A Scalable Optimization Mechanism for Pairwise Based Discrete Hashing.

Maintaining the pairwise relationship among originally high-dimensional data into a low-dimensional binary space is a popular strategy to learn binary codes. One simple and intuitive method is to utilize two identical code matrices produced by hash functions to approximate a pairwise real label matrix. However, the resulting quartic problem in term of hash functions is difficult to directly solve due to the non-convex and non-smooth nature of the objective. In this paper, unlike previous optimization methods using various relaxation strategies, we aim to directly solve the original quartic problem using a novel alternative optimization mechanism to linearize the quartic problem by introducing a linear regression model. Additionally, we find that gradually learning each batch of binary codes in a sequential mode, i.e. batch by batch, is greatly beneficial to the convergence of binary code learning. Based on this significant discovery and the proposed strategy, we introduce a scalable symmetric discrete hashing algorithm that gradually and smoothly updates each batch of binary codes. To further improve the smoothness, we also propose a greedy symmetric discrete hashing algorithm to update each bit of batch binary codes. Moreover, we extend the proposed optimization mechanism to solve the non-convex optimization problems for binary code learning in many other pairwise based hashing algorithms. Extensive experiments on benchmark single-label and multi-label databases demonstrate the superior performance of the proposed mechanism over recent state-of-the-art methods on two kinds of retrieval tasks: similarity and ranking order. The source codes are available on https://github.com/xsshi2015/Scalable-Pairwise-based-Discrete-Hashing.

Deep Convolutional Hashing for Low-Dimensional Binary Embedding of Histopathological Images.

Compact binary representations of histopa-thology images using hashing methods provide efficient approximate nearest neighbor search for direct visual query in large-scale databases. They can be utilized to measure the probability of the abnormality of the query image based on the retrieved similar cases, thereby providing support for medical diagnosis. They also allow for efficient managing of large-scale image databases because of a low storage requirement. However, the effectiveness of binary representations heavily relies on the visual descriptors that represent the semantic information in the histopathological images. Traditional approaches with hand-crafted visual descriptors might fail due to significant variations in image appearance. Recently, deep learning architectures provide promising solutions to address this problem using effective semantic representations. In this paper, we propose a deep convolutional hashing method that can be trained "point-wise" to simultaneously learn both semantic and binary representations of histopathological images. Specifically, we propose a convolutional neural network that introduces a latent binary encoding (LBE) layer for low-dimensional feature embedding to learn binary codes. We design a joint optimization objective function that encourages the network to learn discriminative representations from the label information, and reduce the gap between the real-valued low-dimensional embedded features and desired binary values. The binary encoding for new images can be obtained by forward propagating through the network and quantizing the output of the LBE layer. Experimental results on a large-scale histopathological image dataset demonstrate the effectiveness of the proposed method.

Oral Cancer Knowledge and Awareness in Patients Visiting Kantipur Dental College.

BACKGROUND: Lack of knowledge and awareness about oral cancer, its risk factors and negligence of the early warning signs play crucial role in raising the incidence of the disease. The present study was carried out to evaluate the awareness of oral cancer among patients visiting Kantipur Dental College, Kathmandu, Nepal. METHODS: The cross-sectional study was done in 471 patients from 15-85 years. Self administered questionnaire was prepared which comprised of knowledge of oral cancer, source of information, its early signs and symptoms along with the awareness of its risk factors. RESULTS: Most of the participants (41.80%) had not heard of oral cancer. 31.60% recognized tobacco smoking and tobacco chewing as the chief risk factor with 15.50% and 10.80% of participants who identified white patch and red patch as early sign of oral cancer respectively. Pearson's chi square test was used which showed statistically significant association of total mean knowledge score and awareness score with age, education level and occupation (p<0.05). CONCLUSIONS: This study done in dental patients showed lack of knowledge and awareness in general public about oral cancer. There seem to be a need for more planned awareness programs through newspapers, radio, television and health campaigns regarding the association of habits in the development of oral cancer and benefits of detecting oral cancer at early stage for better prognosis.

AIIMDs: An Integrated Framework of Automatic Idiopathic Inflammatory Myopathy Diagnosis for Muscle.

Idiopathic inflammatory myopathy (IIM) is a common skeletal muscle disease that relates to weakness and inflammation of muscle. Early diagnosis and prognosis of different types of IIMs will guide the effective treatment. Interpretation of digitized images of the cross-section muscle biopsy, which is currently done manually, provides the most reliable diagnostic information. With the increasing volume of images, the management and manual interpretation of the digitized muscle images suffer from low efficiency and high interobserver variabilities. In order to address these problems, we propose the first complete framework of automatic IIM diagnosis system for the management and interpretation of digitized skeletal muscle histopathology images. The proposed framework consists of several key components: (1) Automatic cell segmentation, perimysium annotation, and nuclei detection; (2) histogram-based feature extraction and quantification; (3) content-based image retrieval to search and retrieve similar cases in the database for comparative study; and (4) majority voting-based classification to provide decision support for computer-aided clinical diagnosis. Experiments show that the proposed diagnosis system provides efficient and robust interpretation of the digitized muscle image and computer-aided diagnosis of IIM.

Substance Abuse among Students in a Dental School.

INTRODUCTION: Substance abuse has become a burning issue among the medical and dental students. Dental students, who later transform into dentists, have a significant role in substance abuse cessation. Thus the study was undertaken to quantify substance abuse among dental students of Kantipur Dental College. METHODS: A descriptive cross-sectional study was conducted using pretested self-administered questionnaire among undergraduate and post graduate students of Kantipur Dental College. Convenience sampling was done and sample size was calculated. RESULTS: Study revealed 166 (74.10%) as never smokers, 3 (1.30%) as former smokers and 55 (24.60%) as current smokers. Similarly 97 (43.3%) students never used alcoholic drink, 95 (42.41%) consumed alcohol monthly, 29 (12.95%) consumed alcohol 2-4 times a month and 3 (1.34%) consumed alcohol 2-3 times a week. A total of 78 (35%) students used cannabis. CONCLUSIONS: Substantial numbers of students were indulged in deleterious habits of smoking, tobacco and cannabis intake. Students need to be properly counselled to discourage substance abuse and create a healthy society.

Effects of Fatty Acids on the Interfacial and Solution Behavior of Mixed Lipidic Aggregates Called Solid Lipid Nanoparticles.

Mutual miscibility of soylecithin, tristearin, fatty acids (FAs), and curcumin was assessed by means of surface pressure-area isotherms at the air-solution interface in order to formulate modified solid lipid nanoparticles (SLN). Appearance of minima in the excess area (Aex) and changes in free energy of mixing (∆G(0)ex) were recorded for systems with 20 mole% FAs. Modified SLNs, promising as topical drug delivery systems, were formulated using the lipids in combination with curcumin, stabilized by an aqueous Tween 60 solution. Optimal formulations were assessed by judiciously varying the FA chain length and composition. Physicochemical properties of SLNs were studied such as the size, zeta potential (by dynamic light scattering), morphology (by freeze fracture transmission electron microscopy), and thermal behavior (by differential scanning calorimetry). The size and zeta potential of the formulations were in the range 300-500 nm and -10 to -20 mV, respectively. Absorption and emission spectroscopic analyses supported the dynamic light scattering and differential scanning calorimetry data and confirmed localization of curcumin to the palisade layer of SLNs. These nanoparticles showed a sustained release of incorporated curcumin. Curcumin-loaded SLNs were effective against a gram-positive bacterial species, Bacillus amyloliquefaciens. Our results on the physicochemical properties of curcumin-loaded SLNs, the sustained release, and on antibacterial activity suggest that SLNs are promising delivery agents for topical drugs.

Spatial Clockwork Recurrent Neural Network for Muscle Perimysium Segmentation.

Accurate segmentation of perimysium plays an important role in early diagnosis of many muscle diseases because many diseases contain different perimysium inflammation. However, it remains as a challenging task due to the complex appearance of the perymisum morphology and its ambiguity to the background area. The muscle perimysium also exhibits strong structure spanned in the entire tissue, which makes it difficult for current local patch-based methods to capture this long-range context information. In this paper, we propose a novel spatial clockwork recurrent neural network (spatial CW-RNN) to address those issues. Specifically, we split the entire image into a set of non-overlapping image patches, and the semantic dependencies among them are modeled by the proposed spatial CW-RNN. Our method directly takes the 2D structure of the image into consideration and is capable of encoding the context information of the entire image into the local representation of each patch. Meanwhile, we leverage on the structured regression to assign one prediction mask rather than a single class label to each local patch, which enables both efficient training and testing. We extensively test our method for perimysium segmentation using digitized muscle microscopy images. Experimental results demonstrate the superiority of the novel spatial CW-RNN over other existing state of the arts.

Ion-pair amphiphile: a neoteric substitute that modulates the physicochemical properties of biomimetic membranes.

Ion-pair amphiphiles (IPAs) are neoteric pseudo-double-tailed compounds with potential as a novel substitute of phospholipid. IPA, synthesized by stoichiometric/equimolar mixing of aqueous solution of hexadecyltrimethylammonium bromide (HTMAB) and sodium dodecyl sulfate (SDS), was used as a potential substituent of naturally occurring phospholipid, soylecithin (SLC). Vesicles were prepared using SLC and IPA in different ratios along with cholesterol. The impact of IPA on SLC was examined by way of surface pressure (π)-area (A) measurements. Associated thermodynamic parameters were evaluated; interfacial miscibility between the components was found to depend on SLC/IPA ratio. Solution behavior of the bilayers, in the form of vesicles, was investigated by monitoring the hydrodynamic diameter, zeta potential, and polydispersity index over a period of 100 days. Size and morphology of the vesicles were also investigated by electron microscopic studies. Systems comprising 20 and 40 mol % IPA exhibited anomalous behavior. Thermal behavior of the vesicles, as scrutinized by differential scanning calorimetry, was correlated with the hydrocarbon chain as well as the headgroup packing. Entrapment efficiency (EE) of the vesicles toward the cationic dye methylene blue (MB) was also evaluated. Vesicles were smart enough to entrap the dye, and the efficiency was found to vary with IPA concentration. EE was found to be well above 80% for some stable dispersions. Such formulations thus could be considered to have potential as novel drug delivery systems.

AUTOMATIC MUSCLE PERIMYSIUM ANNOTATION USING DEEP CONVOLUTIONAL NEURAL NETWORK.

Diseased skeletal muscle expresses mononuclear cell infiltration in the regions of perimysium. Accurate annotation or segmentation of perimysium can help biologists and clinicians to determine individualized patient treatment and allow for reasonable prognostication. However, manual perimysium annotation is time consuming and prone to inter-observer variations. Meanwhile, the presence of ambiguous patterns in muscle images significantly challenge many traditional automatic annotation algorithms. In this paper, we propose an automatic perimysium annotation algorithm based on deep convolutional neural network (CNN). We formulate the automatic annotation of perimysium in muscle images as a pixel-wise classification problem, and the CNN is trained to label each image pixel with raw RGB values of the patch centered at the pixel. The algorithm is applied to 82 diseased skeletal muscle images. We have achieved an average precision of 94% on the test dataset.