20 years). The index of tonsillitis (IT) was calculated by multiplying the number of tonsillitis episodes per year by the morbidity period in years. On oropharyngeal examination the presence or absence of three sclerotic signs was evaluated: tonsillar sclerosis, obstruction of tonsillar crypts and scar tissue on the tonsils. The occurrence of Streptococcus pyogenes was assessed by culture and PCR methods in 24 tonsillar core specimens. The samples for EM investigation of crypt epithelium were taken from 10 removed tonsils.

Results

The IT values were in positive correlation with the number of sclerotic signs on oropharyngeal examination (r = 0.325, P = 0.010). Based on the IT values and the presence or absence of tonsillar sclerosis and obstruction of tonsillar crypts the receiver-operating curve (ROC) was constructed. It revealed that an IT score of 36 is an optimal cut-off value for prediction of sclerotic type tonsils. S. pyogenes was never found by culture, but its presence by PCR in nearly one third (29%) of diseased tonsillar tissue specimens was tightly associated with longer morbidity. EM revealed coccoid forms of intracellular bacteria in the crypt epithelium, which was accompanied with the damage of tight junctions between epithelial cells.

Conclusion

The index of tonsillitis ≥36, being a combination between the frequency of tonsillitis and the length of morbidity period, predicts the sclerotic process in recurrently inflamed tonsils. Therefore, the high IT values could serve as an indicator for TE in adults. The correlation between the longer morbidity period and the presence of S. pyogenes by PCR suggests that persistent infection may have a role in maintenance of recurrent inflammation in tonsils.     

Characterization of the secreted proteome of rat hepatocytes cultured in collagen sandwiches

Analysis of proteins in biological samples opens up the possibility of discovering new markers of toxicity. The liver is one of the primary targets of drug-induced toxicity, and it also secretes many plasma proteins, which can be measured clinically. Most of the plasma proteins produced by the liver are secreted by hepatocytes, but there is little information regarding the protein profile secreted by these cells. The purpose of this study was to analyze the secreted proteome of primary rat hepatocytes in a collagen gel sandwich configuration by a gel-LC-MS/MS procedure. We identified over 600 peptides corresponding to more than 200 proteins. The protein profile included over 50 plasma proteins, suggesting that the cultured hepatocytes secrete many of the proteins that they produce in vivo. Our data also suggests that the hepatocytes are actively remodeling their environment, since we identified several structural extracellular matrix proteins as well as some proteins known to be secreted specifically during liver regeneration. We also identified two proteins, alpha1-antitrypsin and alpha2-macroglobulin, whose secretions appear to be down-regulated in cells exposed to aflatoxin B1. It was noted that a 15 nM dose of aflatoxin B1 led to substantially diminished levels of these proteins and that day 6 of incubation was the ideal time point for medium collection. These data suggest that proteins in the conditioned medium of hepatocyte sandwich culture might lead to the discovery of biomarkers for drug-induced chemical toxicity.     

Anaerobic bacteraemia: a review of 17 cases

Of 93 blood cultures received with a suspicion of anaerobic bacteraemia over a period of two years, only 17 (18.3%) showed anaerobic growth. Twelve grew anaerobes alone while five had a polymicrobial flora. Seven of these patients (4.3%) had pre-existing heart disease while others had history of prior surgery, diabetes mellitus or urinary tract infection. Oropharynx was the commonest portal of entry, followed by gastrointestinal tract. The anaerobes isolated were anaerobic streptococci, Bacteroides fragilis group and Bilophila and Eubacterium species. Fifteen patients developed major complications such as congestive cardiac failure, systemic embolisation, and perforative peritonitis. The mortality rate among the cases with anaerobic bacteraemia was 23.5% in this study.     

A Search for Energy Minimized Sequences of Proteins

In this paper, we present numerical evidence that supports the notion of minimization in the sequence space of proteins for a target conformation. We use the conformations of the real proteins in the Protein Data Bank (PDB) and present computationally efficient methods to identify the sequences with minimum energy. We use edge-weighted connectivity graph for ranking the residue sites with reduced amino acid alphabet and then use continuous optimization to obtain the energy-minimizing sequences. Our methods enable the computation of a lower bound as well as a tight upper bound for the energy of a given conformation. We validate our results by using three different inter-residue energy matrices for five proteins from protein data bank (PDB), and by comparing our energy-minimizing sequences with 80 million diverse sequences that are generated based on different considerations in each case. When we submitted some of our chosen energy-minimizing sequences to Basic Local Alignment Search Tool (BLAST), we obtained some sequences from non-redundant protein sequence database that are similar to ours with an E-value of the order of 10^-7. In summary, we conclude that proteins show a trend towards minimizing energy in the sequence space but do not seem to adopt the global energy-minimizing sequence. The reason for this could be either that the existing energy matrices are not able to accurately represent the inter-residue interactions in the context of the protein environment or that Nature does not push the optimization in the sequence space, once it is able to perform the function.