Deep Learning Framework for Liver Segmentation from T1-Weighted MRI Images.

The human liver exhibits variable characteristics and anatomical information, which is often ambiguous in radiological images. Machine learning can be of great assistance in automatically segmenting the liver in radiological images, which can be further processed for computer-aided diagnosis. Magnetic resonance imaging (MRI) is preferred by clinicians for liver pathology diagnosis over volumetric abdominal computerized tomography (CT) scans, due to their superior representation of soft tissues. The convenience of Hounsfield unit (HoU) based preprocessing in CT scans is not available in MRI, making automatic segmentation challenging for MR images. This study investigates multiple state-of-the-art segmentation networks for liver segmentation from volumetric MRI images. Here, T1-weighted (in-phase) scans are investigated using expert-labeled liver masks from a public dataset of 20 patients (647 MR slices) from the Combined Healthy Abdominal Organ Segmentation grant challenge (CHAOS). The reason for using T1-weighted images is that it demonstrates brighter fat content, thus providing enhanced images for the segmentation task. Twenty-four different state-of-the-art segmentation networks with varying depths of dense, residual, and inception encoder and decoder backbones were investigated for the task. A novel cascaded network is proposed to segment axial liver slices. The proposed framework outperforms existing approaches reported in the literature for the liver segmentation task (on the same test set) with a dice similarity coefficient (DSC) score and intersect over union (IoU) of 95.15% and 92.10%, respectively.

Solar-driven Dish Stirling System for sustainable power generation in Bangladesh: A case study in Cox's Bazar.

In recent years, the power sector of Bangladesh has seen a major development in terms of generation capacity. But as before, it is heavily dependent on fossil fuels overlooking the potential of renewable energy resources. The scope for grid-connected renewable energy systems has not been explored too far and in terms of solar thermal energy and concentrating solar power (CSP), it is even less. This study focuses on assessing the techno-economic feasibility of solar-driven Dish Stirling system for large-scale grid-connected power generation in Bangladesh. Detailed modeling and optimization of a 100 MW Dish Stirling power plant have been carried out in Cox's Bazar, Bangladesh, a location suitable for solar energy harnessing due to favorable climatic conditions. The modeling parameters and weather data have been collected from relevant literature, various solar data providers, and specific plant parameters have been optimized for the Bangladeshi climatic condition. Simulation of the modeled plant carried out by the System Advisor Model (SAM) shows that, it can supply 129.856 GWh electricity annually operating at an overall efficiency of 24.91% which is much higher than the values reported in similar literature for the South-Asian regions. The levelized cost of electricity (LCOE) has been determined to be 10.18 cents/kWh, which is highly competitive and promising. The insights obtained from this study can be a perfect starting point for the policymakers and concerned authorities of Bangladesh to further explore the viability of this technology for renewable and sustainable power.

Deep learning based automated quantification of urethral plate characteristics using the plate objective scoring tool (POST).

INTRODUCTION: The plate objective scoring tool (POST) was recently introduced as a reproducible and precise approach to quantifying urethral plate (UP) characteristics and guide to selecting particular surgical techniques. However, defining the landmarks mandatory for the POST score from captured images can potentially leads to variability. Although artificial intelligence (AI) is yet to be wholly accepted and explored in hypospadiology, it has certainly brought new possibilities to light. OBJECTIVES: To explore the capacity of deep learning algorithm to further streamline and optimize UP characteristics appraisal on 2D images using the POST, aiming to increase the objectivity and reproducibility of UP appraisal in hypospadias repair. METHODS: The five key POST landmarks were marked by specialists in a 691-image dataset of prepubertal boys undergoing primary hypospadias repair. This dataset was then used to develop and validate a deep learning-based landmark detection model. The proposed framework begins with glans localization and detection, where the input image is cropped using the predicted bounding box. Next, a deep convolutional neural network (CNN) architecture is used to predict the coordinates of the five POST landmarks. These predicted landmarks are then used to assess UP characteristics in distal hypospadias. RESULTS: The proposed model accurately localized the glans area, with a mean average precision (mAP) of 99.5% and an overall sensitivity of 99.1%. A normalized mean error (NME) of 0.07152 was achieved in predicting the coordinates of the landmarks, with a mean squared error (MSE) of 0.001 and a 2.5% failure rate at a threshold of 0.2 NME. DISCUSSION: Our results support the possibility of further standardizing UP assessment from captured hypospadias images, and the use of machine learning algorithms and image recognition shows that these novel artificial intelligence technologies are useful for scoring hypospadias. External validation can provide valuable information on the generalizability and reliability of deep learning algorithms, which can aid in assessments, decision-making and predictions for surgical outcomes. CONCLUSIONS: This deep learning application shows robustness and high precision in using POST to appraise UP characteristics. Further assessment using international multi-centre image-based databases is ongoing.

Heavy metals contamination in shrimp and crab from southwest regions in Bangladesh: Possible health risk assessment.

Shrimp and Crab, important sources of protein, are currently being adversely affected by the rising industrialization, which has led to higher levels of heavy metals. The goal of this study was to evaluate the health risks of contamination associated with nine heavy metals (Cd, Pb, Cu, Cr, Zn, Ni, As, Al, and Fe) in two species of shrimp (Macrobrachium rosenbergii and Metapenaeus monoceros) and one species of crab (Scylla serrata) that were collected from the Khulna, Satkhira, and Bagerhat areas of Bangladesh. Inductively coupled plasma-optical emission spectrometry (ICP-OES) was used for the study. The results showed that all metal concentrations in shrimp and crab samples were below the recommended level, indicating that ingestion of these foods would not pose any substantial health risks to individuals. To evaluate the non-carcinogenic health risks, the target hazard quotient (THQ) and hazard index (HI) were determined, and the target cancer risk (TR) was utilized to evaluate the carcinogenic health risks. From the health point of view, this study showed that crustaceans obtained from the study sites were non - toxic (THQ and HI < 1), and long-term, continuous intake is unlikely to pose any significant health hazards (TR = 10-7-10-5) from either carcinogenic or non-carcinogenic effects.

A Deep Learning-Based Automatic Segmentation and 3D Visualization Technique for Intracranial Hemorrhage Detection Using Computed Tomography Images.

Intracranial hemorrhage (ICH) occurs when blood leaks inside the skull as a result of trauma to the skull or due to medical conditions. ICH usually requires immediate medical and surgical attention because the disease has a high mortality rate, long-term disability potential, and other potentially life-threatening complications. There are a wide range of severity levels, sizes, and morphologies of ICHs, making accurate identification challenging. Hemorrhages that are small are more likely to be missed, particularly in healthcare systems that experience high turnover when it comes to computed tomography (CT) investigations. Although many neuroimaging modalities have been developed, CT remains the standard for diagnosing trauma and hemorrhage (including non-traumatic ones). A CT scan-based diagnosis can provide time-critical, urgent ICH surgery that could save lives because CT scan-based diagnoses can be obtained rapidly. The purpose of this study is to develop a machine-learning algorithm that can detect intracranial hemorrhage based on plain CT images taken from 75 patients. CT images were preprocessed using brain windowing, skull-stripping, and image inversion techniques. Hemorrhage segmentation was performed using multiple pre-trained models on preprocessed CT images. A U-Net model with DenseNet201 pre-trained encoder outperformed other U-Net, U-Net++, and FPN (Feature Pyramid Network) models with the highest Dice similarity coefficient (DSC) and intersection over union (IoU) scores, which were previously used in many other medical applications. We presented a three-dimensional brain model highlighting hemorrhages from ground truth and predicted masks. The volume of hemorrhage was measured volumetrically to determine the size of the hematoma. This study is essential in examining ICH for diagnostic purposes in clinical practice by comparing the predicted 3D model with the ground truth.

Multidrug-resistant Escherichia coli isolated from patients and surrounding hospital environments in Bangladesh: A molecular approach for the determination of pathogenicity and resistance.

Extended spectrum ß-lactamase producing Escherichia coli (ESBL E. coli) is a primary concern for hospital and community healthcare settings, often linked to an increased incidence of nosocomial infections. This study investigated the characteristics of ESBL E. coli isolated from hospital environments and clinical samples. In total, 117 ESBL E. coli isolates were obtained. The isolates were subjected to molecular analysis for the presence of resistance and virulence genes, antibiotic susceptibility testing, quantitative adherence assay, ERIC-PCR for phylogenetic analysis and whole genome sequencing of four highly drug resistant isolates. Out of the 117 isolates, 68.4% were positive for blaCTX-M, 39.3% for blaTEM, 30.8% for blaNDM-1, 13.7% for blaOXA and 1.7% for blaSHV gene. Upon screening for diarrheagenic genes, no isolates were found to harbour any of the tested genes. In the case of extraintestinal pathogenic E. coli (ExPEC) virulence factors, 7.6%, 11%, 5.9%, 4.3% and 21.2% of isolates harbored the focG, kpsMII, sfaS, afa and iutA genes, respectively. At a temperature of 25°C, 14.5% of isolates exhibited strong biofilm formation with 21.4% and 28.2% exhibiting moderate and weak biofilm formation respectively, whereas 35.9% were non-biofilm formers. On the other hand at 37°C, 2.6% of isolates showed strong biofilm formation with 3.4% and 31.6% showing moderate and weak biofilm formation respectively, whereas, 62.4% were non-biofilm formers. Regarding antibiotic susceptibility testing, all isolates were found to be multidrug-resistant (MDR), with 30 isolates being highly drug resistant. ERIC-PCR resulted in 12 clusters, with cluster E-10 containing the maximum number of isolates. Hierarchical clustering and correlation analysis revealed associations between environmental and clinical isolates, indicating likely transmission and dissemination from the hospital environment to the patients. The whole genome sequencing of four highly drug resistant ExPEC isolates showed the presence of various antimicrobial resistance genes, virulence factors and mobile genetic elements, with isolates harbouring the plasmid incompatibility group IncF (FII, FIB, FIA). The sequenced isolates were identified as human pathogens with a 93.3% average score. This study suggests that ESBL producing E. coli are prevalent in the healthcare settings of Bangladesh, acting as a potential reservoir for AMR bacteria. This information may have a profound effect on treatment, and improvements in public healthcare policies are a necessity to combat the increased incidences of hospital-acquired infections in the country.

BIO-CXRNET: a robust multimodal stacking machine learning technique for mortality risk prediction of COVID-19 patients using chest X-ray images and clinical data.

Nowadays, quick, and accurate diagnosis of COVID-19 is a pressing need. This study presents a multimodal system to meet this need. The presented system employs a machine learning module that learns the required knowledge from the datasets collected from 930 COVID-19 patients hospitalized in Italy during the first wave of COVID-19 (March-June 2020). The dataset consists of twenty-five biomarkers from electronic health record and Chest X-ray (CXR) images. It is found that the system can diagnose low- or high-risk patients with an accuracy, sensitivity, and F1-score of 89.03%, 90.44%, and 89.03%, respectively. The system exhibits 6% higher accuracy than the systems that employ either CXR images or biomarker data. In addition, the system can calculate the mortality risk of high-risk patients using multivariate logistic regression-based nomogram scoring technique. Interested physicians can use the presented system to predict the early mortality risks of COVID-19 patients using the web-link: Covid-severity-grading-AI. In this case, a physician needs to input the following information: CXR image file, Lactate Dehydrogenase (LDH), Oxygen Saturation (O2%), White Blood Cells Count, C-reactive protein, and Age. This way, this study contributes to the management of COVID-19 patients by predicting early mortality risk. Supplementary Information: The online version contains supplementary material available at 10.1007/s00521-023-08606-w.

Optimization of the factors affecting BT-2 black tea fermentation by observing their combined effects on the quality parameters of made tea using Response Surface Methodology (RSM).

This research work aimed to optimize the fermentation time, temperature, and relative humidity of the black tea produced from Bangladesh Tea 2 (BT-2) variety by observing their quality parameters. Total theaflavin (TF), thearubigin (TR), the ratio of TF: TR, total liquor color (TLC), high polymeric substances (HPS), and total phenolic content (TPC) were evaluated for quality measurements of BT-2 black tea. Response Surface Methodology (RSM) with Box-Behnken design (BBD) was applied to optimize fermentation time, temperature, and relative humidity as well as evaluate the effects of optimized conditions on the quality of made tea. The results obtained from the response surface optimization affirmed that under the optimum conditions of time (80.14 min), temperature (28.76 °C), and relative humidity (92.30%), the model showed the value of TF (0.69%), TR (5.57%), HPS (8.61%), TLC (3.05%), and TPC (7.95 GAE g/100g tea). Moreover, the optimized model found that the TF:TR value was 1:9.13, which is close to black tea's optimum quality. The values observed in experiments were highly congruent with the predicted value by the regression model. The Analysis of Variance (ANOVA) test revealed that the model was significant for TF, TR, HPS, TLC, TPC, and TF:TR values of prepared BT-2 black tea at different levels (p < 0.001 to p < 0.01). The composite desirability of the model was 0.93, which suggests that the developed model could be utilized effectively to maintain the quality parameters of BT-2 black tea during fermentation.

Prognostic Model of ICU Admission Risk in Patients with COVID-19 Infection Using Machine Learning.

With the onset of the COVID-19 pandemic, the number of critically sick patients in intensive care units (ICUs) has increased worldwide, putting a burden on ICUs. Early prediction of ICU requirement is crucial for efficient resource management and distribution. Early-prediction scoring systems for critically ill patients using mathematical models are available, but are not generalized for COVID-19 and Non-COVID patients. This study aims to develop a generalized and reliable prognostic model for ICU admission for both COVID-19 and non-COVID-19 patients using best feature combination from the patient data at admission. A retrospective cohort study was conducted on a dataset collected from the pulmonology department of Moscow City State Hospital between 20 April 2020 and 5 June 2020. The dataset contains ten clinical features for 231 patients, of whom 100 patients were transferred to ICU and 131 were stable (non-ICU) patients. There were 156 COVID positive patients and 75 non-COVID patients. Different feature selection techniques were investigated, and a stacking machine learning model was proposed and compared with eight different classification algorithms to detect risk of need for ICU admission for both COVID-19 and non-COVID patients combined and COVID patients alone. C-reactive protein (CRP), chest computed tomography (CT), lung tissue affected (%), age, admission to hospital, and fibrinogen parameters at hospital admission were found to be important features for ICU-requirement risk prediction. The best performance was produced by the stacking approach, with weighted precision, sensitivity, F1-score, specificity, and overall accuracy of 84.45%, 84.48%, 83.64%, 84.47%, and 84.48%, respectively, for both types of patients, and 85.34%, 85.35%, 85.11%, 85.34%, and 85.35%, respectively, for COVID-19 patients only. The proposed work can help doctors to improve management through early prediction of the risk of need for ICU admission of patients during the COVID-19 pandemic, as the model can be used for both types of patients.

QUCoughScope: An Intelligent Application to Detect COVID-19 Patients Using Cough and Breath Sounds.

Problem-Since the outbreak of the COVID-19 pandemic, mass testing has become essential to reduce the spread of the virus. Several recent studies suggest that a significant number of COVID-19 patients display no physical symptoms whatsoever. Therefore, it is unlikely that these patients will undergo COVID-19 testing, which increases their chances of unintentionally spreading the virus. Currently, the primary diagnostic tool to detect COVID-19 is a reverse-transcription polymerase chain reaction (RT-PCR) test from the respiratory specimens of the suspected patient, which is invasive and a resource-dependent technique. It is evident from recent researches that asymptomatic COVID-19 patients cough and breathe in a different way than healthy people. Aim-This paper aims to use a novel machine learning approach to detect COVID-19 (symptomatic and asymptomatic) patients from the convenience of their homes so that they do not overburden the healthcare system and also do not spread the virus unknowingly by continuously monitoring themselves. Method-A Cambridge University research group shared such a dataset of cough and breath sound samples from 582 healthy and 141 COVID-19 patients. Among the COVID-19 patients, 87 were asymptomatic while 54 were symptomatic (had a dry or wet cough). In addition to the available dataset, the proposed work deployed a real-time deep learning-based backend server with a web application to crowdsource cough and breath datasets and also screen for COVID-19 infection from the comfort of the user's home. The collected dataset includes data from 245 healthy individuals and 78 asymptomatic and 18 symptomatic COVID-19 patients. Users can simply use the application from any web browser without installation and enter their symptoms, record audio clips of their cough and breath sounds, and upload the data anonymously. Two different pipelines for screening were developed based on the symptoms reported by the users: asymptomatic and symptomatic. An innovative and novel stacking CNN model was developed using three base learners from of eight state-of-the-art deep learning CNN algorithms. The stacking CNN model is based on a logistic regression classifier meta-learner that uses the spectrograms generated from the breath and cough sounds of symptomatic and asymptomatic patients as input using the combined (Cambridge and collected) dataset. Results-The stacking model outperformed the other eight CNN networks with the best classification performance for binary classification using cough sound spectrogram images. The accuracy, sensitivity, and specificity for symptomatic and asymptomatic patients were 96.5%, 96.42%, and 95.47% and 98.85%, 97.01%, and 99.6%, respectively. For breath sound spectrogram images, the metrics for binary classification of symptomatic and asymptomatic patients were 91.03%, 88.9%, and 91.5% and 80.01%, 72.04%, and 82.67%, respectively. Conclusion-The web-application QUCoughScope records coughing and breathing sounds, converts them to a spectrogram, and applies the best-performing machine learning model to classify the COVID-19 patients and healthy subjects. The result is then reported back to the test user in the application interface. Therefore, this novel system can be used by patients in their premises as a pre-screening method to aid COVID-19 diagnosis by prioritizing the patients for RT-PCR testing and thereby reducing the risk of spreading of the disease.

ESBL Producing Escherichia coli in Faecal Sludge Treatment Plants: An Invisible Threat to Public Health in Rohingya Camps, Cox's Bazar, Bangladesh.

Introduction: Human faecal sludge contains diverse harmful microorganisms, making it hazardous to the environment and public health if it is discharged untreated. Faecal sludge is one of the major sources of E. coli that can produce extended-spectrum ß-lactamases (ESBLs). Objective: This study aimed to investigate the prevalence and molecular characterization of ESBL-producing E. coli in faecal sludge samples collected from faecal sludge treatment plants (FSTPs) in Rohingya camps, Bangladesh. Methods: ESBL producing E. coli were screened by cultural as well as molecular methods and further characterized for their major ESBL genes, plasmid profiles, pathotypes, antibiotic resistance patterns, conjugation ability, and genetic similarity. Results: Of 296 isolates, 180 were phenotypically positive for ESBL. All the isolates, except one, contained at least one ESBL gene that was tested (blaCTX-M-1, blaCTX-M-2, blaCTX-M-8, blaCTX-M-9, blaCTX-M-15, blaCTX-M-25, blaTEM , and blaSHV ). From plasmid profiling, it was observed that plasmids of 1-211 MDa were found in 84% (151/180) of the isolates. Besides, 13% (24/180) of the isolates possessed diarrhoeagenic virulence genes. From the remaining isolates, around 51% (79/156) harbored at least one virulence gene that is associated with the extraintestinal pathogenicity of E. coli. Moreover, 4% (3/156) of the isolates were detected to be potential extraintestinal pathogenic E. coli (ExPEC) strains. Additionally, all the diarrhoeagenic and ExPEC strains showed resistance to three or more antibiotic groups which indicate their multidrug-resistant potential. ERIC-PCR differentiated these pathogenic isolates into seven clusters. In addition to this, 16 out of 35 tested isolates transferred plasmids of 32-112 MDa to E. coli J53 recipient strain. Conclusion: The present study implies that the faecal sludge samples examined here could be a potential origin for spreading MDR pathogenic ESBL-producing E. coli. The exposure of Rohingya individuals, living in overcrowded camps, to these organisms poses a severe threat to their health.