An efficient multi-level pre-processing algorithm for the enhancement of dermoscopy images in melanoma detection.

In this paper, a multi-level algorithm for pre-processing of dermoscopy images is proposed, which helps in improving the quality of the raw images, making it suitable for skin lesion detection. This multi-level pre-processing method has a positive impact on automated skin lesion segmentation using Regularized Extreme Learning Machine. Raw images are subjected to de-noising, illumination correction, contrast enhancement, sharpening, reflection removal, and virtual shaving before the skin lesion segmentation. The Non-Local Means (NLM) filter with lowest Blind Reference less Image Spatial Quality Evaluator (BRISQUE) score exhibits better de-noising of dermoscopy images. To suppress uneven illumination, gamma correction is subjected to the denoised image. The Robust Image Contrast Enhancement (RICE) algorithm is used for contrast enhancement, and produces enhanced images with better structural preservation and negligible loss of information. Unsharp masking for sharpening exhibits low BRISQUE scores for better sharpening of fine details in an image. Output images produced by the phase congruency-based method in virtual shaving show high similarity with ground truth images as the hair is removed completely from the input images. Obtained scores at each stage of pre-processing framework show that the performance is superior compared to all the existing methods, both qualitatively and quantitatively, in terms of uniform contrast, preservation of information content, removal of undesired information, and elimination of artifacts in melanoma images. The output of the proposed system is assessed qualitatively and quantitatively with and without pre-processing of dermoscopy images. From the overall evaluation results, it is found that the segmentation of skin lesion is more efficient using Regularized Extreme Learning Machine if the multi-level pre-processing steps are used in proper sequence.

Regression analysis on forward modeling of diffuse optical tomography system for carcinoma cell detection.

The forward model design was employed in the Diffuse Optical Tomography (DOT) system to determine the optimal photonic flux in soft tissues like the brain and breast. Absorption coefficient (mua), reduced scattering coefficient (mus), and photonic flux (phi) were the parameters subjected to optimization. The Box-Behnken Design (BBD) method of the Response Surface Methodology (RSM) was applied to enhance the Diffuse Optical Tomography experimental system. The DC modulation voltages applied to different laser diodes of 850 nm and 780 nm wavelengths and spacing between the source and detector are the two factors operating on three optimization parameters that predicted the result through two-dimensional tissue image contours. The analysis of the Variance (ANOVA) model developed was substantial (R2 = > 0.954). The experimental results indicate that spacing and wavelength were more influential factors for rebuilding image contour. The position of the tumor in soft tissues is inspired by parameters like absorption coefficient and scattering coefficient, which depend on DC voltages applied to the Laser diode. This regression method predicted the values throughout the studied parameter space and was suitable for enhancement learning of diffuse optical tomography systems. The range of residual error percentage evaluated between experimental and predicted values for mua, mus, and phi was 0.301%, 0.287%, and 0.1%, respectively.

Early Diagnosis of Tuberculosis Using Deep Learning Approach for IOT Based Healthcare Applications.

In the modern world, Tuberculosis (TB) is regarded as a serious health issue with a high rate of mortality. TB can be cured completely by early diagnosis. For achieving this, one tool utilized is CXR (Chest X-rays) which is used to screen active TB. An enhanced deep learning (DL) model is implemented for automatic Tuberculosis detection. This work undergoes the phases like preprocessing, segmentation, feature extraction, and optimized classification. Initially, the CXR image is preprocessed and segmented using AFCM (Adaptive Fuzzy C means) clustering. Then, feature extraction and several features are extracted. Finally, these features are given to the DL classifier Deep Belief Network (DBN). To improve the classification accuracy and to optimize the DBN, a metaheuristic optimization Adaptive Monarch butterfly optimization (AMBO) algorithm is used. Here, the Deep Belief Network with Adaptive Monarch butterfly optimization (DBN-AMBO) is used for enhancing the accuracy, reducing the error function, and optimizing weighting parameters. The overall implementation is carried out on the Python platform. The overall performance evaluations of the DBN-AMBO were carried out on MC and SC datasets and compared over the other approaches on the basis of certain metrics.

Investigations on Brain Tumor Classification Using Hybrid Machine Learning Algorithms.

The imaging modalities are used to view other organs and analyze different tissues in the body. In such imaging modalities, a new and developing imaging technique is hyperspectral imaging. This multicolour representation of tissues helps us to better understand the issues compared to the previous image models. This research aims to analyze the tumor localization in the brain by performing different operations on hyperspectral images. The tumor is located using the combination of k-based clustering processes like k-nearest neighbour and k-means clustering. The value of k in both methods is determined using the optimization process called the firefly algorithm. The optimization processes reduce the manual calculation for finding K's optimal value to segment the brain regions. The labelling of the areas of the brain is done using the multilayer feedforward neural network. The proposed technique produced better results than the existing methods like hybrid k-means clustering and parallel k-means clustering by having a higher peak signal-to-noise ratio and a lesser mean absolute error value. The proposed model achieved 96.47% accuracy, 96.32% sensitivity, and 98.24% specificity, which are improved compared to other techniques.

Role of breath phase and breath boundaries for the classification between asthmatic and healthy subjects.

Asthma is an inflammatory disease of the airways which causes cough, chest tightness, wheezing and other distinct sounds during breathing. Spirometry is a golden standard lung function test, is used to monitor and diagnose asthma. Spirometry is very time-consuming and requires a lot of patient's efforts. Therefore, an alternate method which can overcome spirometry limitations is required. Sound based method can be one such alternative as it is less tedious, less time consuming and suitable for patients of all ages. It has been shown in the past that breath, among other vocal sounds, performs the best for an asthma vs healthy subject classification task. Breath consists of two phases, namely, inhale and exhale. Experiments in this work show, exhale performs better for classification task compared to the entire breath cycle as well as the inhale. However, this requires manual marking of the breath boundaries, which is a very time-consuming task. We, in this work, investigate how critical are the breath cycle and breath phase boundaries for the classification task. Experiments with chunks of random duration shows that they perform on par or better than the exhale. However, a segment comprising the second and third quarters of a breath cycle results in the highest classification accuracy of 80.64%. This suggests that, while breath phase boundaries may not be important, breath cycle boundaries could benefit in the classification task.

Medical students' perception of the reliability, usefulness and feasibility of unproctored online formative assessment tests.

Medical education has gone online because of the COVID-19 pandemic. Formative assessment is essential to facilitate the learning process in medical education. However, various challenges arise during online assessment, which include reliability, when done without monitoring and practical concerns like Internet connectivity issues. This study was done to assess the medical students' perceptions of the reliability, usefulness, and practical challenges of online tests. One hundred first-year undergraduate medical students taking up online classes and tests in the subject of physiology were enrolled in this study. A questionnaire with items regarding practical challenges, reliability, and usefulness of the online tests, in general, and about different types of online assessment methods, in particular, were sent to the students online. Each item was rated on a five-point Likert scale, and the responses were analyzed anonymously. A large percentage of students used mobile phones (81.4%) to undertake online tests. Although most students (73.2%; P < 0.001) felt that online tests helped them substantially in learning the subject, network connectivity issues were considered to be a matter of serious concern (85.5%, P < 0.001). Among the assessment methods used, viva voce by video conferencing was thought to be most reliable (83%, P < 0.001). Multiple-choice question-based assessment when done online was felt to be more practically feasible with faster feedback than classroom assessment. The results of the study suggest that medical students find online formative assessments helpful for their learning, despite their concerns about reliability and practical challenges.

Event-triggered H∞ state estimation for semi-Markov jumping discrete-time neural networks with quantization.

This paper investigates H∞ state estimation problem for a class of semi-Markovian jumping discrete-time neural networks model with event-triggered scheme and quantization. First, a new event-triggered communication scheme is introduced to determine whether or not the current sampled sensor data should be broad-casted and transmitted to the quantizer, which can save the limited communication resource. Second, a novel communication framework is employed by the logarithmic quantizer that quantifies and reduces the data transmission rate in the network, which apparently improves the communication efficiency of networks. Third, a stabilization criterion is derived based on the sufficient condition which guarantees a prescribed H∞ performance level in the estimation error system in terms of the linear matrix inequalities. Finally, numerical simulations are given to illustrate the correctness of the proposed scheme.

Reactivity of cyclopentadienyl transition metal(ii) complexes with borate ligands: structural characterization of the toluene-activated molybdenum complex [Cp*Mo(CO)2(η3-CH2C6H5)].

Reactions of cyclopentadienyl transition-metal halide complexes [Cp*Mo(CO)3Cl], 1, and [CpFe(CO)2I], 2, (Cp = C5H5; Cp* = η5-C5Me5) with borate ligands are reported. Treatment of 1 with [NaBt2] (Bt2 = dihydrobis(2-mercapto-benzothiazolyl)borate) in toluene yielded [Cp*Mo(CO)2(C7H4S2N)], 3, and [Cp*Mo(CO)2(η3-CH2C6H5)], 4, with a selective binding of toluene through C-H activation followed by orthometallation. Note that compound 4 is a structurally characterized toluene-activated molecule in which the metal is in η3-coordination mode. Under similar reaction conditions, [NaPy2] (Py2 = dihydrobis(2-mercaptopyridyl)borate) produced only the mercaptopyridyl molybdenum complex [Cp*Mo(CO)2(C5H4SN)], 5, in good yield. On the other hand, when compound 2 was treated individually with [NaBt] (Bt = trihydro(2-mercapto-benzothiazolyl)borate) and [NaPy2] in THF, formation of the η1-coordinated complexes [CpFe(CO)2(C7H4S2N)], 6, and [CpFe(CO)2(C5H4SN)], 7, was observed. The solid-state molecular structures of compounds 3, 4, 6, and 7 have been established by single-crystal X-ray crystallographic analyses.

Insertion of benzonitrile into Al-N and ga-N bonds: formation of fused carbatriaza-gallanes/alanes and their subsequent synthesis from amidines and trimethyl-gallium/aluminum.

Insertion of aromatic nitriles into Al-N and Ga-N bonds are reported. Sterically less hindered aluminum amide [PhNHAlMe2]2 (1) undergoes C≡N insertion with benzonitrile to give an isomeric mixture of tetracyclic triazaalanes {[PhNC(Ph)N]3[PhNC(Ph)NH]Al[AlMe][AlMe2]2} (2 and 3). A similar reaction with analogous gallium amide affords a tetracyclic triazagallane {[PhNC(Ph)N]3[PhNC(Ph)NH]Ga[GaMe][GaMe2]2} (6) along with a novel bowl shaped carbon containing Ga-N cluster {[PhNC(Ph)N][PhN][GaMe]2}3 (5). On the other hand, when sterically bulky gallium amide (Dipp on N, Dipp = 2,6-diisopropylphenyl) is employed, a tetrameric gallium amidinate {[(Dipp)NC(Ph)N]GaMe}4 (8) is obtained. Tetracyclic triazagallazane 6 is also synthesized from the condensation reaction of N-phenylbenzamidine with GaMe3·OEt2. Unlike AlMe3, this reaction produces only one isomer. In case of amidines with bulkier substituents on N such as Dipp, formation of a bicyclic triazagallane {[(Dipp)NC(Ph)NH]2[(Dipp)NC(Ph)N][GaMe]2} (14) is also observed along with tetrameric gallium amidinate 8, whereas N-tert-butylbenzamidine affords exclusively a tetrameric gallium amidinate {[(tert-Bu)NC(Ph)N]GaMe}4 (15) similar to its Al analogue. However, treating N-(Dipp)acetamidine with GaMe3·OEt2 gives only a bicyclic triazagallane {[(Dipp)NC(Me)NH]2[(Dipp)NC(Me)N][GaMe]2} (16). An intermediate [(tert-Bu)N(H) C(Ph)NGaMe2]2 (17), which is involved in the formation of tetrameric gallium amidinate 15, is also characterized. A comparison of the structural parameters of Ga-N-C and Al-N-C frameworks synthesized in this study is reported.

A rare case of multifocal lymphadenopathy in a young male.

Lymphadenopathy can be caused by localized and systemic diseases. While viral and bacterial infections commonly cause lymphadenitis in young adults, tuberculosis (TB) is a common cause for lymphadenopathy in endemic areas. Besides, lymphadenopathy may be a presenting manifestation of malignancy, systemic disorders and some rare diseases. Thus, relevant evaluation and exclusion of commoner causes is important to clinch the diagnosis. Histopathological examination is mandatory in such patients. We hereby report the case of a young adult male who presented with low-grade fever and abdominal pain with cervical and mesenteric lymphadenopathy in a TB endemic region, but was proved to have atypical presentation of Kikuchi-Fujimoto disease, which is a rare but benign cause of lymphadenopathy.

Development and Evaluation of Mouth Dissolving Films of Amlodipine Besylate for Enhanced Therapeutic Efficacy.

The present investigation was undertaken with an objective of formulating mouth dissolving films (MDFs) of Amlodipine Besylate (AMLO) to enhance convenience and compliance of the elderly and pediatric patients for better therapeutic efficacy. Film formers like hydroxy propyl methyl cellulose (HPMC) and methyl cellulose (MC) along with film modifiers like poly vinyl pyrrolidone K30 (PVP K30), and sodium lauryl sulphate (SLS) as solubilizing agents were evaluated. The prepared MDFs were evaluated for in vitro dissolution characteristics, in vitro disintegration time, and their physicomechanical properties. All the prepared MDFs showed good mechanical properties like tensile strength, folding endurance, and % elongation. MDFs were evaluated by means of FTIR, SEM, and X-RD studies. MDFs with 7.5% (w/w) of HPMC E3 gave better dissolution properties when compared to HPMC E5, HPMC E15, and MC. MDFs with PVP K30 and SLS gave superior dissolution properties when compared to MDFs without PVP K30 and SLS. The dissolution properties of MDFs with PVP K30 were superior when compared to MDFs with SLS. In the case of F3 containing 7.5% of HPMC E3 and 0.04% of PVP K30, complete and faster release was observed within 60 sec when compared to other formulations. Release kinetics data reveals diffusion is the release mechanism.

Preparation and Evaluation of Valsartan Liquid Filling Formulations for Soft Gels.

The present investigation includes the preparation of liquid filling formulations for soft gels using an antihypertensive drug, valsartan (VAL), in order to improve its dissolution properties and thereby its bioavailability. Formulations were prepared using excipients like polyethylene glycol 400 (PEG 400), propylene glycol (PG), polyvinylpyrrolidone (PVP K-30), antioxidants, ethanol, and purified water. Prepared formulations were evaluated for appearance, pH, drug content percentage, viscosity, stability, and in vitro dissolution studies. The compatibility between the drug and excipients in formulations was confirmed by FTIR spectra. The drug contents were in the range of 99.62-99.63 and the viscosity was in the range of 60.9-591.7 cps with all the formulations developed. Formulations containing 10 mg PVP K 30 gave better dissolution properties when compared to formulations without PVP K 30, and a complete drug dissolution was observed within 10 min and followed the first-order release kinetics. Stability studies were conducted for selected formulations (F4-F9) for a period of 6 months at room temperature (~30°C/65% RH). From the studies, it can be concluded that VAL liquid filling formulations for soft gels were successfully prepared with in vitro dissolution properties superior when compared to VAL itself.

In vivo studies on the effect of Ocimum sanctum L. leaf extract in modifying the genotoxicity induced by chromium and mercury in Allium root meristems.

In vivo cytogenetic assay in Allium cepa root tip cells has been carried out to detect the modifying effect of Ocimum sanctum aqueous leaf extract against chromium (Cr) and mercury (Hg) induced genotoxicity. It was observed that the roots post-treated with the leaf extract showed highly significant (p < 0.001) recovery in mitotic index (MI) and chromosomal aberrations (CA) when compared to pre-treated (Cr/Hg) samples and the lower doses of the leaf extract were found to be more effective than higher doses. The present study reveals that the Ocimum sanctum leaf extract possesses the protective effect against Cr/Hg induced genetic damage.

Interaction of cisplatin with planar model membranes - dose dependent change in electrical characteristics.

The drug cisplatin has broad antineoplastic activity against advanced testicular and ovarian cancers, epithelial malignancies, cancers of the head, neck, bladder, oesophagus and lungs. Peripheral neurotoxicity, ototoxicity and nephrotoxicity are its major side effects. The nonspecific action of this drug on the lipid bilayer architecture of membranes has been studied by following the effects produced on the electrical characteristics of model planar bilayer lipid membranes (BLM). The results confirm that the drug has a strong surface interaction with the zwitterionic polar head groups of the amphipathic phospholipids constituting the BLM. The permeability characteristics of cisplatin through the hydrophobic core are limited. Cisplatin does not fluidise the membrane sufficiently to cause its breakdown but creates small ion conducting defects on the membrane bilayer resulting in a marginal increase in ion conductivity. These results indicate that cisplatin exhibits a non-specific action on the lipid bilayer component of the membrane which might be partly responsible for its neurotoxic side effects.