Observer-invariant histopathology using genetics-based machine learning

Prostate cancer accounts for one-third of noncutaneous cancers diagnosed in US men and is a leading cause of cancer-related death. Advances in Fourier transform infrared spectroscopic imaging now provide very large data sets describing both the structural and local chemical properties of cells within prostate tissue. Uniting spectroscopic imaging data and computer-aided diagnoses (CADx), our long term goal is to provide a new approach to pathology by automating the recognition of cancer in complex tissue. The first step toward the creation of such CADx tools requires mechanisms for automatically learning to classify tissue types—a key step on the diagnosis process. Here we demonstrate that genetics-based machine learning (GBML) can be used to approach such a problem. However, to efficiently analyze this problem there is a need to develop efficient and scalable GBML implementations that are able to process very large data sets. In this paper, we propose and validate an efficient GBML technique——based on an incremental genetics-based rule learner. exploits massive parallelisms via the message passing interface (MPI) and efficient rule-matching using hardware-implemented operations. Results demonstrate that is capable of performing prostate tissue classification efficiently, making a compelling case for using GBML implementations as efficient and powerful tools for biomedical image processing.     

Anosognosia in parietal lobe syndrome

Patients with right parietal lesions often deny their paralysis (anosognosia), but do they have "tacit" knowledge of their paralysis? I devised three novel tests to explore this. First, the patients were given a choice between a bimanual task (e.g., tying shoe laces) vs a unimanual one (e.g., threading a bolt). They chose the former on 17 of 18 trials and, surprisingly, showed no frustration or learning despite repeated failed attempts. I conclude that they have no tacit knowledge of paralysis (or, if such knowledge exists, it is not available for this particular task). Second, I used a "virtual reality box" to convey the optical illusion to the patient that she was moving her paralyzed left hand up and down to the rhythm of a metronome, and yet she showed no sign of surprise. Third, I irrigated patient BM's left ear canal with cold water, a procedure that is known to shift that patient's spatial frame of reference by stimulating the vestibular system. Surprisingly, this allowed her "repressed" memory of the paralysis to come to the surface; she said she had been paralyzed continuously for several days. I suggest that the vestibular stimulation produces these remarkable effects by mimicking REM sleep. These patients also employ a whole arsenal of grossly exaggerated Freudian "defense mechanisms" to account for their paralysis. To explain this, I propose that in normal individuals the left hemisphere ordinarily deals with small, local anomalies by trying to impose consistency but, when the anomaly exceeds threshold, an interaction with the right hemisphere forces a "paradigm shift." A failure of this process, in patients with right hemisphere damage, might partially account for anosognosia. Finally, I present a new conceptual framework that may help link several psychological and neurological phenomena such as Freudian defense mechanisms, vestibular stimulation, anosognosia, memory repression, visual illusions, anterograde amnesia, REM sleep, dreaming, and humor.     

Adaptive Window Based 3-D Feature Selection for Multispectral Image Classification Using Firefly Algorithm

Feature extraction is the most critical step in classification of multispectral image. The classification accuracy is mainly influenced by the feature sets that are selected to classify the image. In the past, handcrafted feature sets are used which are not adaptive for different image domains. To overcome this, an evolutionary learning method is developed to automatically learn the spatial-spectral features for classification. A modified Firefly Algorithm (FA) which achieves maximum classification accuracy with reduced size of feature set is proposed to gain the interest of feature selection for this purpose. For extracting the most efficient features from the data set, we have used 3-D discrete wavelet transform which decompose the multispectral image in all three dimensions. For selecting spatial and spectral features we have studied three different approaches namely overlapping window (OW-3DFS), non-overlapping window (NW-3DFS) adaptive window cube (AW-3DFS) and Pixel based technique. Fivefold Multiclass Support Vector Machine (MSVM) is used for classification purpose. Experiments conducted on Madurai LISS IV multispectral image exploited that the adaptive window approach is used to increase the classification accuracy.     

ArRaNER: A novel named entity recognition model for biomedical literature documents

Developments in advanced innovations have prompted the generation of an immense amount of digital information. The data deluge contains hidden information that is difficult to extract. In the biomedical domain, the development of technology has caused the production of voluminous data. Processing these voluminous textual data is referred to as ‘biomedical content mining’. Emerging artificial intelligence (AI) models play a major role in the automation of Pharma 4.0. In AI, natural language processing (NLP) plays a dynamic role in extracting knowledge from biomedical documents. Research articles published by scientists and researchers contain an enormous amount of hidden information. Most of the original and peer-reviewed articles are indexed in PubMed. Extracting meaningful information from a large number of literature documents is very difficult for human beings. This research aims to extract the named entities of literature documents available in the life science domain. A high-level architecture is proposed along with a novel named entity recognition (NER) model. The model is built using rule-based machine learning (ML). The proposed ArRaNER model produced better accuracy and was also able to identify more entities. The NER model was tested on two different datasets: a PubMed dataset and a Wikipedia talk dataset. The ArRaNER model obtains an accuracy of 83.42% on the PubMed articles and 77.65% on the Wikipedia articles.

     

Extranasal Staphylococcus aureus colonization predisposes to bloodstream infections in patients on hemodialysis with noncuffed internal jugular vein catheters

Introduction: Staphylococcal infection of endogenous origin is an important cause of morbidity and mortality in patients who receive hemodialysis (HD). The risk of such infections in nasal carriers of the organism is well defined. Extranasal carriage of the organism at extranasal sites may pose similar risks. Methods: A total of 70 patients about to undergo internal jugular vein catheterization for HD were enrolled in this prospective observational study. Swab cultures were obtained from anterior nares, posterior pharynx, axillae, toe web spaces, and vascular access sites at baseline and 1 week later. A patient was defined as a persistent carrier when the same organism was grown in both samples. Staphylococcus aureus bloodstream infections were assessed by blood and catheter tip cultures over a 90‐day period. Findings: The mean age of the patients was 43.71 ± 16.2 years. Persistent S. aureus carriage at anterior nares, throat, axilla, toe web spaces, vascular access site, and all sites was documented in 27.9%, 11.4%, 40%, 32.9%, 4.3%, and 64.2% of patients, respectively. Fifteen patients developed S. aureus infections. Catheter related S. aureus infections (CRI) were more likely in persistent carriers than nonpersistent carriers with odds ratios (95% CI) of 10.2 (2.8–37.1), 8.6 (1.7–42.2), 17.3 (3.4–86.0), 3.0 (0.9–9.8), and 1.9 (0.2–22.4) for anterior nares, throat, axilla, toe web spaces, and vascular access site carriers, respectively. The probability of developing CRI in persistent S. aureus carriers was 55% compared to none in noncarriers at 90 days (P = 0.04). Discussion: Extranasal S. aureus carriage is as significant a risk factor as nasal carriage for staphylococcal infections in patients on HD through catheters. The study is limited by lack of molecular phenotyping.     

Biocompatible antimicrobial cotton fibres for healthcare industries: a biogenic approach for synthesis of bio‐organic‐coated silver nanoparticles

Cotton fibres coated with biogenically fabricated silver nanoparticles (SNPs) are most sought material because of their enhanced activity and biocompatibility. After successful synthesis of SNPs on cotton fibres using leaf extract of Vitex negundo Linn, the fibres were studied using diffuse reflectance spectroscopy, scanning electron microscopy, nanoparticle tracking analysis, energy dispersive X‐ray, and inductively coupled plasma atomic emission spectrometry. The characterisation revealed uniformly distributed spherical agglomerates of SNPs having individual particle size around 50 nm with the deposition load of 423 μg of silver per gram of cotton. Antimicrobial assay of cotton–SNPs fibres showed effective performance against pathogenic bacteria and fungi. The method is biogenic, environmentally benign, rapid, and cost‐effective, producing highly biocompatible antimicrobial coating required for the healthcare industry.Inspec keywords: cotton, health care, nanoparticles, coatings, silver, fibres, nanofabrication, scanning electron microscopy, X‐ray chemical analysis, atomic emission spectroscopy, plasma applications, microorganisms, biotechnologyOther keywords: biocompatible antimicrobial cotton fibre coating, healthcare industry, bioorganic‐coated silver nanoparticle synthesis, biogenically fabricated silver nanoparticle, SNP, leaf extraction, Vitex negundo Linn, diffuse reflectance spectroscopy, scanning electron microscopy, nanoparticle tracking analysis, energy dispersive X‐ray spectrometry, inductively coupled plasma atomic emission spectrometry, uniformly distributed spherical agglomerate, antimicrobial assay, pathogenic bacteria, fungi, Ag     

Mesoporous titanium dioxide nanocatalyst: a recyclable approach for one‐pot synthesis of 5‐hydroxymethylfurfural

The present study deals with the production of 5‐hydroxymethyl furfural (HMF) from fructose by chemo‐conversion method using chemical catalyst, conventionally achieved by microwave‐assisted dehydration process. Five different chemical catalysts, namely oxalic acid, phosphotungstic acid and mesoporous titanium dioxide nanoparticles (TNPs) were compared at constant conditions of which TNPs yielded a maxima of 33.95%. The optimum temperature and catalyst loading were found to be 200°C and 20%, respectively, at a 5% optimum substrate concentration during 15 min optimum reaction time to yield 61.53% HMF. The efficiency of synthesised TNPs was investigated further through reusability studies. TNPs were properly recycled and the catalytic activity recovery was good even after a 14 batch reactions. The specific surface area of the TNP obtained is about 105.46 m² /g and its pore‐volume is about 0.42 cm³ /g according to single point adsorption. A large accessible surface area combined with a minimal pore size (15.92 nm) obtained with mesoporous TNPs is desirable for better catalyst loading, high‐yield HMF, retention and reduced diffusion constraints.Inspec keywords: mesoporous materials, recycling, production management, dissociation, nanoparticles, nanotechnologyOther keywords: mesoporous titanium dioxide nanocatalyst, recyclable approach, one‐pot synthesis, 5‐hydroxymethyl furfural production, HMF, chemo‐conversion method, chemical catalyst, microwave‐assisted dehydration process, oxalic acid, phosphotungstic acid, mesoporous titanium dioxide nanoparticles, TNP     

Lanthanide Doped Near Infrared Active Upconversion Nanophosphors: Fundamental Concepts,Synthesis Strategies,and Technological Applications

Near infrared (NIR) light utilization in a range of current technologies has gained huge significance due to its abundance in nature and nondestructive properties. NIR active lanthanide (Ln) doped upconversion nanomaterials synthesized in controlled shape, size, and surface functionality can be combined with various pertinent materials for extensive applications in diverse fields. Upconversion nanophosphors (UCNP) possess unique abilities, such as deep tissue penetration, enhanced photostability, low toxicity, sharp emission peaks, long anti‐Stokes shift, etc., which have bestowed them with prodigious advantages over other conventional luminescent materials. As new generation fluorophores, UCNP have found a wide range of applications in various fields. In this Review, a comprehensive overview of lanthanide doped NIR active UCNP is provided by discussing the fundamental concepts including the different mechanisms proposed for explaining the upconversion processes, followed by the different strategies employed for the synthesis of these materials, and finally the technological applications of UCNP, mainly in the fields of bioimaging, drug delivery, sensing, and photocatalysis by highlighting the recent works in these areas. In addition, a brief note on the applications of UCNP in other fields is also provided along with the summary and future perspectives of these materials.     

Evaluation of potential anti‐cancer activity of cationic liposomal nanoformulated Lycopodium clavatum in colon cancer cells

Research dealing with early diagnosis and efficient treatment in colon cancer to improve patient''s survival is still under investigation. Chemotherapeutic agent result in high systemic toxicity due to their non‐specific actions on DNA repair and/or cell replication. Traditional medicine such as Lycopodium clavatum (LC) has been claimed to have therapeutic potentials against cancer. The present study focuses on targeted drug delivery of cationic liposomal nanoformulated LC (CL‐LC) in colon cancer cells (HCT15) and comparing the efficacy with an anti‐colon cancer drug, 7‐ethyl‐10‐hydroxy‐camptothecin (SN38) along with its nanoformulated form (CL‐SN38). The colloidal suspension of LC was made using thin film hydration method. The drugs were characterised using ultraviolet, dynamic light scattering, scanning electron microscopy, energy, dispersive X‐ray spectroscopy. In vitro drug release showed kinetics of 49 and 89% of SN38 and LC, whereas CL‐SN38 and CL‐LC showed 73 and 74% of sustained drug release, respectively. Studies on morphological changes, cell viability, cytotoxicity, apoptosis, cancer‐associated gene expression analysis of Bcl‐2, Bax, p53 by real‐time polymerase chain reaction and western blot analysis of Bad and p53 protein were performed. Nanoformulated LC significantly inhibited growth and increased the apoptosis of colon cancer cells indicating its potential anti‐cancer activity against colon cancer cells.Inspec keywords: cancer, biological organs, cellular biophysics, drug delivery systems, drugs, nanomedicine, genetics, DNA, molecular biophysics, biochemistry, lipid bilayers, toxicology, suspensions, colloids, light scattering, X‐ray chemical analysis, solvation, enzymes, nanostructured materialsOther keywords: energy dispersive X‐ray spectroscopy, in vitro drug release, morphological changes, cell viability, cytotoxicity, apoptosis, cancer‐associated gene expression analysis, Bcl‐2, Bax, real‐time polymerase chain reaction, western blot analysis, Bad protein, p53 protein, scanning electron microscopy, dynamic light scattering, ultraviolet scattering, thin film hydration method, colloidal suspension, nanoformulated form CL‐SN38, 7‐ethyl‐10‐hydroxy‐camptothecin, anticolon cancer drug, colon cancer cells HCT15, cationic liposomal nanoformulated LC, targeted drug delivery, therapeutic potentials, Lycopodium clavatum, traditional medicines, cell replication, DNA repair, nonspecific actions, high systemic toxicity, chemotherapeutic agents, patient survival, colon cancer treatment, colon cancer diagnosis, CL‐LC, potential anticancer activity     

Robust named entity detection from optical character recognition output

In this paper, we focus on information extraction from optical character recognition (OCR) output. Since the content from OCR inherently has many errors, we present robust algorithms for information extraction from OCR lattices instead of merely looking them up in the top-choice (1-best) OCR output. Specifically, we address the challenge of named entity detection in noisy OCR output and show that searching for named entities in the recognition lattice significantly improves detection accuracy over 1-best search. While lattice-based named entity (NE) detection improves NE recall from OCR output, there are two problems with this approach: (1) the number of false alarms can be prohibitive for certain applications and (2) lattice-based search is computationally more expensive than 1-best NE lookup. To mitigate the above challenges, we present techniques for reducing false alarms using confidence measures and for reducing the amount of computation involved in performing the NE search. Furthermore, to demonstrate that our techniques are applicable across multiple domains and languages, we experiment with optical character recognition systems for videotext in English and scanned handwritten text in Arabic.