CT-based severity assessment for COVID-19 using weakly supervised non-local CNN.

Evaluating patient criticality is the foremost step in administering appropriate COVID-19 treatment protocols. Learning an Artificial Intelligence (AI) model from clinical data for automatic risk-stratification enables accelerated response to patients displaying critical indicators. Chest CT manifestations including ground-glass opacities and consolidations are a reliable indicator for prognostic studies and show variability with patient condition. To this end, we propose a novel attention framework to estimate COVID-19 severity as a regression score from a weakly annotated CT scan dataset. It takes a non-locality approach that correlates features across different parts and spatial scales of the 3D scan. An explicit guidance mechanism from limited infection labeling drives attention refinement and feature modulation. The resulting encoded representation is further enriched through cross-channel attention. The attention model also infuses global contextual awareness into the deep voxel features by querying the base CT scan to mine relevant features. Consequently, it learns to effectively localize its focus region and chisel out the infection precisely. Experimental validation on the MosMed dataset shows that the proposed architecture has significant potential in augmenting existing methods as it achieved a 0.84 R-squared score and 0.133 mean absolute difference.

AI for COVID-19 Detection from Radiographs: Incisive Analysis of State of the Art Techniques, Key Challenges and Future Directions.

Background and objective: In recent years, Artificial Intelligence has had an evident impact on the way research addresses challenges in different domains. It has proven to be a huge asset, especially in the medical field, allowing for time-efficient and reliable solutions. This research aims to spotlight the impact of deep learning and machine learning models in the detection of COVID-19 from medical images. This is achieved by conducting a review of the state-of-the-art approaches proposed by the recent works in this field. Methods: The main focus of this study is the recent developments of classification and segmentation approaches to image-based COVID-19 detection. The study reviews 140 research papers published in different academic research databases. These papers have been screened and filtered based on specified criteria, to acquire insights prudent to image-based COVID-19 detection. Results: The methods discussed in this review include different types of imaging modality, predominantly X-rays and CT scans. These modalities are used for classification and segmentation tasks as well. This review seeks to categorize and discuss the different deep learning and machine learning architectures employed for these tasks, based on the imaging modality utilized. It also hints at other possible deep learning and machine learning architectures that can be proposed for better results towards COVID-19 detection. Along with that, a detailed overview of the emerging trends and breakthroughs in Artificial Intelligence-based COVID-19 detection has been discussed as well. Conclusion: This work concludes by stipulating the technical and non-technical challenges faced by researchers and illustrates the advantages of image-based COVID-19 detection with Artificial Intelligence techniques.

Ischemic Lesion Segmentation using Ensemble of Multi-Scale Region Aligned CNN.

The first and foremost step in the diagnosis of ischemic stroke is the delineation of the lesion from radiological images for effective treatment planning. Manual delineation of the lesion by radiological experts is generally laborious and time-consuming. Sometimes, it is prone to intra-observer and inter-observer variability. State of the art deep architectures based on Fully Convolutional Networks (FCN) and cascaded CNNs have shown good results in automated lesion segmentation. This work proposes a series of enhancements over the learning paradigm in the existing methods, by focusing on learning meticulous feature representations through the CNN layers for accurate ischemic lesion segmentation from multimodal MRI. Multiple levels of losses, integration of features from multiple scales, an ensemble of prediction maps from sub-networks are employed to enable the CNN to correlate between features seen from different receptive fields. To allow for progressive refinement of features from block to block, a custom dropout module has been proposed that suppresses noisy features. Multi-branch residual connections and attention mechanisms were also included in the CNN blocks to enable the integration of information from multiple receptive fields and selectively weigh significant features. Also, to tackle data imbalance both at voxel and sample level, patch-based modeling and separation of concerns into classification & segmentation functional branches are proposed. By incorporating the above mentioned architectural enhancements, the proposed deep architecture was able to achieve better segmentation performance against the existing models. The proposed approach was evaluated on the ISLES 2015 SISS dataset, and it achieved a mean dice coefficient of 0.775. By combining sample classification and lesion segmentation into a fully automated framework, the proposed approach has yielded better results compared to most of the existing works.

Improved binary dragonfly optimization algorithm and wavelet packet based non-linear features for infant cry classification.

BACKGROUND AND OBJECTIVE: Infant cry signal carries several levels of information about the reason for crying (hunger, pain, sleepiness and discomfort) or the pathological status (asphyxia, deaf, jaundice, premature condition and autism, etc.) of an infant and therefore suited for early diagnosis. In this work, combination of wavelet packet based features and Improved Binary Dragonfly Optimization based feature selection method was proposed to classify the different types of infant cry signals. METHODS: Cry signals from 2 different databases were utilized. First database contains 507 cry samples of normal (N), 340 cry samples of asphyxia (A), 879 cry samples of deaf (D), 350 cry samples of hungry (H) and 192 cry samples of pain (P). Second database contains 513 cry samples of jaundice (J), 531 samples of premature (Prem) and 45 samples of normal (N). Wavelet packet transform based energy and non-linear entropies (496 features), Linear Predictive Coding (LPC) based cepstral features (56 features), Mel-frequency Cepstral Coefficients (MFCCs) were extracted (16 features). The combined feature set consists of 568 features. To overcome the curse of dimensionality issue, improved binary dragonfly optimization algorithm (IBDFO) was proposed to select the most salient attributes or features. Finally, Extreme Learning Machine (ELM) kernel classifier was used to classify the different types of infant cry signals using all the features and highly informative features as well. RESULTS: Several experiments of two-class and multi-class classification of cry signals were conducted. In binary or two-class experiments, maximum accuracy of 90.18% for H Vs P, 100% for A Vs N, 100% for D Vs N and 97.61% J Vs Prem was achieved using the features selected (only 204 features out of 568) by IBDFO. For the classification of multiple cry signals (multi-class problem), the selected features could differentiate between three classes (N, A & D) with the accuracy of 100% and seven classes with the accuracy of 97.62%. CONCLUSION: The experimental results indicated that the proposed combination of feature extraction and selection method offers suitable classification accuracy and may be employed to detect the subtle changes in the cry signals.

Locality sensitivity discriminant analysis-based feature ranking of human emotion actions recognition.

[Purpose] Computational intelligence similar to pattern recognition is frequently confronted with high-dimensional data. Therefore, the reduction of the dimensionality is critical to make the manifold features amenable. Procedures that are analytically or computationally manageable in smaller amounts of data and low-dimensional space can become important to produce a better classification performance. [Methods] Thus, we proposed two stage reduction techniques. Feature selection-based ranking using information gain (IG) and Chi-square (Chisq) are used to identify the best ranking of the features selected for emotion classification in different actions including knocking, throwing, and lifting. Then, feature reduction-based locality sensitivity discriminant analysis (LSDA) and principal component analysis (PCA) are used to transform the selected feature to low-dimensional space. Two-stage feature selection-reduction methods such as IG-PCA, IG-LSDA, Chisq-PCA, and Chisq-LSDA are proposed. [Results] The result confirms that applying feature ranking combined with a dimensional-reduction method increases the performance of the classifiers. [Conclusion] The dimension reduction was performed using LSDA by denoting the features of the highest importance determined using IG and Chisq to not only improve the effectiveness but also reduce the computational time.

Congenital nasal pyriform aperture stenosis: a rare cause of neonatal nasal airway obstruction.

Congenital nasal pyriform aperture stenosis (CNPAS) is a rare cause of nasal airway obstruction that clinically mimics choanal atresia in a neonate. The differentiation between the two is very important as the management of the two conditions is different. Timely recognition is important to prevent fatal outcome. CNPAS may present as an isolated condition or with associated craniofacial anomalies. Despite typical findings of CNPAS being present on cross-sectional imaging, this condition is commonly overlooked, probably because of a lack of familiarity with the normal morphological features of the nasal cavity in infants and also owing to a lack of awareness of this rare entity. Here we report a case of CNPAS with pre- and post-surgical CT images and the complication that occurred owing to nasal stenting.

Optimal selection of mother wavelet for accurate infant cry classification.

Wavelet theory is emerging as one of the prevalent tool in signal and image processing applications. However, the most suitable mother wavelet for these applications is still a relative question mark amongst researchers. Selection of best mother wavelet through parameterization leads to better findings for the analysis in comparison to random selection. The objective of this article is to compare the performance of the existing members of mother wavelets and to select the most suitable mother wavelet for accurate infant cry classification. Optimal wavelet is found using three different criteria namely the degree of similarity of mother wavelets, regularity of mother wavelets and accuracy of correct recognition during classification processes. Recorded normal and pathological infant cry signals are decomposed into five levels using wavelet packet transform. Energy and entropy features are extracted at different sub bands of cry signals and their effectiveness are tested with four supervised neural network architectures. Findings of this study expound that, the Finite impulse response based approximation of Meyer is the best wavelet candidate for accurate infant cry classification analysis.

A new hybrid intelligent system for accurate detection of Parkinson's disease.

Elderly people are commonly affected by Parkinson's disease (PD) which is one of the most common neurodegenerative disorders due to the loss of dopamine-producing brain cells. People with PD's (PWP) may have difficulty in walking, talking or completing other simple tasks. Variety of medications is available to treat PD. Recently, researchers have found that voice signals recorded from the PWP is becoming a useful tool to differentiate them from healthy controls. Several dysphonia features, feature reduction/selection techniques and classification algorithms were proposed by researchers in the literature to detect PD. In this paper, hybrid intelligent system is proposed which includes feature pre-processing using Model-based clustering (Gaussian mixture model), feature reduction/selection using principal component analysis (PCA), linear discriminant analysis (LDA), sequential forward selection (SFS) and sequential backward selection (SBS), and classification using three supervised classifiers such as least-square support vector machine (LS-SVM), probabilistic neural network (PNN) and general regression neural network (GRNN). PD dataset was used from University of California-Irvine (UCI) machine learning database. The strength of the proposed method has been evaluated through several performance measures. The experimental results show that the combination of feature pre-processing, feature reduction/selection methods and classification gives a maximum classification accuracy of 100% for the Parkinson's dataset.

Analysis of infant cry through weighted linear prediction cepstral coefficients and Probabilistic Neural Network.

Acoustic analysis of infant cry signals has been proven to be an excellent tool in the area of automatic detection of pathological status of an infant. This paper investigates the application of parameter weighting for linear prediction cepstral coefficients (LPCCs) to provide the robust representation of infant cry signals. Three classes of infant cry signals were considered such as normal cry signals, cry signals from deaf babies and babies with asphyxia. A Probabilistic Neural Network (PNN) is suggested to classify the infant cry signals into normal and pathological cries. PNN is trained with different spread factor or smoothing parameter to obtain better classification accuracy. The experimental results demonstrate that the suggested features and classification algorithms give very promising classification accuracy of above 98% and it expounds that the suggested method can be used to help medical professionals for diagnosing pathological status of an infant from cry signals.

Normal and hypoacoustic infant cry signal classification using time-frequency analysis and general regression neural network.

Crying is the most noticeable behavior of infancy. Infant cry signals can be used to identify physical or psychological status of an infant. Recently, acoustic analysis of infant cry signal has shown promising results and it has been proven to be an excellent tool to investigate the pathological status of an infant. This paper proposes short-time Fourier transform (STFT) based time-frequency analysis of infant cry signals. Few statistical features are derived from the time-frequency plot of infant cry signals and used as features to quantify infant cry signals. General Regression Neural Network (GRNN) is employed as a classifier for discriminating infant cry signals. Two classes of infant cry signals are considered such as normal cry signals and pathological cry signals from deaf infants. To prove the reliability of the proposed features, two neural network models such as Multilayer Perceptron (MLP) and Time-Delay Neural Network (TDNN) trained by scaled conjugate gradient algorithm are also used as classifiers. The experimental results show that the GRNN classifier gives very promising classification accuracy compared to MLP and TDNN and the proposed method can effectively classify normal and pathological infant cries.

Luminance sticker based facial expression recognition using discrete wavelet transform for physically disabled persons.

Developing tools to assist physically disabled and immobilized people through facial expression is a challenging area of research and has attracted many researchers recently. In this paper, luminance stickers based facial expression recognition is proposed. Recognition of facial expression is carried out by employing Discrete Wavelet Transform (DWT) as a feature extraction method. Different wavelet families with their different orders (db1 to db20, Coif1 to Coif 5 and Sym2 to Sym8) are utilized to investigate their performance in recognizing facial expression and to evaluate their computational time. Standard deviation is computed for the coefficients of first level of wavelet decomposition for every order of wavelet family. This standard deviation is used to form a set of feature vectors for classification. In this study, conventional validation and cross validation are performed to evaluate the efficiency of the suggested feature vectors. Three different classifiers namely Artificial Neural Network (ANN), k-Nearest Neighborhood (kNN) and Linear Discriminant Analysis (LDA) are used to classify a set of eight facial expressions. The experimental results demonstrate that the proposed method gives very promising classification accuracies.

Classification of speech dysfluencies using LPC based parameterization techniques.

The goal of this paper is to discuss and compare three feature extraction methods: Linear Predictive Coefficients (LPC), Linear Prediction Cepstral Coefficients (LPCC) and Weighted Linear Prediction Cepstral Coefficients (WLPCC) for recognizing the stuttered events. Speech samples from the University College London Archive of Stuttered Speech (UCLASS) were used for our analysis. The stuttered events were identified through manual segmentation and were used for feature extraction. Two simple classifiers namely, k-nearest neighbour (kNN) and Linear Discriminant Analysis (LDA) were employed for speech dysfluencies classification. Conventional validation method was used for testing the reliability of the classifier results. The study on the effect of different frame length, percentage of overlapping, value of ã in a first order pre-emphasizer and different order p were discussed. The speech dysfluencies classification accuracy was found to be improved by applying statistical normalization before feature extraction. The experimental investigation elucidated LPC, LPCC and WLPCC features can be used for identifying the stuttered events and WLPCC features slightly outperforms LPCC features and LPC features.

Identification and characterization of a principal oxidation impurity in clopidogrel drug substance and drug product.

The focus of this study is identification, isolation and characterization of a principal oxidation impurity of clopidogrel which ranged from 0.05 to 0.12% using high performance liquid chromatography. This impurity is considered as principal oxidation impurity as it is observed in oxidative degradation (stress) study. Preparative HPLC with Xterra MS C18 ODB column was used to isolate the impurity. The isolated impurity was co-injected with the sample containing impurities and found the retention time match of the spiked impurities. A thorough study was undertaken to characterize this impurity and based on their spectral data (UV, MS, MSn 1H/13C, DEPT and 2D NMR) the structure was characterized as 5-[1-(2-chlorophenyl)-2-methoxy-2-oxoethyl]-6,7-dihydrothieno[3,2-c]pyridin-5-ium with a molecular weight 320 amu.

Solvent, emulsifier and drug concentration factors in poly(D,L-lactic acid) microspheres containing hexamethylmelamine.

Biodegradable poly(D,L-lactic acid) (PLA) microspheres containing hexamethylmelamine (HMM) were developed for potential use in chemoembolization and intraperitoneal implantation. The emulsion-solvent-evaporation/extraction method was used to prepare 15 formulations with different drug/polymer ratios, solvent compositions and emulsifer concentrations in the continuous aqueous phase. A central composite experimental design was used, with five levels of the three different factors. All formulations resulted in the formation of discrete matrix microspheres containing crystalline drug. The mean particle sizes of the microsphere formulations ranged from 62-348 microm and the effect of the independent variables on microsphere size was satisfactorily predicted using response surface methodology. For theoretical drug loads of 5-40%, efficiency of entrapment ranged from 75-107% and porosities of the microspheres were between 0-6.5%. The rate of drug release from the microspheres depended on drug loading and particle size. Microspheres with 22.5% or greater theoretical drug content released drug rapidly, with almost complete release occurring in 70 h or less. Formulations with drug loading of 5% and 9.57%, however, released drug very slowly, with less than 50% released in 40 days. Release kinetics of narrow sieve cuts of microspheres with high drug load (35.4%) followed square root of time profiles.

Controlled-release tablets from carrageenans: effect of formulation, storage and dissolution factors.

The purpose of this study was to investigate the potential of two carrageenans, iota-carrageenan and lambda-carrageenan for the preparation of controlled-release tablets. Tablets were compressed on a Carver press and the effect of formulation factors, moisture, and storage on the release of theophylline was studied. The effect of sodium chloride in the tablet formulation and a change in the ionic strength of the dissolution media was studied on the release of three model drugs. The release rate increased both with an increase in tablet diameter and increase in drug to carrageenan ratio in the tablets. The two lubricants studied had a negligible effect on the rate of drug release at their commonly used concentrations. Moisture content of carrageenans, storage of tablets at 37 degrees C/75% RH for 3 months, and incorporation of 10% sodium chloride in the tablets did not have any significant effect on the release rate. The change in ionic strength of simulated gastric fluid altered the release rate whereas the ionic strength of simulated intestinal fluid did not have a significant effect on the release rate. Carrageenan tablets were relatively insensitive to small changes in formulation parameters and dissolution conditions.

Heat shock protein-peptide complexes elicit cytotoxic T-lymphocyte and antibody responses specific for bovine herpesvirus 1.

Epitope-based vaccines offer a promising alternative to modified live vaccines against viruses such as herpesviruses which give rise to latent infections, and induce immunosuppression. The success of this approach depends on the ability to direct the CTL epitopes to the MHC class I antigen presentation pathway. The objective of this study was to evaluate the potential of the heat shock protein gp96 in this regard. A group of BALB/c mice was injected with three murine CTL epitope peptides of bovine herpesvirus 1 (BHV-1) complexed in vitro with bovine gp96 (gp96-peptides). Three other groups were injected with either the peptides alone, gp96 alone, or the peptides complexed with BSA. CTLs from mice immunized with gp96-peptides specifically lysed the peptide-pulsed syngeneic targets, as well as BHV-1-infected targets. CTLs from the other three groups did not lyse these targets. To further evaluate the utility of this approach, groups of BALB/c mice were immunized with gp96 isolated from a syngeneic cell-line transduced with BHV-1 glycoprotein D (BC-gD). Mice immunized with gp96 from BC-gD developed CTLs, as well as Abs specific for BHV-1 gD. Furthermore, in vitro stimulation of naive bovine PBMCs with gp96 from BC-gD resulted in CTLs specific for BHV-1. These results demonstrate the feasibility of using gp96-peptide complexes isolated from cells expressing BHV-1 proteins to induce CTL and Ab responses against BHV-1, without the prior knowledge of the CTL and Ab epitope sequences.

Sustained high-level expression of full-length human factor VIII and restoration of clotting activity in hemophilic mice using a minimal adenovirus vector.

The successful prophylactic treatment of hemophilia A by frequent infusions of plasma concentrates or recombinant factor VIII (hFVIII) indicates that gene therapy may be a potential alternative for the treatment of the disease. For efficient delivery and long-term expression of the hFVIII gene, a novel minimal adenovirus (mini-Ad) vector, MiniAdFVIII, has been developed. The vector is devoid of all viral genes and carries the full-length hFVIII cDNA under the control of the human 12.5-kb albumin promoter. The MiniAdFVIII vector was propagated with the assistance of an ancillary vector in 293 cells and was purified by CsCl banding. Sustained expression of hFVIII at physiologic levels (100-800 ng/mL) was achieved in mice after a single intravenous injection of MiniAdFVIII. The expressed hFVIII had a structure identical to that of recombinant hFVIII, as determined by Western blot analysis. The functionality of the protein was confirmed by the restoration of blood coagulation capacity in MiniAdFVIII-treated hemophilic mice, as determined by tail clipping observations. Although antivector or antihuman FVIII antibodies at various levels were detected, long-term expression of the transgene was observed in the mice that did not generate antibodies against the transgene product. The vector DNA persisted in the liver tissues of the mice with long-term expression. No significant histopathologic findings or toxicities were observed to be associated with the vector in the MiniAdFVIII-treated C57BL/6 mice. These results support the further development of MiniAdFVIII for clinical trials toward the treatment of hemophilia A.

A case-control study on risk factors for pancreatic diseases in Kerala, India.

BACKGROUND/AIMS: We simultaneously conducted case-control studies, in Kerala of South India, on chronic calcific pancreatitis of the tropics (CCPT), pancreatic ductal adenocarcinoma (PDA) with CCPT, and PDA alone to assess similarity of and difference between their risk factors. METHODOLOGY: Cases with one of these diseases were identified at the Trivandrum Medical College (TMC) Hospital, in Kerala, from 1994 to 1996. Controls were selected from healthy hospital visitors of the TMC Hospital by individual age (within +/- 3 years) and sex-matched with the index case. Odds ratios and their 95% confidence intervals for potential risk factors were calculated. RESULTS: Frequent consumption of cassava was positively associated with the risk of PDA with CCPT. Heavy cigarette smoking and drinking large amounts of coffee and/or tea everyday were positively related to the risk of PDA alone. Frequent consumption of vegetables and/or fruits was correlated to the decreased risk of PDA alone. CONCLUSIONS: Risk factors as well as preventive factors seem to be different between PDA with CCPT and PDA alone. Further study is necessary, especially to clarify the prognostic factors which would induce pancreatic malignancy in patients with CCPT.

Stable alphavirus packaging cell lines for Sindbis virus and Semliki Forest virus-derived vectors.

Alphavirus vectors are being developed for possible human vaccine and gene therapy applications. We have sought to advance this field by devising DNA-based vectors and approaches for the production of recombinant vector particles. In this work, we generated a panel of alphavirus vector packaging cell lines (PCLs). These cell lines were stably transformed with expression cassettes that constitutively produced RNA transcripts encoding the Sindbis virus structural proteins under the regulation of their native subgenomic RNA promoter. As such, translation of the structural proteins was highly inducible and was detected only after synthesis of an authentic subgenomic mRNA by the vector-encoded replicase proteins. Efficient production of biologically active vector particles occurred after introduction of Sindbis virus vectors into the PCLs. In one configuration, the capsid and envelope glycoproteins were separated into distinct cassettes, resulting in vector packaging levels of 10(7) infectious units/ml, but reducing the generation of contaminating replication-competent virus below the limit of detection. Vector particle seed stocks could be amplified after low multiplicity of infection of PCLs, again without generating replication-competent virus, suggesting utility for production of large-scale vector preparations. Furthermore, both Sindbis virus-based and Semliki Forest virus-based vectors could be packaged with similar efficiency, indicating the possibility of developing a single PCL for use with multiple alphavirus-derived vectors.