ChestCovidNet: An Effective DL-based Approach for COVID-19, Lung Opacity, and Pneumonia Detection Using Chest Radiographs Images.

Currently used lung disease screening tools are expensive in terms of money and time. Therefore, chest radiograph images (CRIs) are employed for prompt and accurate COVID-19 identification. Recently, many researchers have applied Deep learning (DL) based models to detect COVID-19 automatically. However, their model could have been more computationally expensive and less robust, i.e., its performance degrades when evaluated on other datasets. This study proposes a trustworthy, robust, and lightweight network (ChestCovidNet) that can detect COVID-19 by examining various CRIs datasets. The ChestCovidNet model has only 11 learned layers, eight convolutional (Conv) layers, and three fully connected (FC) layers. The framework employs both the Conv and group Conv layers, Leaky Relu activation function, shufflenet unit, Conv kernels of 3×3 and 1×1 to extract features at different scales, and two normalization procedures that are cross-channel normalization and batch normalization. We used 9013 CRIs for training whereas 3863 CRIs for testing the proposed ChestCovidNet approach. Furthermore, we compared the classification results of the proposed framework with hybrid methods in which we employed DL frameworks for feature extraction and support vector machines (SVM) for classification. The study's findings demonstrated that the embedded low-power ChestCovidNet model worked well and achieved a classification accuracy of 98.12% and recall, F1-score, and precision of 95.75%.

Overcoming Diffusion Limitation of Faradaic Processes: Property-Performance Relationships of 2D Conductive Metal-Organic Framework Cu3 (HHTP)2 for Reversible Lithium-Ion Storage.

Faradaic reactions including charge transfer are often accompanied with diffusion limitation inside the bulk. Conductive two-dimensional frameworks (2D MOFs) with a fast ion transport can combine both-charge transfer and fast diffusion inside their porous structure. To study remaining diffusion limitations caused by particle morphology, different synthesis routes of Cu-2,3,6,7,10,11-hexahydroxytriphenylene (Cu3 (HHTP)2 ), a copper-based 2D MOF, are used to obtain flake- and rod-like MOF particles. Both morphologies are systematically characterized and evaluated for redox-active Li+ ion storage. The redox mechanism is investigated by means of X-ray absorption spectroscopy, FTIR spectroscopy and in situ XRD. Both types are compared regarding kinetic properties for Li+ ion storage via cyclic voltammetry and impedance spectroscopy. A significant influence of particle morphology for 2D MOFs on kinetic aspects of electrochemical Li+ ion storage can be observed. This study opens the path for optimization of redox active porous structures to overcome diffusion limitations of Faradaic processes.

An Efficient Deep Learning Approach to Automatic Glaucoma Detection Using Optic Disc and Optic Cup Localization.

Glaucoma is an eye disease initiated due to excessive intraocular pressure inside it and caused complete sightlessness at its progressed stage. Whereas timely glaucoma screening-based treatment can save the patient from complete vision loss. Accurate screening procedures are dependent on the availability of human experts who performs the manual analysis of retinal samples to identify the glaucomatous-affected regions. However, due to complex glaucoma screening procedures and shortage of human resources, we often face delays which can increase the vision loss ratio around the globe. To cope with the challenges of manual systems, there is an urgent demand for designing an effective automated framework that can accurately identify the Optic Disc (OD) and Optic Cup (OC) lesions at the earliest stage. Efficient and effective identification and classification of glaucomatous regions is a complicated job due to the wide variations in the mass, shade, orientation, and shapes of lesions. Furthermore, the extensive similarity between the lesion and eye color further complicates the classification process. To overcome the aforementioned challenges, we have presented a Deep Learning (DL)-based approach namely EfficientDet-D0 with EfficientNet-B0 as the backbone. The presented framework comprises three steps for glaucoma localization and classification. Initially, the deep features from the suspected samples are computed with the EfficientNet-B0 feature extractor. Then, the Bi-directional Feature Pyramid Network (BiFPN) module of EfficientDet-D0 takes the computed features from the EfficientNet-B0 and performs the top-down and bottom-up keypoints fusion several times. In the last step, the resultant localized area containing glaucoma lesion with associated class is predicted. We have confirmed the robustness of our work by evaluating it on a challenging dataset namely an online retinal fundus image database for glaucoma analysis (ORIGA). Furthermore, we have performed cross-dataset validation on the High-Resolution Fundus (HRF), and Retinal Image database for Optic Nerve Evaluation (RIM ONE DL) datasets to show the generalization ability of our work. Both the numeric and visual evaluations confirm that EfficientDet-D0 outperforms the newest frameworks and is more proficient in glaucoma classification.

Toward Realigning Automatic Speaker Verification in the Era of COVID-19.

The use of face masks has increased dramatically since the COVID-19 pandemic started in order to to curb the spread of the disease. Additionally, breakthrough infections caused by the Delta and Omicron variants have further increased the importance of wearing a face mask, even for vaccinated individuals. However, the use of face masks also induces attenuation in speech signals, and this change may impact speech processing technologies, e.g., automated speaker verification (ASV) and speech to text conversion. In this paper we examine Automatic Speaker Verification (ASV) systems against the speech samples in the presence of three different types of face mask: surgical, cloth, and filtered N95, and analyze the impact on acoustics and other factors. In addition, we explore the effect of different microphones, and distance from the microphone, and the impact of face masks when speakers use ASV systems in real-world scenarios. Our analysis shows a significant deterioration in performance when an ASV system encounters different face masks, microphones, and variable distance between the subject and microphone. To address this problem, this paper proposes a novel framework to overcome performance degradation in these scenarios by realigning the ASV system. The novelty of the proposed ASV framework is as follows: first, we propose a fused feature descriptor by concatenating the novel Ternary Deviated overlapping Patterns (TDoP), Mel Frequency Cepstral Coefficients (MFCC), and Gammatone Cepstral Coefficients (GTCC), which are used by both the ensemble learning-based ASV and anomaly detection system in the proposed ASV architecture. Second, this paper proposes an anomaly detection model for identifying vocal samples produced in the presence of face masks. Next, it presents a Peak Norm (PN) filter to approximate the signal of the speaker without a face mask in order to boost the accuracy of ASV systems. Finally, the features of filtered samples utilizing the PN filter and samples without face masks are passed to the proposed ASV to test for improved accuracy. The proposed ASV system achieved an accuracy of 0.99 and 0.92, respectively, on samples recorded without a face mask and with different face masks. Although the use of face masks affects the ASV system, the PN filtering solution overcomes this deficiency up to 4%. Similarly, when exposed to different microphones and distances, the PN approach enhanced system accuracy by up to 7% and 9%, respectively. The results demonstrate the effectiveness of the presented framework against an in-house prepared, diverse Multi Speaker Face Masks (MSFM) dataset, (IRB No. FY2021-83), consisting of samples of subjects taken with a variety of face masks and microphones, and from different distances.

A Robust End-to-End Deep Learning-Based Approach for Effective and Reliable BTD Using MR Images.

Detection of a brain tumor in the early stages is critical for clinical practice and survival rate. Brain tumors arise in multiple shapes, sizes, and features with various treatment options. Tumor detection manually is challenging, time-consuming, and prone to error. Magnetic resonance imaging (MRI) scans are mostly used for tumor detection due to their non-invasive properties and also avoid painful biopsy. MRI scanning of one patient's brain generates many 3D images from multiple directions, making the manual detection of tumors very difficult, error-prone, and time-consuming. Therefore, there is a considerable need for autonomous diagnostics tools to detect brain tumors accurately. In this research, we have presented a novel TumorResnet deep learning (DL) model for brain detection, i.e., binary classification. The TumorResNet model employs 20 convolution layers with a leaky ReLU (LReLU) activation function for feature map activation to compute the most distinctive deep features. Finally, three fully connected classification layers are used to classify brain tumors MRI into normal and tumorous. The performance of the proposed TumorResNet architecture is evaluated on a standard Kaggle brain tumor MRI dataset for brain tumor detection (BTD), which contains brain tumor and normal MR images. The proposed model achieved a good accuracy of 99.33% for BTD. These experimental results, including the cross-dataset setting, validate the superiority of the TumorResNet model over the contemporary frameworks. This study offers an automated BTD method that aids in the early diagnosis of brain cancers. This procedure has a substantial impact on improving treatment options and patient survival.

AFD-StackGAN: Automatic Mask Generation Network for Face De-Occlusion Using StackGAN.

To address the problem of automatically detecting and removing the mask without user interaction, we present a GAN-based automatic approach for face de-occlusion, called Automatic Mask Generation Network for Face De-occlusion Using Stacked Generative Adversarial Networks (AFD-StackGAN). In this approach, we decompose the problem into two primary stages (i.e., Stage-I Network and Stage-II Network) and employ a separate GAN in both stages. Stage-I Network (Binary Mask Generation Network) automatically creates a binary mask for the masked region in the input images (occluded images). Then, Stage-II Network (Face De-occlusion Network) removes the mask object and synthesizes the damaged region with fine details while retaining the restored face's appearance and structural consistency. Furthermore, we create a paired synthetic face-occluded dataset using the publicly available CelebA face images to train the proposed model. AFD-StackGAN is evaluated using real-world test images gathered from the Internet. Our extensive experimental results confirm the robustness and efficiency of the proposed model in removing complex mask objects from facial images compared to the previous image manipulation approaches. Additionally, we provide ablation studies for performance comparison between the user-defined mask and auto-defined mask and demonstrate the benefits of refiner networks in the generation process.

Stochastic Recognition of Human Physical Activities via Augmented Feature Descriptors and Random Forest Model.

Human physical activity recognition from inertial sensors is shown to be a successful approach for monitoring elderly individuals and children in indoor and outdoor environments. As a result, researchers have shown significant interest in developing state-of-the-art machine learning methods capable of utilizing inertial sensor data and providing key decision support in different scenarios. This paper analyzes data-driven techniques for recognizing human daily living activities. Therefore, to improve the recognition and classification of human physical activities (for example, walking, drinking, and running), we introduced a model that integrates data preprocessing methods (such as denoising) along with major domain features (such as time, frequency, wavelet, and time-frequency features). Following that, stochastic gradient descent (SGD) is used to improve the performance of the extracted features. The selected features are catered to the random forest classifier to detect and monitor human physical activities. Additionally, the proposed HPAR system was evaluated on five benchmark datasets, namely the IM-WSHA, PAMAP-2, UCI HAR, MobiAct, and MOTIONSENSE databases. The experimental results show that the HPAR system outperformed the present state-of-the-art methods with recognition rates of 90.18%, 91.25%, 91.83%, 90.46%, and 92.16% from the IM-WSHA, PAMAP-2, UCI HAR, MobiAct, and MOTIONSENSE datasets, respectively. The proposed HPAR model has potential applications in healthcare, gaming, smart homes, security, and surveillance.

[Deep periocular trauma with affection of the lacrimal ducts during Caesarean section]. / Tiefes periokuläres Trauma mit Tränenwegsbeteiligung durch Kaiserschnittentbindung.

Periocular injuries during a caesarean section are extremely rare. The case report of a five hour old newborn addresses the trauma management concerning diagnostics, therapy, and post-operative care of a deep periocular soft tissue injury. The pattern of injury consisted of full thickness wounds of the medial and lateral lid margins, opening of the superior conjunctival fornix, and penetration of Tenon's capsule. The reconstruction was performed layer by layer while an autostable monocanaliculonasal lacrimal intubation was inserted.

Proton Conduction in a Single Crystal of a Phosphonato-Sulfonate-Based Coordination Polymer: Mechanistic Insight.

The proton conduction properties of a phosphonato-sulfonate-based coordination polymer are studied by impedance spectroscopy using a single crystal specimen. Two distinct conduction mechanisms are identified. Water-mediated conductance along the crystal surface occurs by mass transport, as evidenced by a high activation energy (0.54 eV). In addition, intrinsic conduction by proton 'hopping' through the interior of the crystal with a low activation energy (0.31 eV) is observed. This latter conduction is anisotropic with respect to the crystal structure and seems to occur through a channel along the c axis of the orthorhombic crystal. Proton conduction is assumed to be mediated by sulfonate groups and non-coordinating water molecules that are part of the crystal structure.

Detection of BCR-ABL fusion gene and its transcript variants in chronic myeloid leukaemia patients - a multi-comparison study.

OBJECTIVE: To compare blood cells and plasma for BCR-ABL quantification and to find out the frequency of b2a2, b3a2 and e1a2 transcripts in chronic myeloid leukaemia patients, and to assess the correlation of BCR-ABL transcripts with haematological counts, age and gender. METHODS: The study was conducted in April 2018 at King Edward Medical University, Lahore, Pakistan, and comprised chronic myeloid leukaemia patients from Mayo Hospital, Lahore. Ribonucleic acid was extracted using commercial extraction kits and detection of BCR-ABL messenger ribonucleic acid and its transcript variants was done by real time polymerase chain reaction. Data was analysed using SPSS 11.5. RESULTS: Of the 48 patients, fusion of b3a2 was detected in 32(66.66%) and b2a2 in 10(32.10%), while fusion e1a2 was not detected at all. No co-expression of transcripts was seen in any patient. No significant correlation was found between transcript type and any of haematological parameters (p>0.05). No significant correlation of transcript type with gender and age was found (p>0.05). BCR-ABL/G6PD ratios in peripheral blood cells were higher than that of plasma (p<0.05). CONCLUSIONS: Plasma can be used as an alternative to blood cells for BCR-ABL quantification, and transcript types cannot be easily explained by clinical factors.

Compared cardiorespiratory endurance and musculoskeletal legs explosive power in students of Tsinghua University Beijing China and University of Sindh Pakistan.

OBJECTIVE: To assess the health-related physical fitness status of students and the attributes of performance in terms of endurance and power. METHODS: The cross-sectional study was conducted at University of Sindh, Jamshoro, Pakistan, and Tsinghua University, Beijing, China, during academic session of January 2012 to December 2013, and comprised an equal number of male and female students aged 18-23 years. Prior to the assessment, physical activity readiness questionnaire was filled by all the subjects, while standardised health-related physical fitness criterion was used to make comparisons in terms of oxygen consumption. . RESULTS: There were 600 subjects in all; 300(50%) at each of the two centres, and at both centres, there were 150(25%) boys and 150(25%) girls. Both for power and endurance, mean values of Chinese students were significantly better than their Pakistani counterparts (p<0.05). CONCLUSIONS: Chinese students had better health-related physical fitness levels than Pakistani students of either gender.

Efficient Photocatalytic Degradation of Norfloxacin in Aqueous Media by Hydrothermally Synthesized Immobilized TiO2/Ti Films with Exposed {001} Facets.

In this study, a novel immobilized TiO2/Ti film with exposed {001} facets was prepared via a facile one-pot hydrothermal route for the degradation of norfloxacin from aqueous media. The effects of various hydrothermal conditions (i.e., solution pH, hydrothermal time (HT) and HF concentration) on the growth of {001} faceted TiO2/Ti film were investigated. The maximum photocatalytic performance of {001} faceted TiO2/Ti film was observed when prepared at pH 2.62, HT of 3 h and at HF concentration of 0.02 M. The as-prepared {001} faceted TiO2/Ti films were fully characterized by field-emission scanning electron microscope (FE-SEM), X-ray diffraction (XRD), high resolution transmission electron microscope (HR-TEM), and X-ray photoelectron spectroscopy (XPS). More importantly, the as-prepared {001} faceted TiO2/Ti film exhibited excellent photocatalytic performance toward degradation of norfloxacin in various water matrices (Milli-Q water, tap water, river water and synthetic wastewater). The individual influence of various anions (SO42-, HCO3-, NO3-, Cl-) and cations (K+, Ca2+, Mg2+, Cu2+, Na+, Fe3+) usually present in the real water samples on the photocatalytic performance of as-prepared TiO2/Ti film with exposed {001} facet was investigated. The mechanistic studies revealed that •OH is mainly involved in the photocatalytic degradation of norfloxacin by {001} faceted TiO2/Ti film. In addition, norfloxacin degradation byproducts were investigated, on the basis of which degradation schemes were proposed.

Intra-operative implantation errors during Austin Moore Hemiarthroplasty.

Austin Moore hemiarthroplasty is an established treatment in elderly patients with neck of femur fractures. Being commonly performed, it is also associated with several technical errors of implantation which results in complications and failure requiring revision surgery. This retrospective pre- and post-operative radiographic study to determine the frequency of technical errors was conducted at the Indus Hospital, Karachi, and comprised data of 50 patients who underwent Austin Moore hemiarthroplasty between January and November 2016. Of the total, 29(58%%) patients had no error of implantation. Overhanging of prosthesis was observed in 21(42%) patients, followed by inadequate length of the neck remnant in 18(36%). Moreover, 8(16%) patients sustained intra-operative periprosthetic fractures managed with cerclage wire. Also, 33(66%) patients had a Dorr type-Afemur morphologic pattern. Hemiarthroplasty was found to be a technically demanding procedure associated with avoidable intra-operative implantation errors by proper preoperative planning, careful patient selection, proper training of surgeons, hence avoiding failure.

Buried Probe in Complex Congenital Nasolacrimal Duct Obstructions: Clinical Profiles and Outcomes.

PURPOSE: To report the clinical profiles and outcomes of buried probe variant of complex congenital nasolacrimal duct obstruction (CNLDO). METHODS: Retrospective chart review of all patients endoscopically diagnosed as a buried probe variant of complex CNLDO, over a 3.5 year period from a single surgeon's (MJA) database were included in the study. A detailed lacrimal system evaluation was performed and intraoperative findings including nasal endoscopy were documented. A minimum follow up of 3 months following the final intervention was considered for analysis. Anatomical and functional success of the interventions was assessed at the final follow up. RESULTS: Twenty-two eyes of 21 patients with buried probes were studied. The mean age at presentations was 41.2 months. Epiphora and discharge were the commonest presenting symptoms noted in 77.2% (17/22). Associated lacrimal anomalies include punctal agenesis, incomplete punctal canalization and atonic lacrimal sac. All patients underwent irrigation and probing under nasal endoscopic guidance. Further, 3 patients underwent endoscopic dacryocystorhinostomy for persistent CNLDO. At a mean follow up of 4.9 months, the final anatomical and functional successes were noted in 90.9% and 81.8%, respectively. CONCLUSIONS: Buried probe is a variant of complex CNLDO, noted more commonly in older children. Endoscopic guidance is crucial for its diagnosis and satisfactory outcomes.

Canaliculops Associated With Punctal Agenesis: A Clinicopathological Correlation and Review of Literature.

Canaliculops or canaliculocele is a rare form of noninflammatory and noninfectious canalicular ectasia. To the best of the authors' knowledge, so far only 5 such cases have been described in the literature. Typical clinical and characteristic immunohistochemical features aid in the diagnosis. Although rare, it should be kept in the differential diagnosis of cystic lesions in the medial canthus area. The authors report the sixth such case, but the first case to show an association with punctal agenesis. Addition of more such cases to literature will help unravel the etiopathogenesis of this intriguing canalicular disorder.

Recognition of diabetic retinopathy and macular edema using deep learning.

Diabetic retinopathy (DR) and diabetic macular edema (DME) are both serious eye conditions associated with diabetes and if left untreated, and they can lead to permanent blindness. Traditional methods for screening these conditions rely on manual image analysis by experts, which can be time-consuming and costly due to the scarcity of such experts. To overcome the aforementioned challenges, we present the Modified CornerNet approach with DenseNet-100. This system aims to localize and classify lesions associated with DR and DME. To train our model, we first generate annotations for input samples. These annotations likely include information about the location and type of lesions within the retinal images. DenseNet-100 is a deep CNN used for feature extraction, and CornerNet is a one-stage object detection model. CornerNet is known for its ability to accurately localize small objects, which makes it suitable for detecting lesions in retinal images. We assessed our technique on two challenging datasets, EyePACS and IDRiD. These datasets contain a diverse range of retinal images, which is important to estimate the performance of our model. Further, the proposed model is also tested in the cross-corpus scenario on two challenging datasets named APTOS-2019 and Diaretdb1 to assess the generalizability of our system. According to the accomplished analysis, our method outperformed the latest approaches in terms of both qualitative and quantitative results. The ability to effectively localize small abnormalities and handle over-fitted challenges is highlighted as a key strength of the suggested framework which can assist the practitioners in the timely recognition of such eye ailments.

A Tale of Two Diagnoses; Gout Vs Chronic Osteomyelitis. A Case Report.

Gout can potentially be diagnosed clinically and treated, if classical symptoms are present. In some cases, gout and osteomyelitis can have similar presenting signs and symptoms and it may be difficult to differentiate just on clinical presentation, routine laboratory workup and imaging like radiography or ultrasound. Arthrocentesis can be crucial in such scenarios to differentiate the two entities as missed opportunity to treat infectious etiology can have detrimental outcomes. We present a case of patient with ankle pain and swelling treated as recurrent gout, as there were no risk factors for osteomyelitis. Arthrocentesis confirmed the diagnosis of osteomyelitis and patient was treated with intravenous antibiotics, resulting in resolution of symptoms.

Somtimes: self organizing maps for time series clustering and its application to serious illness conversations.

There is demand for scalable algorithms capable of clustering and analyzing large time series data. The Kohonen self-organizing map (SOM) is an unsupervised artificial neural network for clustering, visualizing, and reducing the dimensionality of complex data. Like all clustering methods, it requires a measure of similarity between input data (in this work time series). Dynamic time warping (DTW) is one such measure, and a top performer that accommodates distortions when aligning time series. Despite its popularity in clustering, DTW is limited in practice because the runtime complexity is quadratic with the length of the time series. To address this, we present a new a self-organizing map for clustering TIME Series, called SOMTimeS, which uses DTW as the distance measure. The method has similar accuracy compared with other DTW-based clustering algorithms, yet scales better and runs faster. The computational performance stems from the pruning of unnecessary DTW computations during the SOM's training phase. For comparison, we implement a similar pruning strategy for K-means, and call the latter K-TimeS. SOMTimeS and K-TimeS pruned 43% and 50% of the total DTW computations, respectively. Pruning effectiveness, accuracy, execution time and scalability are evaluated using 112 benchmark time series datasets from the UC Riverside classification archive, and show that for similar accuracy, a 1.8× speed-up on average for SOMTimeS and K-TimeS, respectively with that rates vary between 1× and 18× depending on the dataset. We also apply SOMTimeS to a healthcare study of patient-clinician serious illness conversations to demonstrate the algorithm's utility with complex, temporally sequenced natural language. Supplementary Information: The online version contains supplementary material available at 10.1007/s10618-023-00979-9.

Behind the Bait: Delving into PhishTank's hidden data.

Phishing constitutes a form of social engineering that aims to deceive individuals through email communication. Extensive prior research has underscored phishing as one of the most commonly employed attack vectors for infiltrating organizational networks. A prevalent method involves misleading the target by employing phishing URLs concealed through hyperlink strategies. PhishTank, a website employing the concept of crowd-sourcing, aggregates phishing URLs and subsequently verifies their authenticity. In the course of this study, we leveraged a Python script to extract data from the PhishTank website, amassing a comprehensive dataset comprising over 190,0000 phishing URLs. This dataset is a valuable resource that can be harnessed by both researchers and practitioners for enhancing phish- ing filters, fortifying firewalls, security education, and refining training and testing models, among other applications.