The role of the nucleus pulposus in intervertebral disc recovery: Towards improved specifications for nucleus replacement devices

Nucleus replacement devices (NRDs) have potential to treat degenerated or herniated intervertebral discs (IVDs). However, IVD height loss is a post-treatment complication. IVD height recovery involves the nucleus pulposus (NP), but the mechanism of this in response to physiological loads is not fully elucidated. This study aimed to characterise the non-linear recovery behaviour of the IVD in intact, post-nuclectomy, and post-NRD treatment states, under physiological loading. 36 bovine IVDs (12 intact, 12 post-nuclectomy, 12 post-treatment) underwent creep-recovery protocols simulating Sitting, Walking or Running, followed by 12 h of recovery. A rheological model decoupled the fluid-independent (elastic, fast) and fluid-dependent (slow) recovery phases. In post-nuclectomy and post-treatment groups, nuclectomy efficiency (ratio of NP removed to remaining NP) was quantified following post-test sectioning. Relative to intact, post-nuclectomy recovery significantly decreased in Sitting (-0.3 ± 0.4 mm, p < 0.05) and Walking (-0.6 ± 0.3 mm, p < 0.001) coupled with significant decreases to the slow response (p < 0.05). Post-nuclectomy, the fast and slow responses negatively correlated with nuclectomy efficiency (p < 0.05). In all protocols, the post-treatment group performed significantly worse in recovery (-0.5 ± 0.3 mm, p < 0.01) and the slow response (p < 0.05). Results suggest the NP mainly facilitates slow-phase recovery, linearly dependent on the amount of NP present. Failure of this NRD to recover is attributed to poor fluid imbibition. Additionally, unconfined NRD performance cannot be extrapolated to the in vitro response. This knowledge informs NRD design criteria to provide high osmotic pressure, and encourages testing standards to incorporate long-term recovery protocols.

The influence of geometry on intervertebral disc stiffness

Geometry plays an important role in intervertebral disc (IVD) mechanics. Previous computational studies have found a link between IVD geometry and stiffness. However, few experimental studies have investigated this link, possibly due to difficulties in non-destructively quantifying internal geometric features. Recent advances in ultra-high resolution MRI provides the opportunity to visualise IVD features in unprecedented detail. This study aimed to quantify 3D human IVD geometries using 9.4 T MRIs and to investigate correlations between geometric variations and IVD stiffness. Thirty human lumbar motion segments (fourteen non-degenerate and sixteen degenerate) were scanned using a 9.4 T MRI and geometric parameters were measured. A 1kN compressive load was applied to each motion segment and stiffness was calculated. Degeneration caused a reduction (p < 0.05) in IVD height, a decreased nucleus-annulus area ratio, and a 1.6 ± 3.0 mm inward collapse of the inner annulus. The IVD height, anteroposterior (AP) width, lateral width, cross-sectional area, nucleus-annulus boundary curvature, and nucleus-annulus area ratio had a significant (p < 0.05) influence on IVD stiffness. Linear relationships (p < 0.05, r > 0.47) were observed between these geometric features and IVD compressive stiffness and a multivariate regression model was generated to enable stiffness to be predicted from features observable on clinical imaging (stiffness, N/mm = 6062 - (61.2 × AP width, mm) - (169.2 × IVD height, mm)). This study advances our understanding of disc structure-function relationships and how these change with degeneration, which can be used to both generate and validate more realistic computational models.

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.

Brain Tumor Segmentation and Classification from Sensor-Based Portable Microwave Brain Imaging System Using Lightweight Deep Learning Models

Automated brain tumor segmentation from reconstructed microwave (RMW) brain images and image classification is essential for the investigation and monitoring of the progression of brain disease. The manual detection, classification, and segmentation of tumors are extremely time-consuming but crucial tasks due to the tumor's pattern. In this paper, we propose a new lightweight segmentation model called MicrowaveSegNet (MSegNet), which segments the brain tumor, and a new classifier called the BrainImageNet (BINet) model to classify the RMW images. Initially, three hundred (300) RMW brain image samples were obtained from our sensors-based microwave brain imaging (SMBI) system to create an original dataset. Then, image preprocessing and augmentation techniques were applied to make 6000 training images per fold for a 5-fold cross-validation. Later, the MSegNet and BINet were compared to state-of-the-art segmentation and classification models to verify their performance. The MSegNet has achieved an Intersection-over-Union (IoU) and Dice score of 86.92% and 93.10%, respectively, for tumor segmentation. The BINet has achieved an accuracy, precision, recall, F1-score, and specificity of 89.33%, 88.74%, 88.67%, 88.61%, and 94.33%, respectively, for three-class classification using raw RMW images, whereas it achieved 98.33%, 98.35%, 98.33%, 98.33%, and 99.17%, respectively, for segmented RMW images. Therefore, the proposed cascaded model can be used in the SMBI system.

A Lightweight Deep Learning Based Microwave Brain Image Network Model for Brain Tumor Classification Using Reconstructed Microwave Brain (RMB) Images

Computerized brain tumor classification from the reconstructed microwave brain (RMB) images is important for the examination and observation of the development of brain disease. In this paper, an eight-layered lightweight classifier model called microwave brain image network (MBINet) using a self-organized operational neural network (Self-ONN) is proposed to classify the reconstructed microwave brain (RMB) images into six classes. Initially, an experimental antenna sensor-based microwave brain imaging (SMBI) system was implemented, and RMB images were collected to create an image dataset. It consists of a total of 1320 images: 300 images for the non-tumor, 215 images for each single malignant and benign tumor, 200 images for each double benign tumor and double malignant tumor, and 190 images for the single benign and single malignant tumor classes. Then, image resizing and normalization techniques were used for image preprocessing. Thereafter, augmentation techniques were applied to the dataset to make 13,200 training images per fold for 5-fold cross-validation. The MBINet model was trained and achieved accuracy, precision, recall, F1-score, and specificity of 96.97%, 96.93%, 96.85%, 96.83%, and 97.95%, respectively, for six-class classification using original RMB images. The MBINet model was compared with four Self-ONNs, two vanilla CNNs, ResNet50, ResNet101, and DenseNet201 pre-trained models, and showed better classification outcomes (almost 98%). Therefore, the MBINet model can be used for reliably classifying the tumor(s) using RMB images in the SMBI system.

Machine learning and discriminant function analysis in the formulation of generic models for sex prediction using patella measurements

Sex prediction from bone measurements that display sexual dimorphism is one of the most important aspects of forensic anthropology. Some bones like the skull and pelvis display distinct morphological traits that are based on shape. These morphological traits which are sexually dimorphic across different population groups have been shown to provide an acceptably high degree of accuracy in the prediction of sex. A sample of 100 patella of Mixed Ancestry South Africans (MASA) was collected from the Dart collection. Six parameters: maximum height (maxh), maximum breadth (maxw), maximum thickness (maxt), the height of articular facet (haf), lateral articular facet breadth (lafb), and medial articular facet breath (mafb) were used in this study. Stepwise and direct discriminant function analyses were performed for measurements that exhibited significant differences between male and female mean measurements, and the "leave-one-out" approach was used for validation. Moreover, we have used eight classical machine learning techniques along with feature ranking techniques to identify the best feature combinations for sex prediction. A stacking machine learning technique was trained and validated to classify the sex of the subject. Here, we have used the top performing three ML classifiers as base learners and the predictions of these models were used as inputs to different machine learning classifiers as meta learners to make the final decision. The measurements of the patella of South Africans are sexually dimorphic and this observation is consistent with previous studies on the patella of different countries. The range of average accuracies obtained for pooled multivariate discriminant function equations is 81.9-84.2%, while the stacking ML technique provides 90.8% accuracy which compares well with those presented for previous studies in other parts of the world. In conclusion, the models proposed in this study from measurements of the patella of different population groups in South Africa are useful resent with reasonably high average accuracies.

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.

A Novel Machine Learning Approach for Severity Classification of Diabetic Foot Complications Using Thermogram Images

Diabetes mellitus (DM) is one of the most prevalent diseases in the world, and is correlated to a high index of mortality. One of its major complications is diabetic foot, leading to plantar ulcers, amputation, and death. Several studies report that a thermogram helps to detect changes in the plantar temperature of the foot, which may lead to a higher risk of ulceration. However, in diabetic patients, the distribution of plantar temperature does not follow a standard pattern, thereby making it difficult to quantify the changes. The abnormal temperature distribution in infrared (IR) foot thermogram images can be used for the early detection of diabetic foot before ulceration to avoid complications. There is no machine learning-based technique reported in the literature to classify these thermograms based on the severity of diabetic foot complications. This paper uses an available labeled diabetic thermogram dataset and uses the k-mean clustering technique to cluster the severity risk of diabetic foot ulcers using an unsupervised approach. Using the plantar foot temperature, the new clustered dataset is verified by expert medical doctors in terms of risk for the development of foot ulcers. The newly labeled dataset is then investigated in terms of robustness to be classified by any machine learning network. Classical machine learning algorithms with feature engineering and a convolutional neural network (CNN) with image-enhancement techniques are investigated to provide the best-performing network in classifying thermograms based on severity. It is found that the popular VGG 19 CNN model shows an accuracy, precision, sensitivity, F1-score, and specificity of 95.08%, 95.08%, 95.09%, 95.08%, and 97.2%, respectively, in the stratification of severity. A stacking classifier is proposed using extracted features of the thermogram, which is created using the trained gradient boost classifier, XGBoost classifier, and random forest classifier. This provides a comparable performance of 94.47%, 94.45%, 94.47%, 94.43%, and 93.25% for accuracy, precision, sensitivity, F1-score, and specificity, respectively.

Blind ECG Restoration by Operational Cycle-GANs

OBJECTIVE

ECG recordings often suffer from a set of artifacts with varying types, severities, and durations, and this makes an accurate diagnosis by machines or medical doctors difficult and unreliable. Numerous studies have proposed ECG denoising; however, they naturally fail to restore the actual ECG signal corrupted with such artifacts due to their simple and naive noise model. In this pilot study, we propose a novel approach for blind ECG restoration using cycle-consistent generative adversarial networks (Cycle-GANs) where the quality of the signal can be improved to a clinical level ECG regardless of the type and severity of the artifacts corrupting the signal.

METHODS

To further boost the restoration performance, we propose 1D operational Cycle-GANs with the generative neuron model.

RESULTS

The proposed approach has been evaluated extensively using one of the largest benchmark ECG datasets from the China Physiological Signal Challenge (CPSC-2020) with more than one million beats. Besides the quantitative and qualitative evaluations, a group of cardiologists performed medical evaluations to validate the quality and usability of the restored ECG, especially for an accurate arrhythmia diagnosis.

SIGNIFICANCE

As a pioneer study in ECG restoration, the corrupted ECG signals can be restored to clinical level quality.

CONCLUSION

By means of the proposed ECG restoration, the ECG diagnosis accuracy and performance can significantly improve.

Nutrition adequacy, gastrointestinal and hepatic function during extracorporeal membrane oxygenation in critically ill adults: a retrospective observational study

AIMS

To identify clinical and biochemical markers associated with nutrition adequacy and gastrointestinal and liver dysfunction in adults on extracorporeal membrane oxygenation (ECMO).

METHODS

A retrospective, observational, study was conducted at 2 centres in Australia. Adult patients who received ECMO from July 2011 to June 2015 were included. Mode of ECMO used, fluid balance, number of systemic inflammatory response syndrome (SIRS) criteria present, vasoactive-inotropic scores (VIS) and liver function tests (LFTs) were collected for the duration of ECMO until 7 days after ECMO cessation. Multiple regression models were used to determine if the collected variables were associated with nutrition adequacy. The mean LFTs during ECMO were also compared to mean LFTs post ECMO cessation.

RESULTS

During the first 5 days of ECMO commencement, mean nutrition adequacy was 10% higher in the veno-venous (VV) ECMO group than in the veno-arterial (VA) group (95% confidence interval [CI], 2% to 17%). For every 5,000 ml increase of fluid balance, an associated decrease in nutrition adequacy was observed (-8%, 95% CI, -15% to -2%). A doubling of bilirubin and VIS were associated with a mean reduction in nutrition adequacy of -5% (CI -8% to -2%) and -2% (CI, -3% to -1%), respectively.

CONCLUSIONS

In the first 5 days of ECMO commencement, higher nutrition adequacy was associated with the VV mode of ECMO and reduced nutrition adequacy with increased fluid balance, more vasopressor and inotropic support and raised bilirubin. Prospective investigation is required to confirm whether these associations have a causal relationship.

QCovSML: A reliable COVID-19 detection system using CBC biomarkers by a stacking machine learning model

The reverse transcription-polymerase chain reaction (RT-PCR) test is considered the current gold standard for the detection of coronavirus disease (COVID-19), although it suffers from some shortcomings, namely comparatively longer turnaround time, higher false-negative rates around 20-25%, and higher cost equipment. Therefore, finding an efficient, robust, accurate, and widely available, and accessible alternative to RT-PCR for COVID-19 diagnosis is a matter of utmost importance. This study proposes a complete blood count (CBC) biomarkers-based COVID-19 detection system using a stacking machine learning (SML) model, which could be a fast and less expensive alternative. This study used seven different publicly available datasets, where the largest one consisting of fifteen CBC biomarkers collected from 1624 patients (52% COVID-19 positive) admitted at San Raphael Hospital, Italy from February to May 2020 was used to train and validate the proposed model. White blood cell count, monocytes (%), lymphocyte (%), and age parameters collected from the patients during hospital admission were found to be important biomarkers for COVID-19 disease prediction using five different feature selection techniques. Our stacking model produced the best performance with weighted precision, sensitivity, specificity, overall accuracy, and F1-score of 91.44%, 91.44%, 91.44%, 91.45%, and 91.45%, respectively. The stacking machine learning model improved the performance in comparison to other state-of-the-art machine learning classifiers. Finally, a nomogram-based scoring system (QCovSML) was constructed using this stacking approach to predict the COVID-19 patients. The cut-off value of the QCovSML system for classifying COVID-19 and Non-COVID patients was 4.8. Six datasets from three different countries were used to externally validate the proposed model to evaluate its generalizability and robustness. The nomogram demonstrated good calibration and discrimination with the area under the curve (AUC) of 0.961 for the internal cohort and average AUC of 0.967 for all external validation cohort, respectively. The external validation shows an average weighted precision, sensitivity, F1-score, specificity, and overall accuracy of 92.02%, 95.59%, 93.73%, 90.54%, and 93.34%, respectively.

Increasing TB/HIV Case Notification through an Active Case-Finding Approach among Rural and Mining Communities in Northwest Tanzania

While Tanzania is among the high TB burden countries to reach the WHO's End TB 2030 milestones, 41% of the people estimated to have had TB in 2020 were not diagnosed and notified. As part of the response to close the TB treatment coverage gap, SHDEPHA+ Kahama conducted a TB REACH active case-finding (ACF) intervention among rural and mining communities in Northwest Tanzania to increase TB/HIV case notification from July 2017 to June 2020. The intervention successfully linked marginalized mining communities with integrated TB/HIV screening, diagnostic, and referral services, screening 144,707 people for TB of whom 24,200 were tested for TB and 4,478 were tested for HIV, diagnosing 1,499 people with TB and 1,273 people with HIV (including at least 154 people with TB/HIV coinfection). The intervention revealed that community-based ACF can ensure high rates of linkage to care among hard-to-reach populations for TB. Providing integrated TB and HIV screening and diagnostic services during evening hours (Moonlight Events) in and around mining settlements can yield a large number of people with undiagnosed TB and HIV. For TB, this is true not only amongst miners but also FSW living in the same communities, who appear to be at similar or equally high risk of infection. Local NGOs can help to bridge the TB treatment coverage gap and to improve TB and HIV health outcomes by linking these marginalized groups with public sector services. Capturing the number of referrals arriving at CTCs is an important next step to identify how well the integrated TB/HIV outreach services operate and how they can be strengthened.

Estimating the Relative Crystallinity of Biodegradable Polylactic Acid and Polyglycolide Polymer Composites by Machine Learning Methodologies

Biodegradable polymers have recently found significant applications in pharmaceutics processing and drug release/delivery. Composites based on poly (L-lactic acid) (PLLA) have been suggested to enhance the crystallization rate and relative crystallinity of pure PLLA polymers. Despite the large amount of experimental research that has taken place to date, the theoretical aspects of relative crystallinity have not been comprehensively investigated. Therefore, this research uses machine learning methods to estimate the relative crystallinity of biodegradable PLLA/PGA (polyglycolide) composites. Six different artificial intelligent classes were employed to estimate the relative crystallinity of PLLA/PGA polymer composites as a function of crystallization time, temperature, and PGA content. Cumulatively, 1510 machine learning topologies, including 200 multilayer perceptron neural networks, 200 cascade feedforward neural networks (CFFNN), 160 recurrent neural networks, 800 adaptive neuro-fuzzy inference systems, and 150 least-squares support vector regressions, were developed, and their prediction accuracy compared. The modeling results show that a single hidden layer CFFNN with 9 neurons is the most accurate method for estimating 431 experimentally measured datasets. This model predicts an experimental database with an average absolute percentage difference of 8.84%, root mean squared errors of 4.67%, and correlation coefficient (R²) of 0.999008. The modeling results and relevancy studies show that relative crystallinity increases based on the PGA content and crystallization time. Furthermore, the effect of temperature on relative crystallinity is too complex to be easily explained.

COVID-19 infection localization and severity grading from chest X-ray images

The immense spread of coronavirus disease 2019 (COVID-19) has left healthcare systems incapable to diagnose and test patients at the required rate. Given the effects of COVID-19 on pulmonary tissues, chest radiographic imaging has become a necessity for screening and monitoring the disease. Numerous studies have proposed Deep Learning approaches for the automatic diagnosis of COVID-19. Although these methods achieved outstanding performance in detection, they have used limited chest X-ray (CXR) repositories for evaluation, usually with a few hundred COVID-19 CXR images only. Thus, such data scarcity prevents reliable evaluation of Deep Learning models with the potential of overfitting. In addition, most studies showed no or limited capability in infection localization and severity grading of COVID-19 pneumonia. In this study, we address this urgent need by proposing a systematic and unified approach for lung segmentation and COVID-19 localization with infection quantification from CXR images. To accomplish this, we have constructed the largest benchmark dataset with 33,920 CXR images, including 11,956 COVID-19 samples, where the annotation of ground-truth lung segmentation masks is performed on CXRs by an elegant human-machine collaborative approach. An extensive set of experiments was performed using the state-of-the-art segmentation networks, U-Net, U-Net++, and Feature Pyramid Networks (FPN). The developed network, after an iterative process, reached a superior performance for lung region segmentation with Intersection over Union (IoU) of 96.11% and Dice Similarity Coefficient (DSC) of 97.99%. Furthermore, COVID-19 infections of various shapes and types were reliably localized with 83.05% IoU and 88.21% DSC. Finally, the proposed approach has achieved an outstanding COVID-19 detection performance with both sensitivity and specificity values above 99%.

A nomogram-based diabetic sensorimotor polyneuropathy severity prediction using Michigan neuropathy screening instrumentations

BACKGROUND

Diabetic Sensorimotor polyneuropathy (DSPN) is one of the major indelible complications in diabetic patients. Michigan neuropathy screening instrumentation (MNSI) is one of the most common screening techniques used for DSPN, however, it does not provide any direct severity grading system.

METHOD

For designing and modeling the DSPN severity grading systems for MNSI, 19 years of data from Epidemiology of Diabetes Interventions and Complications (EDIC) clinical trials were used. Different Machine learning-based feature ranking techniques were investigated to identify the important MNSI features associated with DSPN diagnosis. A multivariable logistic regression-based nomogram was generated and validated for DSPN severity grading using the best performing top-ranked MNSI features.

RESULTS

Top-10 ranked features from MNSI features: Appearance of Feet (R), Ankle Reflexes (R), Vibration perception (L), Vibration perception (R), Appearance of Feet (L), 10-gm filament (L), Ankle Reflexes (L), 10-gm filament (R), Bed Cover Touch, and Ulceration (R) were identified as important features for identifying DSPN by Multi-Tree Extreme Gradient Boost model. The nomogram-based prediction model exhibited an accuracy of 97.95% and 98.84% for the EDIC test set and an independent test set, respectively. A DSPN severity score technique was generated for MNSI from the DSPN severity prediction model. DSPN patients were stratified into four severity levels: absent, mild, moderate, and severe using the cut-off values of 17.6, 19.1, 20.5 for the DSPN probability less than 50%, 75%-90%, and above 90%, respectively.

CONCLUSIONS

The findings of this work provide a machine learning-based MNSI severity grading system which has the potential to be used as a secondary decision support system by health professionals in clinical applications and large clinical trials to identify high-risk DSPN patients.

A Comparative Study between Magnetic Resonance Imaging and Clinical FIGO Criteria in Different Stages of Carcinoma Cervix

The objective of this study was to determine whether Magnetic Resonance Imaging is a sensitive and specific alternative method to clinical FIGO criteria in the staging of cervical carcinoma. This prospective cross-sectional study was conducted in the Department of Radiology and Imaging, BSMMU, Dhaka during the period of September 2018 to August 2020. A total of 60 patients were selected purposively and all are staged clinically by EUA. Then all samples underwent MRI in Department of Radiology and Imaging, BSMMU. Images of uterine cervix, corpus, vagina and parametrium were taken with a prefixed standard protocol (TIWI axial, T2WI axial and sagittal, DWI axial & DCE) and reporting was done by Radiologist. Comparison was done between the MRI and clinical FIGO criteria of staging of cervical carcinoma. P value <0.05 was considered as significant. Sensitivity & specificity of the MRI was measured. Data were analyzed by using Statistical Package for Social Sciences (SPSS) software version 23.0 for Windows (SPSS Inc., Chicago, Illinois, USA). Out of 60 patients in this study the mean age was found 47.5±10.1 years with range from 22 to 60 years. Positive correlation (r=0.993; p=0.001) between histopathological size and MRI size of tumour. Positive correlation (r=0.950; p=0.001) between histopathological size and FIGO size of tumour. MRI findings more correlates with histopathology than clinically detected tumor size. The sensitivity, specificity, accuracy, positive and negative predictive values of MRI diagnosis evaluation for vaginal extension was 100.00%, 95.20%, 100.00%, 98.30% and 97.50% respectively. Sensitivity, specificity, accuracy, positive and negative predictive values of MRI diagnosis evaluation for parametrial invasion was 100.00%, all. In this study we observed that MRI staging was more likely to be concordant with pathological stage in comparison to the clinical stage. There was a concordance rate of 95.00% in MRI and 65.00% in clinical staging respectively. Out of 3 non-concordant cases in MRI, 2 were upstaged and 1 case was down staged in histopathology. FIGO staging concurred with histopathology in 39(65.00%) cases and differed in 21(35.00%) cases. Magnetic resonance imaging (MRI) is a sensitive and specific modality for accurate staging of cervical carcinoma in comparison with clinical FIGO criteria considering histopathology as gold standard.

A machine learning model for early detection of diabetic foot using thermogram images

Diabetes foot ulceration (DFU) and amputation are a cause of significant morbidity. The prevention of DFU may be achieved by the identification of patients at risk of DFU and the institution of preventative measures through education and offloading. Several studies have reported that thermogram images may help to detect an increase in plantar temperature prior to DFU. However, the distribution of plantar temperature may be heterogeneous, making it difficult to quantify and utilize to predict outcomes. We have compared a machine learning-based scoring technique with feature selection and optimization techniques and learning classifiers to several state-of-the-art Convolutional Neural Networks (CNNs) on foot thermogram images and propose a robust solution to identify the diabetic foot. A comparatively shallow CNN model, MobilenetV2 achieved an F1 score of ∼95% for a two-feet thermogram image-based classification and the AdaBoost Classifier used 10 features and achieved an F1 score of 97%. A comparison of the inference time for the best-performing networks confirmed that the proposed algorithm can be deployed as a smartphone application to allow the user to monitor the progression of the DFU in a home setting.

Mortality Prediction Utilizing Blood Biomarkers to Predict the Severity of COVID-19 Using Machine Learning Technique

Healthcare researchers have been working on mortality prediction for COVID-19 patients with differing levels of severity. A rapid and reliable clinical evaluation of disease intensity will assist in the allocation and prioritization of mortality mitigation resources. The novelty of the work proposed in this paper is an early prediction model of high mortality risk for both COVID-19 and non-COVID-19 patients, which provides state-of-the-art performance, in an external validation cohort from a different population. Retrospective research was performed on two separate hospital datasets from two different countries for model development and validation. In the first dataset, COVID-19 and non-COVID-19 patients were admitted to the emergency department in Boston (24 March 2020 to 30 April 2020), and in the second dataset, 375 COVID-19 patients were admitted to Tongji Hospital in China (10 January 2020 to 18 February 2020). The key parameters to predict the risk of mortality for COVID-19 and non-COVID-19 patients were identified and a nomogram-based scoring technique was developed using the top-ranked five parameters. Age, Lymphocyte count, D-dimer, CRP, and Creatinine (ALDCC), information acquired at hospital admission, were identified by the logistic regression model as the primary predictors of hospital death. For the development cohort, and internal and external validation cohorts, the area under the curves (AUCs) were 0.987, 0.999, and 0.992, respectively. All the patients are categorized into three groups using ALDCC score and death probability: Low (probability < 5%), Moderate (5% < probability < 50%), and High (probability > 50%) risk groups. The prognostic model, nomogram, and ALDCC score will be able to assist in the early identification of both COVID-19 and non-COVID-19 patients with high mortality risk, helping physicians to improve patient management.

Clinical Risk Index for Babies II Score as a Predictor of Neonatal Death among Preterm Low Birth Weight Babies

Clinical risk index for babies II (CRIB II) score is simple, validated and widely used risk-adjustment instrument for predicting mortality among preterm low birth weight babies. To assess the efficacy of CRIB II score as a tool to predict the risk for neonatal death among the preterm and LBW babies admitted in NICU of BSMMU, a tertiary care hospital in Bangladesh. This prospective observational study was conducted in Department of Neonatology in BSMMU from September 2016 to August 2017. Inborn preterm neonates with gestational age ≤34 weeks admitted were enrolled in the study. CRIB-II score was calculated for each infant within 1 hour of birth from birth weight, gestational age, sex, admission temperature and base excess. The primary outcome measured in the study was neonatal death or survival up to 28 days. Total 112 patients were finally analyzed in this study. Mean CRIB II score was significantly higher in the non-survivor group compared to the survivor group (p-value <0.0001). Receiver operating characteristic (ROC) curve analysis for mortality prediction by CRIB II score, gestational age and birth weight showed AUC 0.87 (95% CI 0.76-0.97), 0.76 (95% CI 0.63-0.88) and 0.79 (95% CI 0.66-0.92) respectively. ROC curve analysis also revealed that the most suitable cut-off points for predicting mortality were 5 for CRIB II score, 32 weeks for gestational age and 1250 gram for birth weight. Using these most suitable cut-off points, CRIB II score had the highest sensitivity and specificity followed by birth weight and gestational age. In this study, CRIB II score was found to be an effective tool for predicting neonatal death among preterm LBW babies. It predicted outcome more accurately than birth weight or gestational age alone.

Detection and Severity Classification of COVID-19 in CT Images Using Deep Learning

Detecting COVID-19 at an early stage is essential to reduce the mortality risk of the patients. In this study, a cascaded system is proposed to segment the lung, detect, localize, and quantify COVID-19 infections from computed tomography images. An extensive set of experiments were performed using Encoder-Decoder Convolutional Neural Networks (ED-CNNs), UNet, and Feature Pyramid Network (FPN), with different backbone (encoder) structures using the variants of DenseNet and ResNet. The conducted experiments for lung region segmentation showed a Dice Similarity Coefficient (DSC) of 97.19% and Intersection over Union (IoU) of 95.10% using U-Net model with the DenseNet 161 encoder. Furthermore, the proposed system achieved an elegant performance for COVID-19 infection segmentation with a DSC of 94.13% and IoU of 91.85% using the FPN with DenseNet201 encoder. The proposed system can reliably localize infections of various shapes and sizes, especially small infection regions, which are rarely considered in recent studies. Moreover, the proposed system achieved high COVID-19 detection performance with 99.64% sensitivity and 98.72% specificity. Finally, the system was able to discriminate between different severity levels of COVID-19 infection over a dataset of 1110 subjects with sensitivity values of 98.3%, 71.2%, 77.8%, and 100% for mild, moderate, severe, and critical, respectively.

Exploring the effect of image enhancement techniques on COVID-19 detection using chest X-ray images

Computer-aided diagnosis for the reliable and fast detection of coronavirus disease (COVID-19) has become a necessity to prevent the spread of the virus during the pandemic to ease the burden on the healthcare system. Chest X-ray (CXR) imaging has several advantages over other imaging and detection techniques. Numerous works have been reported on COVID-19 detection from a smaller set of original X-ray images. However, the effect of image enhancement and lung segmentation of a large dataset in COVID-19 detection was not reported in the literature. We have compiled a large X-ray dataset (COVQU) consisting of 18,479 CXR images with 8851 normal, 6012 non-COVID lung infections, and 3616 COVID-19 CXR images and their corresponding ground truth lung masks. To the best of our knowledge, this is the largest public COVID positive database and the lung masks. Five different image enhancement techniques: histogram equalization (HE), contrast limited adaptive histogram equalization (CLAHE), image complement, gamma correction, and balance contrast enhancement technique (BCET) were used to investigate the effect of image enhancement techniques on COVID-19 detection. A novel U-Net model was proposed and compared with the standard U-Net model for lung segmentation. Six different pre-trained Convolutional Neural Networks (CNNs) (ResNet18, ResNet50, ResNet101, InceptionV3, DenseNet201, and ChexNet) and a shallow CNN model were investigated on the plain and segmented lung CXR images. The novel U-Net model showed an accuracy, Intersection over Union (IoU), and Dice coefficient of 98.63%, 94.3%, and 96.94%, respectively for lung segmentation. The gamma correction-based enhancement technique outperforms other techniques in detecting COVID-19 from the plain and the segmented lung CXR images. Classification performance from plain CXR images is slightly better than the segmented lung CXR images; however, the reliability of network performance is significantly improved for the segmented lung images, which was observed using the visualization technique. The accuracy, precision, sensitivity, F1-score, and specificity were 95.11%, 94.55%, 94.56%, 94.53%, and 95.59% respectively for the segmented lung images. The proposed approach with very reliable and comparable performance will boost the fast and robust COVID-19 detection using chest X-ray images.

An Early Warning Tool for Predicting Mortality Risk of COVID-19 Patients Using Machine Learning

COVID-19 pandemic has created an extreme pressure on the global healthcare services. Fast, reliable, and early clinical assessment of the severity of the disease can help in allocating and prioritizing resources to reduce mortality. In order to study the important blood biomarkers for predicting disease mortality, a retrospective study was conducted on a dataset made public by Yan et al. in [1] of 375 COVID-19 positive patients admitted to Tongji Hospital (China) from January 10 to February 18, 2020. Demographic and clinical characteristics and patient outcomes were investigated using machine learning tools to identify key biomarkers to predict the mortality of individual patient. A nomogram was developed for predicting the mortality risk among COVID-19 patients. Lactate dehydrogenase, neutrophils (%), lymphocyte (%), high-sensitivity C-reactive protein, and age (LNLCA)-acquired at hospital admission-were identified as key predictors of death by multi-tree XGBoost model. The area under curve (AUC) of the nomogram for the derivation and validation cohort were 0.961 and 0.991, respectively. An integrated score (LNLCA) was calculated with the corresponding death probability. COVID-19 patients were divided into three subgroups: low-, moderate-, and high-risk groups using LNLCA cutoff values of 10.4 and 12.65 with the death probability less than 5%, 5-50%, and above 50%, respectively. The prognostic model, nomogram, and LNLCA score can help in early detection of high mortality risk of COVID-19 patients, which will help doctors to improve the management of patient stratification.

Clinical Course and Cardiac Complications of Hospitalized COVID-19 Patients

Purpose

We describe the hospitalization course, cardiac complications and echocardiographic findings in a subset of acutely ill hospitalized patients with COVID-19.

Methods

Patients admitted to a large academic hospital in Ontario, Canada from March-June 2020 with COVID-19 and who had an echocardiogram within 4-weeks of their diagnosis were included in this study. Their demographics, hospitalization details and echocardiographic findings were analyzed.

Results

76 patients are included in our study, 83% of whom required ICU. Mean age was 58.9 years (+/-15.7 years). Cardiovascular comorbidities were common: diabetes (35.5%), hypertension (50%), CKD (11.8%), prior CAD (13.2%) or stroke (11.8%). Median length of admission was 25.5 days (IQR 22days). Overall, in-hospital mortality was high at 35.5%, with increased mortality in the ICU vs. non-ICU group (32.9% vs. 15.4%). A large number of patients required invasive support: intubation (77.6%), Extracorporeal life support (23.7%), or renal replacement therapy (19.7%). Cardiac complications included new AF (13.2%), hemodynamically significant VT (3.9%), moderate or more pericardial effusion (2.6%) and acute stroke (9.2%). Echocardiographic analysis demonstrated that 7.9% of patients developed moderate or more LV dysfunction on visual assessment. RV dysfunction was more common (27.6%) with 11.8% being visually classified as moderate or greater in severity. High sensitivity troponin was elevated in 59.2% of patients and was statistically higher in patients experiencing cardiac complications (Chi-Square 0.005). Although not achieving significance, there was a trend towards elevated troponin and development of moderate or greater LV/RV dysfunction (Chi-square 0.30).

Conclusion

In acute patients hospitalized with COVID-19, there was a high prevalence of cardiovascular co-morbidities. Troponin elevations was common and associated with a significantly increased risk of cardiovascular events and a trend towards moderate or greater ventricular dysfunction.

Development and Validation of an Early Scoring System for Prediction of Disease Severity in COVID-19 Using Complete Blood Count Parameters

The coronavirus disease 2019 (COVID-19) after outbreaking in Wuhan increasingly spread throughout the world. Fast, reliable, and easily accessible clinical assessment of the severity of the disease can help in allocating and prioritizing resources to reduce mortality. The objective of the study was to develop and validate an early scoring tool to stratify the risk of death using readily available complete blood count (CBC) biomarkers. A retrospective study was conducted on twenty-three CBC blood biomarkers for predicting disease mortality for 375 COVID-19 patients admitted to Tongji Hospital, China from January 10 to February 18, 2020. Machine learning based key biomarkers among the CBC parameters as the mortality predictors were identified. A multivariate logistic regression-based nomogram and a scoring system was developed to categorize the patients in three risk groups (low, moderate, and high) for predicting the mortality risk among COVID-19 patients. Lymphocyte count, neutrophils count, age, white blood cell count, monocytes (%), platelet count, red blood cell distribution width parameters collected at hospital admission were selected as important biomarkers for death prediction using random forest feature selection technique. A CBC score was devised for calculating the death probability of the patients and was used to categorize the patients into three sub-risk groups: low (<=5%), moderate (>5% and <=50%), and high (>50%), respectively. The area under the curve (AUC) of the model for the development and internal validation cohort were 0.961 and 0.88, respectively. The proposed model was further validated with an external cohort of 103 patients of Dhaka Medical College, Bangladesh, which exhibits in an AUC of 0.963. The proposed CBC parameter-based prognostic model and the associated web-application, can help the medical doctors to improve the management by early prediction of mortality risk of the COVID-19 patients in the low-resource countries.

An Intelligent and Low-Cost Eye-Tracking System for Motorized Wheelchair Control

In the 34 developed and 156 developing countries, there are ~132 million disabled people who need a wheelchair, constituting 1.86% of the world population. Moreover, there are millions of people suffering from diseases related to motor disabilities, which cause inability to produce controlled movement in any of the limbs or even head. This paper proposes a system to aid people with motor disabilities by restoring their ability to move effectively and effortlessly without having to rely on others utilizing an eye-controlled electric wheelchair. The system input is images of the user's eye that are processed to estimate the gaze direction and the wheelchair was moved accordingly. To accomplish such a feat, four user-specific methods were developed, implemented, and tested; all of which were based on a benchmark database created by the authors. The first three techniques were automatic, employ correlation, and were variants of template matching, whereas the last one uses convolutional neural networks (CNNs). Different metrics to quantitatively evaluate the performance of each algorithm in terms of accuracy and latency were computed and overall comparison is presented. CNN exhibited the best performance (i.e., 99.3% classification accuracy), and thus it was the model of choice for the gaze estimator, which commands the wheelchair motion. The system was evaluated carefully on eight subjects achieving 99% accuracy in changing illumination conditions outdoor and indoor. This required modifying a motorized wheelchair to adapt it to the predictions output by the gaze estimation algorithm. The wheelchair control can bypass any decision made by the gaze estimator and immediately halt its motion with the help of an array of proximity sensors, if the measured distance goes below a well-defined safety margin. This work not only empowers any immobile wheelchair user, but also provides low-cost tools for the organization assisting wheelchair users.

Efficacy of Intra-peritoneal Tramadol Instillation for Postoperative Pain Management after Laparoscopic Cholecystectomy

Gall stone disease is one of the most common conditions encountered in general surgical practices in adult population. The gold standard treatment for symptomatic gall stone disease is laparoscopic cholecystectomy. It results in less post-operative pain as compared to open cholecystectomy but post-operative pain may be mild, moderate or even severe in some patients. This Randomized control trail was conducted to In-patient department of Surgery, Mymensingh Medical College & Hospital (MMCH), Mymensingh, Bangladesh from April 2018 to September 2018. It was undertaken to evaluate the analgesic effect of intra-peritoneal tramadol instillation in patients undergoing laparoscopic cholecystectomy. Total 70 patients with symptomatic gallstone disease undergoing laparoscopic cholecystectomy were randomized equally in two groups. Then patients were selected in according to the inclusion and exclusion criteria. In first group (Group A), patients were received intra-peritoneal tramadol 100mg (diluted in 20.0ml distilled water). Sprayed 10.0ml diluted tramadol into the sub diaphragmatic area, 5.0ml into the area of gall bladder bed and 5.0ml into the space between the liver and kidney under direct vision just before removal of trocars. In second group (Group B) the conventional operative procedure was followed. Postoperatively, patient was extubated and shifted to recovery room. Data recorded and analyzed, such as post-operative pain score at 1, 4, 8, and 24 hour; cumulative 1, 8 and 24 hour analgesic consumption. In addition that postoperative hospital period monitoring of heart rate, blood pressure, respiratory rate, temperature at 0, 4, 8, 24 hours was also analyzed. Intensity of pain was assessed by Visual Analogue Scale (VAS) scoring system. Patients showed a VAS ≥3 or patients who requested for analgesia was administrated a supplemental dose of analgesic. In the present study the mean pain scores in Group A were found to be low at1hourpost-operative was 0.60±0.56 and there was a gradual increase in score in respect of time interval with peak of 2.07±0.91 at 24 hours. Whereas, in Group B the mean pain scores immediate post-operative period were at its peak was, 2.50±0.82 which decreased to 1.30±0.84 at 1 hour and further there was rise at 4 hours (2.10±0.71) and 24 hours (2.33±0.0.71). But at any point of time the mean VAS remained significantly low (p<0.050) in patients with Group A compared to Group B except at 1st 24 hours (p=0.210). Intra-peritoneal instillation of tramadol for postoperative pain control in laparoscopic cholecystectomy has beneficial effect in terms of postoperative pain relief following laparoscopic cholecystectomy.

Knowledge, Attitude and Practice of Bangladeshi Women towards Breast Cancer: A Cross Sectional Study

In Bangladesh incidence rate of breast cancer was about 22.5 per 100000 females. Breast cancer has been reported as the highest prevalence rate (19.3 per 100,000) among Bangladeshi women between 15 and 44 years of age. For this prevailing situation a cross-sectional study was designed to assess the knowledge, attitude and practices of community-dwelling women in Bangladesh towards breast cancer at Bangabandhu Sheikh Mujib Medical University (BSMMU), Dhaka, Bangladesh from July 2013 to June 2014. All female participants attending at outpatient department of BSMMU having age more than 20 years and education at least JSC, purposively selected until the sample size achieved 500. Only applying simple cost free method like self breast examination (SBE) and clinical breast examination (CBE) one can asses her breast. Thereby awareness develops regarding her breast so any mass newly appear can be assessed by the lady herself. Early diagnosis of the breast cancer will reduce the burden of treatment cost, mortality & morbidity. Research and development strategy of the project is to enhance the awareness of the community people about breast cancer prevention. Mean age of the study population was 36.16 years. Regarding education nearly 30% (n=150) of them studied up to Junior School, 16% (n=80) respondents completed masters and above remaining in between. Regarding occupation, almost 60% (n=300) were house wife, 32% (n=160) were service holder and only 8% (n=40) of them were students. Knowledge about common female cancer 60% (n=300) were aware about the cervical cancer, 24% (n=120) mentioned breast cancer, 4% (n=20) mentioned ovarian cancer, and 12% (n=60) don't know anything regarding common women cancer. Knowledge about early symptoms of breast cancer, majority of the respondents 66% (n=330) were aware that mass in the breast is the main symptom, 2% (n=10) mentioned pain in breast, 32% (n=160) mentioned that they don't know anything regarding the early symptoms. About the cause of breast cancer 60% (n=300) mentioned that, they don't know anything regarding the cause of breast cancer, 36% (n=180) were aware that non lactation is a cause of breast cancer. About 4% (n=20) of the study population mentioned others, like due to some ones bad did cancer occur as punishment. Knowledge about risk factor of breast cancer, 65% (n=325) have no idea about the risk of breast cancer, 32% (n=160) mentioned few risk factors which have relation with breast cancer and 3% (n=15) did not mention anything. Regarding diagnosis of cancer breast 72% (n=360) mentioned they don't know anything, 16% (n=80) by doing ultra sonogram of breast, 6% (n=30) mentioned about Mammography and 6% (n=30) MRI & others. Regarding screening for prevention of breast cancer 60% (n=300) mentioned that they don't know anything regarding screening. Thirty percent (n=150) were aware that there is screening method but they are not aware specifically regarding this method and they also not aware that breast cancer is a preventable disease. 10% (n=50) were fully aware about screening method like CBE & SBE. About the cause of not seeking medical advice for prevention of Breast cancer, majority of the respondents 40% (n=200) mentioned expenditure problems, 32% (n=160) they don't have any knowledge about this type of medical advice, 8% (n=40) mentioned communication problems and 20% (n=100) others. Regarding Practice of CBE & SBE 68% (n=340) never practice CBE & SBE, 30% (n=150) occasionally practiced CBE & SBE. Only 2% (n=10) mentioned that they were regularly practicing CBE & SBE.

Measurement of Typhi Vi antibodies can be used to assess adaptive immunity in patients with immunodeficiency

Vaccine‐specific antibody responses are essential in the diagnosis of antibody deficiencies. Responses to Pneumovax II are used to assess the response to polysaccharide antigens, but interpretation may be complicated. Typhim Vi^®, a polysaccharide vaccine for Salmonella typhoid fever, may be an additional option for assessing humoral responses in patients suspected of having an immunodeficiency. Here we report a UK multi‐centre study describing the analytical and clinical performance of a Typhi Vi immunoglobulin (Ig)G enzyme‐linked immunosorbent assay (ELISA) calibrated to an affinity‐purified Typhi Vi IgG preparation. Intra‐ and interassay imprecision was low and the assay was linear, between 7·4 and 574 U/ml (slope = 0·99–1·00; R² > 0·99); 71% of blood donors had undetectable Typhi Vi IgG antibody concentrations. Of those with antibody concentrations  > 7·4 U/ml, the concentration range was 7·7–167 U/ml. In antibody‐deficient patients receiving antibody replacement therapy the median Typhi Vi IgG antibody concentrations were  < 25 U/ml. In vaccinated normal healthy volunteers, the median concentration post‐vaccination was 107 U/ml (range 31–542 U/ml). Eight of eight patients (100%) had post‐vaccination concentration increases of at least threefold and six of eight (75%) of at least 10‐fold. In an antibody‐deficient population (n = 23), only 30% had post‐vaccination concentration increases of at least threefold and 10% of at least 10‐fold. The antibody responses to Pneumovax II and Typhim Vi^® correlated. We conclude that IgG responses to Typhim Vi^® vaccination can be measured using the VaccZyme Salmonella typhi Vi IgG ELISA, and that measurement of these antibodies maybe a useful additional test to accompany Pneumovax II responses for the assessment of antibody deficiencies.

Incidence of elephant endotheliotropic herpesvirus in Asian elephants in India

Elephant endotheliotropic herpesviruses (EEHVs) are the cause of acute hemorrhagic disease in endangered Asian and African elephants. In the present study, we report the incidence of EEHV infection and associated mortality in the captive elephant of Assam, India. Our result showed the gross morphology and histopathological changes of EEHV infection in the elephant. Moreover, the phylogenetic analysis of the polymerase, helicase, and GPCR genes from the infected tissue samples suggested the presence of EEHV1A virus.

Literature review and case report: Current concepts for concomitant intra and extracapsular fractures of neck of femur in elderly patients

Though the incidence of concomitant ipsilateral intracapsular and extracapsular fracture neck of femur is still a rare presentation in day to day fracture hip admissions. Cases of simultaneous ipsilateral intra- and extra-capsular neck of femur fractures are forestalled with problems relating to diagnosing this injury as well as debate regarding optimal methods of fixation versus arthroplasty. We did a literature review to assess frequency of such fracture incidence, highlight methods of treatment applied, current practice for management as well as case report presentation.

Outcome of Endoscopic Sinus Surgery in the Treatment of Chronic Rhinosinusitis

This prospective study was conducted to compare the outcome of endoscopic sinus surgery (ESS) using SNOT-20 score chart (subjective) and Lund & Kennedy scoring chart (objective) and carried out in the Department of Otolaryngology & Head-Neck Surgery, Bangabandhu Sheikh Mujib Medical University (BSMMU), Dhaka, Dhaka Medical College Hospital (DMCH) & Shaheed Suhrawardy Medical College Hospital (ShSMCH) from July 2010 to March 2012. Total 73 admitted cases were selected purposively for ESS, male 53(72.60%) and female 20(27.40%). Among the study participants 10(13.7%) had chronic rhinosinusitis with bilateral polyposis and 26(35.62%) had chronic rhinosinusitis with unilateral polyposis and 12(16.44%) had bilateral chronic rhinosinusitis without polyposis and 25(34.25%) had unilateral chronic rhinosinusitis without polyposis. Surgical procedures done among the patients were Uncinectomy (infundibulectomy), Middle Meatal Antrostomy; Anterior Ethmoidectomy; Sphenoidotomy, Associated septoplasty and no significant per or post operative complications were noted. In Chronic rhinosinusitis (CRS) with polyposis pre operative SNOT-20 mean and SD 1.322±0.341 and post ESS snot-20 mean and SD 0.3472±0.0755, CRS without polyposis pre operative SNOT-20 mean and SD 0.9297±0.86 and post ESS SNOT-20 mean and SD 1986±0.0558. In CRS with polyposis pre operative Lund & Kennedy score of endoscopic assessment, mean and SD 5.333±2.255 and post ESS mean and SD 1.31±1.009. In CRS without polyposis pre op Lund & Kennedy score mean and SD 3.108±1.074 and post ESS mean and SD 0.76±0.641.Post ESS SNOT-20 in CRS with Polyposis, 't' test result was 27.58 which was significant (p<0.001) and in CRS without Polyposis was 21.622 which was significant (p<0.001); Lund & Kennedy Score of post ESS in CRS with Polyposis 't' test result was 7.763 which was significant (p<0.001), CRS without Polyposis was 7.177 which was significant (p<0.001).This implies that outcome of ESS in treatment of CRS with or without polyposis had statistically significant role. Symptomatic relief and quality of life improvement after ESS was compared by improvement in post operative scores of SNOT-20 & Lund-Kennedy score of endoscopic assessment. Post operative lower values were considered to be better improvement status. The results of the study suggests that ESS performed in Chronic Rhinosinusitis without Polyposis cases, relief of symptoms and quality of life improved was better than Chronic Rhinosinusitis with Polyposis cases postoperatively as compared by SNOT-20 and Lund & Kennedy score of endoscopic assessment.

Carcinoma Tongue--Clinicopathological Presentation

This prospective study was done to observe the diversity of clinical presentation of carcinoma of tongue and to study the pathological variety of carcinoma of tongue and was conducted in the Department of General Surgery and Otolaryngology and Head Neck Surgery in Bangabandhu Sheikh Mujib Medical University, Dhaka Medical College Hospital on 50 patients from January 2011 to July 2013. In this series highest number of patients were middle aged (36%). Male female ratio was 2:1. Average socioeconomic conditions of the patient were poor (68%). Betel nut and leaves chewing (88%) and smoking (56%) habits were commonly practiced for more than 10 years among the patients. Depending on site of involvement, variation in presenting symptoms has been observed. Oral tongue carcinoma mostly was presented with tongue lesion, pain and dysphagia where as the carcinoma of base of tongue commonly was presented with dysphagia, lump in neck. Lateral border of tongue (60%) was seen commonly involved. Ulcerative lesion (56%) predominantly was found in tongue lesion. Eighty percent (80%) of cases had no palpable Lymph node. Only few patients were found with Lymph node metastasis and most of them had carcinoma in base of the tongue (75%). Most of the carcinoma was well differentiated Squamous cell carcinoma. Carcinoma of tongue in our study commonly found in middle aged male patients. Variation of symptoms has depended on anatomical site involved. Most of the carcinoma was well differentiated Squamous cell carcinoma. Carcinoma other than squamous cell was not found.

Study of Commonest Variety of Sinonasal Malignancy and Its Sex Wise Distribution

This study was done to find the commonest variety of sinonasal malignancy and its association with sex.This cross-sectional study was conducted in the Department of Otolaryngology - Head & Neck Surgery Department, Dhaka Medical College & Hospital and in the Department of Otolaryngology - Head & Neck Surgery Department, Bangabandhu Sheikh Mujib Medical University between January 2009 and December 2009. A total of 146 cases of sinonasal malignancy were consecutively included in the study. The diagnosis was confirmed by histopathology. The mean age was 47.8 years (range: 22-75 years). Over three-quarters (77%) of the patients were male with male to female ratio being 3:1. Nearly one-third (30.8%) of the patients was farmer and over one-third (36.3%) was illiterate. The right sinonasal region was involved in 48.6% cases, left sinonasal region in 39% and both sinonasal region in 12.4% cases. Histopathological diagnosis of sinonasal malignancy revealed that squamous cell carcinoma accounted for 82.9% of sinonasal malignancies, 9.6% adenocarcinoma and the rest were olfactory neuroblastoma, adenoid cystic carcinoma and mucoepidermoid carcinoma. About 96.6% of the tumours involved nasal cavity, 97.9% maxillary sinuses, 17.8% frontal sinuses, 48.6% ethmoidal sinuses and 13% sphenoid sinuses. Over 80% of patients were smoker. Exposure to wood dust was found in 26% of cases. Lather tanning in 4.8% of cases and welding in 4.1% of cases. T staging shows that nearly half (48.6%) of the patients lesion was T2, 29.5% T3, 19.9% T4 and 2.1% T1. None of the patients exhibited lymph node involvement or distant metastasis. Males tend to develop squamous cell carcinoma significantly more than the females with risk of acquiring squamous cell carcinoma being nearly 3(1.1-7.1) times higher in male than that in female (p=0.022). The study concludes that the most common histopathological variety of sinonasal malignancy is squamous cell carcinoma and males are prone to develop this malignancy more frequently than the females.