BDWaste: A comprehensive image dataset of digestible and indigestible waste in Bangladesh.

The "BDWaste" dataset contains two significant categories of waste, namely digestible and indigestible, in Bangladesh. Each category represents 10 distinct species of waste. The digestible categories are sugarcane husk, fish ash, potato peel, paper, mango peel, rice, shell of malta, lemon peel, banana peel, and egg shell. On the other hand, the indigestible species are polythene, cans, plastic, glass, wire, gloves, empty medicine packets, chip packets, bottles, and masks. The research uploaded the primarily collected dataset on Mendeley, and the dataset contains a total of 2497 raw images, of which 1234 were digestible and 1263 belonged to indigestible species. Each species is stored in a fixed file based on its name and categories. Also, each species contains an indoor (with a visible surface) and an outdoor (with a surface that can be seen generally) image. The dataset is free from any blurry, dark, noisy, or invisible images. The research also performed waste classification with pre-trained convolutional neural network models such as MobileNetV2 and InceptionV3. The research found the highest accuracy of 96.70% in the indigestible waste classification and 99.70% in the digestible waste classification. The researchers presume that this data can be used in the future in different types of research, such as sustainable development, sustainable environments, agricultural development, recycling processes, and other computer vision-based applications.

Status of lipid control in Bangladeshi subjects with type 2 diabetes mellitus on lipid-lowering drugs: a multicenter, facility-based, cross-sectional study.

BACKGROUND: Achievement of lipid targets is crucial in patients with type 2 diabetes mellitus (T2DM) to mitigate the risk of cardiovascular diseases (CVD). Data on lipid-control status among patients with T2DM in Bangladesh are scarce. This study was conducted to determine the lipid-control status among patients with T2DM who were on lipid-lowering drugs in the country. METHODS: This cross-sectional study was conducted in the diabetes outpatient departments of several tertiary hospitals in Bangladesh from January 2022 to December 2022. Adults of both sexes diagnosed with T2DM for at least one year and were on the lipid-lowering drug(s) for a minimum of 3 months were included in the study by consecutive sampling. Patients' data were collected by face-to-face interviews, and blood samples were collected for fasting lipid profile. The lipid target was set at < 200 mg/dL for total cholesterol (TC), < 150 mg/dL for triglyceride (TG), < 100 mg/dL for low-density lipoprotein cholesterol (LDL-C), > 40 mg/dL for high-density lipoprotein cholesterol (HDL-C), and < 160 mg/dL for non-HDL cholesterol (non-HDL-C). RESULT: Three thousand sixty patients (age 44.7 ± 13.3 years, female 57%) with T2DM were evaluated. Overall, almost 81% of the study subjects achieved the LDL-C target. Besides, TC, TG, HDL-C, and non-HDL-C targets were achieved by 40.8, 21.6, 66.3, and 44.1% of patients, respectively. However, all the lipid parameters were under control in only 8.8% of patients. Almost 77.6% of the patients with ischemic heart disease, 81.5% of patients with stroke, and 65% of patients with CKD had LDL levels < 70 mg/dL. Only 10.03% achieved the HbA1c target of < 7%. 7.4% of patients achieved both HbA1c < 7% and LDL < 100 mg/dL and 5% achieved both HbA1c < 7% and LDL < 70 mg/dL. Advanced age (aOR 0.97, 95% CI 0.96, 0.98, p < 0.001), longstanding T2DM (aOR 0.53, 95% CI 0.39, 0.72, p < 0.001), and non-statin therapy (aOR 0.25, 95% CI 0.16, 0.37, p < 0.001) were negatively associated with lipid control (LDL < 100 mg/dL) while using oral hypoglycemic drugs or insulin (aOR 2.01, 95% CI 1.45, 2.77, p < 0.001) and having cardiovascular comorbidity (aOR 3.92, 95% CI 3.00, 5.12, p < 0.001) were positively associated with lipid control. CONCLUSION: Though most patients with T2DM achieved their target LDL level, the prevalence of both glycemic and overall lipid control was low in our study despite lipid-lowering therapy.

FP-CNN: Fuzzy pooling-based convolutional neural network for lung ultrasound image classification with explainable AI.

The COVID-19 pandemic wreaks havoc on healthcare systems all across the world. In pandemic scenarios like COVID-19, the applicability of diagnostic modalities is crucial in medical diagnosis, where non-invasive ultrasound imaging has the potential to be a useful biomarker. This research develops a computer-assisted intelligent methodology for ultrasound lung image classification by utilizing a fuzzy pooling-based convolutional neural network FP-CNN with underlying evidence of particular decisions. The fuzzy-pooling method finds better representative features for ultrasound image classification. The FPCNN model categorizes ultrasound images into one of three classes: covid, disease-free (normal), and pneumonia. Explanations of diagnostic decisions are crucial to ensure the fairness of an intelligent system. This research has used Shapley Additive Explanation (SHAP) to explain the prediction of the FP-CNN models. The prediction of the black-box model is illustrated using the SHAP explanation of the intermediate layers of the black-box model. To determine the most effective model, we have tested different state-of-the-art convolutional neural network architectures with various training strategies, including fine-tuned models, single-layer fuzzy pooling models, and fuzzy pooling at all pooling layers. Among different architectures, the Xception model with all pooling layers having fuzzy pooling achieves the best classification results of 97.2% accuracy. We hope our proposed method will be helpful for the clinical diagnosis of covid-19 from lung ultrasound (LUS) images.

Comparison of fasting and random lipid profiles among subjects with type 2 diabetes mellitus: an outpatient-based cross-sectional study in Bangladesh.

BACKGROUND: Despite the wide acceptability of fasting lipid profiles in practice, emerging evidence suggests that random lipid profiles might be a convenient alternative for lipid measurement. The objective of the present study was to compare the fasting and random lipid profile among subjects with type 2 diabetes mellitus (T2DM). METHODS: The present cross-sectional study included 1543 subjects with T2DM visiting several endocrinology outpatient clinics throughout Bangladesh from January to December 2021. The fasting lipid profile was measured in the morning following 8-10 h of overnight fasting, and the random lipid profile was measured at any time of the day, irrespective of the last meal. The values of fasting and random lipids were compared using the Wilcoxon signed-rank test and Spearman rank correlation coefficients. RESULTS: In this study, a good level of correlation was observed between fasting and random lipid levels [r = 0.793, p < 0.001 for triglyceride (TG); r = 0.873, p < 0.001 for low-density lipoprotein cholesterol (LDL-C); r = 0.609, p < 0.001 for high-density lipoprotein cholesterol (HDL-C); and r = 0.780, p < 0.001 for total cholesterol (TC)]. In addition, TG and TC levels increased by 14% and 0.51%, respectively, in the random state compared to the fasting state (p- <0.05), while LDL-C levels decreased by 0.71% (p-value 0.42). No change was noticed in the HDL-C level. The difference between fasting and random lipid profiles was similar irrespective of patients' age, sex, BMI, glucose-lowering drug(s), and lipid-lowering therapy. CONCLUSIONS: Random lipid profile correlates significantly with fasting lipid profile with little difference. Hence, it might be a reliable alternative for fasting lipid profile in patients with T2DM.

Comparison of simplicity, convenience, safety, and cost-effectiveness between use of insulin pen devices and disposable plastic syringes by patients with type 2 diabetes mellitus: a cross-sectional study from Bangladesh.

INTRODUCTION: Insulin pen devices and disposable plastic insulin syringes are two common tools for insulin administration. This study aims to compare the simplicity, convenience, safety, and cost-effectiveness of insulin pens versus syringe devices in patients with type 2 diabetes mellitus (T2DM). METHODS: A cross-sectional study was conducted at 14 diabetes clinics throughout Bangladesh from November 2021 to April 2022 among adults with T2DM injecting insulin by pen devices or disposable insulin syringes at least once a day for at least one year by purposive sampling. The simplicity, convenience, and safety of insulin devices were assessed using a structured questionnaire, and the study subjects were scored based on their answers; higher scores indicated a poorer response. Total scores for simplicity, convenience, and safety were obtained by adding the scores for relevant components. Their average monthly medical expense and cost of insulin therapy were recorded. The median values of the total scores and monthly expenses were compared between pen devices and disposable syringe users. RESULTS: 737 subjects were evaluated; 406 were pen users, and 331 were vial syringe users. The pen users had lower median scores for simplicity [6.0 (5.0-8.0) vs. 7.0 (5.0-9.0), p = 0.002], convenience [4.0 (3.0-6.0) vs. 5.0 (4.0-6.0), p < 0.001], and safety [7.0 (6.0-8.0) vs. 7.0 (6.0-9.0), p = 0.008] than vial syringe users. Pen devices were more expensive than vial syringes in terms of average medical expense per month [BDT 5000 (3500-7000) vs. 3000 (2000-5000), p < 0.001], the total cost of insulin therapy per month [BDT 2000 (1500-3000) vs. 1200 (800-1700), p < 0.001] and cost per unit of insulin used [BDT 2.08 (1.39-2.78) vs. 0.96 (0.64-1.39), p < 0.001]. Non-significant differences in favor of pens were observed in HbA1c levels [8.7 (7.8-10) vs. 8.9 (7.9-10)%, p = 0.607] and proportions of subjects having HbA1c < 7% (6.9 vs. 6.3%, p = 0.991). CONCLUSION: Insulin pens are simpler, more convenient, and safe but more expensive than vial syringes. Glycemic control is comparable between pen and syringe users. Long-term follow-up studies are needed to determine the clinical and economic impacts of such benefits of insulin pens.

IoT-Based Medical Image Monitoring System Using HL7 in a Hospital Database.

In recent years, the healthcare system, along with the technology that surrounds it, has become a sector in much need of development. It has already improved in a wide range of areas thanks to significant and continuous research into the practical implications of biomedical and telemedicine studies. To ensure the continuing technological improvement of hospitals, physicians now also must properly maintain and manage large volumes of patient data. Transferring large amounts of data such as images to IoT servers based on machine-to-machine communication is difficult and time consuming over MQTT and MLLP protocols, and since IoT brokers only handle a limited number of bytes of data, such protocols can only transfer patient information and other text data. It is more difficult to handle the monitoring of ultrasound, MRI, or CT image data via IoT. To address this problem, this study proposes a model in which the system displays images as well as patient data on an IoT dashboard. A Raspberry Pi processes HL7 messages received from medical devices like an ultrasound machine (ULSM) and extracts only the image data for transfer to an FTP server. The Raspberry Pi 3 (RSPI3) forwards the patient information along with a unique encrypted image data link from the FTP server to the IoT server. We have implemented an authentic and NS3-based simulation environment to monitor real-time ultrasound image data on the IoT server and have analyzed the system performance, which has been impressive. This method will enrich the telemedicine facilities both for patients and physicians by assisting with overall monitoring of data.

Identification of Leading Compounds from Euphorbia neriifolia (Dudsor) Extracts as a Potential Inhibitor of SARS-CoV-2 ACE2-RBDS1 Receptor Complex: An Insight from Molecular Docking ADMET Profiling and MD-simulation Studies.

Coronavirus disease-19 (COVID-19) are deadly and infectious disease that impacts individuals in a variety of ways. Scientists have stepped up their attempts to find an antiviral drug that targets the spike protein (S) of Angiotensin converting enzyme 2 (ACE2) (receptor protein) as a viable therapeutic target for coronavirus. The most recent study examines the potential antagonistic effects of 17 phytochemicals present in the plant extraction of Euphorbia neriifolia on the anti-SARS-CoV-2 ACE2 protein. Computational techniques like molecular docking, absorption, distribution, metabolism, excretion, and toxicity (ADMET) investigations, and molecular dynamics (MD) simulation analysis were used to investigate the actions of these phytochemicals. The results of molecular docking studies showed that the control ligand (2-acetamido-2-deoxy-ß-D-glucopyranose) had a binding potential of -6.2 kcal/mol, but the binding potentials of delphin, ß-amyrin, and tulipanin are greater at -10.4, 10.0, and -9.6 kcal/mol. To verify their drug-likeness, the discovered hits were put via Lipinski filters and ADMET analysis. According to MD simulations of the complex run for 100 numbers, delphin binds to the SARS-CoV-2 ACE2 receptor's active region with good stability. In root-mean-square deviation (RMSD) and root mean square fluctuation (RMSF) calculations, delphinan, ß-amyrin, and tulipanin showed reduced variance with the receptor binding domain subunit 1(RBD S1) ACE2 protein complex. The solvent accessible surface area (SASA), radius of gyration (Rg), molecular surface area (MolSA), and polar surface area (PSA) validation results for these three compounds were likewise encouraging. The convenient binding energies across the 100 numbers binding period were discovered by using molecular mechanics of generalized born and surface (MM/GBSA) to estimate the ligand-binding free energies to the protein receptor. All things considered, the information points to a greater likelihood of chemicals found in Euphorbia neriifolia binding to the SARS-CoV-2 ACE2 active site. To determine these lead compounds' anti-SARS-CoV-2 potential, in vitro and in vivo studies should be conducted. How to cite this article: Islam MN, Pramanik MEA, Hossain MA, et al. Identification of Leading Compounds from Euphorbia Neriifolia (Dudsor) Extracts as a Potential Inhibitor of SARS-CoV-2 ACE2-RBDS1 Receptor Complex: An Insight from Molecular Docking ADMET Profiling and MD-simulation Studies. Euroasian J Hepato-Gastroenterol 2023;13(2):89-107.

Particle Swarm Optimized Fuzzy CNN With Quantitative Feature Fusion for Ultrasound Image Quality Identification.

Inherently ultrasound images are susceptible to noise which leads to several image quality issues. Hence, rating of an image's quality is crucial since diagnosing diseases requires accurate and high-quality ultrasound images. This research presents an intelligent architecture to rate the quality of ultrasound images. The formulated image quality recognition approach fuses feature from a Fuzzy convolutional neural network (fuzzy CNN) and a handcrafted feature extraction method. We implement the fuzzy layer in between the last max pooling and the fully connected layer of the multiple state-of-the-art CNN models to handle the uncertainty of information. Moreover, the fuzzy CNN uses Particle swarm optimization (PSO) as an optimizer. In addition, a novel Quantitative feature extraction machine (QFEM) extracts hand-crafted features from ultrasound images. Next, the proposed method uses different classifiers to predict the image quality. The classifiers categories ultrasound images into four types (normal, noisy, blurry, and distorted) instead of binary classification into good or poor-quality images. The results of the proposed method exhibit a significant performance in accuracy (99.62%), precision (99.62%), recall (99.61%), and f1-score (99.61%). This method will assist a physician in automatically rating informative ultrasound images with steadfast operation in real-time medical diagnosis.

Euphorbia neriifolia Leaf Juice on Mild and Moderate COVID-19 Patients: Implications in OMICRON Era.

Coronavirus disease-2019 (COVID-19) has shattered the public health delivery system of most of the countries of the world. COVID-19 displays variable clinical presentations. The severe COVID-19 represents a fulminant pathological condition and most of the patients run a downhill course if extensive medical measures are not adopted. The major challenges about COVID-19 are related to develop strategies to manage huge populations of mild and moderate cases of COVID-19 with two realistic purposes: (1) early negativity of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus and (2) arrest of progression of moderate COVID-19 patients from developing severe complications. Although several medications have been repurposed for these purposes, none of these have passed the test of time in global perspective. Thus, there remains a pressing need to develop new and novel innovative management strategies for these patients as new variants of SARS-CoV-2 have been destroying the normal public health delivery system of different countries from time to time. The study presented here has checked the safety and efficacy of a herbal medication, leaves of Euphorbia neriifolia Linn (E. neriifolia), in mild and moderate COVID-19 patients. Sixty patients (30 mild COVID-19 and 30 moderate COVID-19) were enrolled in the study. Fifteen mild COVID-19 patients received standard of care (SOC) management, and the remaining 15 patients received SOC plus E. neriifolia. The moderate COVID-19 patients similarly received either SOC (N = 15) or SOC plus E. neriifolia (N = 15). Although there were marked diversity regarding biochemical parameters of these patients at entry, the moderate COVID-19 patients receiving E. neriifolia showed decrease in C-reactive protein and D-dimer and increase in oxygen saturation 7 days after trial commencement. However, these improvements were not detected in moderate COVID-19 patients receiving SOC. Hospital staying was significantly lower in both mild and moderate COVID-19 patients receiving SOC plus E. neriifolia than those receiving only SOC. Taken together, it may be proposed that usage of E. neriifolia may have beneficial effects regarding management for COVID-19 patients, especially for those in developing and resource-constrained countries, although a conclusive statement may not be given due to small sample size. This herbal medication is also pertinent in the context of emergence of OMICRON variant of COVID-19 as the overload of SARS-CoV-2-infecetd patients may be addressed considerably by this medication without hospitalization, if proper communication between patients and physicians can be ensured. How to cite this article: Pramanik MEA, Miah MMZ, Ahmed I, et al. Euphorbia neriifolia Leaf Juice on Mild and Moderate COVID-19 Patients: Implications in OMICRON Era. Euroasian J Hepato-Gastroenterol 2022;12(1):10-18.

Prevalence and predictors of diabetes distress among adults with type 2 diabetes mellitus: a facility-based cross-sectional study of Bangladesh.

INTRODUCTION: Diabetes distress (DD) is common and has considerable impacts on diabetes management. Unfortunately, DD is less discussed and frequently underestimated. This study evaluated the prevalence and predictors of DD in adults with type 2 diabetes mellitus (T2DM). METHODS: A cross-sectional study was conducted at several specialized endocrinology outpatient clinics in Bangladesh from July 2019 to June 2020; 259 adults with T2DM participated. Participants' DD and depression were measured using the 17-item Diabetes Distress Scale (DDS-17) and 9-item Patient Health Questionnaire (PHQ-9), respectively. DDS-17 scores ≥2 and PHQ-9 scores ≥10 were the cutoffs for DD and significant depression, respectively. RESULTS: The mean (±SD) age of the participants was 50.36 (±12.7) years, with the majority (54.8%) being male; their median (IQR) duration of diabetes was 6 (3-11) years. Among the study participants, 52.5% had DD (29.7% moderate and 22.8% high DD). The prevalence of emotional burden, physician-related distress, regimen-related distress, and interpersonal distress was 68.7, 28.6, 66, and 37.7%, respectively. Depression was present in 40.5%; 28.6% of the participants had DD and depression. The total DDS-17 score was positively correlated with the PHQ-9 score (r = 0.325, p < 0.001). Rural residence (OR 1.94), presence of any diabetic complication (OR 3.125), insulin use (OR 2.687), and presence of major depression (OR 4.753) were positive predictors of DD. In contrast, age ≥ 40 years at diabetes diagnosis (OR 0.047) and diabetes duration of > 10 years (OR 0.240) were negative predictors of DD (p < 0.05 in all instances). CONCLUSIONS: The prevalence of DD in our setting is notably high; DD and depression frequently overlap. Screening for diabetes distress may be considered, especially in high-risk patients.

Covid-19 detection in chest X-ray through random forest classifier using a hybridization of deep CNN and DWT optimized features.

Chest X-ray image contains sufficient information that finds wide-spread applications in diverse disease diagnosis and decision making to assist the medical experts. This paper has proposed an intelligent approach to detect Covid-19 from the chest X-ray image using the hybridization of deep convolutional neural network (CNN) and discrete wavelet transform (DWT) features. At first, the X-ray image is enhanced and segmented through preprocessing tasks, and then deep CNN and DWT features are extracted. The optimum features are extracted from these hybridized features through minimum redundancy and maximum relevance (mRMR) along with recursive feature elimination (RFE). Finally, the random forest-based bagging approach is used for doing the detection task. An extensive experiment is performed, and the results confirm that our approach gives satisfactory performance compare to the existing methods with an overall accuracy of more than 98.5%.

Diagnosis of corona diseases from associated genes and X-ray images using machine learning algorithms and deep CNN.

Novel Coronavirus with its highly transmittable characteristics is rapidly spreading, endangering millions of human lives and the global economy. To expel the chain of alteration and subversive expansion, early and effective diagnosis of infected patients is immensely important. Unfortunately, there is a lack of testing equipment in many countries as compared with the number of infected patients. It would be desirable to have a swift diagnosis with identification of COVID-19 from disease genes or from CT or X-Ray images. COVID-19 causes flus, cough, pneumonia, and lung infection in patients, wherein massive alveolar damage and progressive respiratory failure can lead to death. This paper proposes two different detection methods - the first is a Gene-based screening method to detect Corona diseases (Middle East respiratory syndrome-related coronavirus, Severe acute respiratory syndrome coronavirus 2, and Human coronavirus HKU1) and differentiate it from Pneumonia. This novel approach to healthcare utilizes disease genes to build functional semantic similarity among genes. Different machine learning algorithms - eXtreme Gradient Boosting, Naïve Bayes, Regularized Random Forest, Random Forest Rule-Based Model, Random Ferns, C5.0 and Multi-Layer Perceptron, are trained and tested on the semantic similarities to classify Corona and Pneumonia diseases. The best performing models are then ensembled, yielding an accuracy of nearly 93%. The second diagnosis technique proposed herein is an automated COVID-19 diagnostic method which uses chest X-ray images to classify Normal versus COVID-19 and Pneumonia versus COVID-19 images using the deep-CNN technique, achieving 99.87% and 99.48% test accuracy. Thus, this research can be an assistance for providing better treatment against COVID-19.

Ensemble of CheXNet and VGG-19 Feature Extractor with Random Forest Classifier for Pediatric Pneumonia Detection.

Pneumonia, an acute respiratory infection, causes serious breathing hindrance by damaging lung/s. Recovery of pneumonia patients depends on the early diagnosis of the disease and proper treatment. This paper proposes an ensemble method-based pneumonia diagnosis from Chest X-ray images. The deep Convolutional Neural Networks (CNNs)-CheXNet and VGG-19 are trained and used to extract features from given X-ray images. These features are then ensembled for classification. To overcome data irregularity problem, Random Under Sampler (RUS), Random Over Sampler (ROS) and Synthetic Minority Oversampling Technique (SMOTE) are applied on the ensembled feature vector. The ensembled feature vector is then classified using several Machine Learning (ML) classification techniques (Random Forest, Adaptive Boosting, K-Nearest Neighbors). Among these methods, Random Forest got better performance metrics than others on the available standard dataset. Comparison with existing methods shows that the proposed method attains improved classification accuracy, AUC values and outperforms all other models providing 98.93% accurate prediction. The model also exhibits potential generalization capacity when tested on different dataset. Outcomes of this study can be great to use for pneumonia diagnosis from chest X-ray images.

Divergences in Clinical, Anthropometric, Metabolic, and Hormonal Parameters among Different Phenotypes of Polycystic Ovary Syndrome Presenting at Endocrinology Outpatient Departments: A Multicenter Study from Bangladesh.

BACKGROUND: Polycystic ovary syndrome (PCOS) is a heterogeneous androgen-excess disorder. Data comparing the PCOS phenotypes in Bangladesh are scarce. OBJECTIVES: The objective of this study was to find out the distribution of Rotterdam classified PCOS phenotypes and to compare the phenotypes concerning clinical, anthropometric, metabolic, and hormonal parameters. SUBJECTS AND METHODS: In this cross-sectional study, 370 PCOS cases in the age group of 20-45 years diagnosed by the Rotterdam consensus criteria were recruited from the endocrinology outpatient departments of several tertiary hospitals of Bangladesh. Metabolic syndrome (MetS) was diagnosed using the International Diabetes Federation criteria. RESULTS: The prevalence of phenotypes A, B, C, and D were 59.2%, 14.1%, 11.9%, and 14.9%, respectively. More than one-third (34.6%) of the women had pre-hypertension (pre-HTN)/hypertension (HTN), 34.1% had abnormal glucose intolerance (AGT), 93.0% had dyslipidemia, and 57.0% had MetS. The hyperandrogenic phenotypes (A, B, and C) had higher prevalence of pre-HTN/HTN, AGT, dyslipidemia, and MetS compared to the normoandrogenic phenotype D, though the differences were statistically insignificant. The clinical and biochemical markers of hyperandrogenism (Ferriman-Gallwey score, hirsutism, acne, and serum testosterone levels) did not differ among the hyperandrogenic phenotypes. The serum prolactin level was highest in phenotype C. No differences were observed in most other clinical, anthropometric, metabolic, and hormonal parameters among the four phenotypes. CONCLUSION: Phenotype A is the most prevalent phenotype of PCOS in our setting. The prevalence of MetS was considerably high. Most of the clinical, anthropometric, and metabolic parameters were similar across the four PCOS phenotypes in this study.

Modified HuffBit Compress Algorithm - An Application of R.

The databases of genomic sequences are growing at an explicative rate because of the increasing growth of living organisms. Compressing deoxyribonucleic acid (DNA) sequences is a momentous task as the databases are getting closest to its threshold. Various compression algorithms are developed for DNA sequence compression. An efficient DNA compression algorithm that works on both repetitive and non-repetitive sequences known as "HuffBit Compress" is based on the concept of Extended Binary Tree. In this paper, here is proposed and developed a modified version of "HuffBit Compress" algorithm to compress and decompress DNA sequences using the R language which will always give the Best Case of the compression ratio but it uses extra 6 bits to compress than best case of "HuffBit Compress" algorithm and can be named as the "Modified HuffBit Compress Algorithm". The algorithm makes an extended binary tree based on the Huffman Codes and the maximum occurring bases (A, C, G, T). Experimenting with 6 sequences the proposed algorithm gives approximately 16.18 % improvement in compression ration over the "HuffBit Compress" algorithm and 11.12 % improvement in compression ration over the "2-Bits Encoding Method".

An Automatic Gastrointestinal Polyp Detection System in Video Endoscopy Using Fusion of Color Wavelet and Convolutional Neural Network Features.

Gastrointestinal polyps are considered to be the precursors of cancer development in most of the cases. Therefore, early detection and removal of polyps can reduce the possibility of cancer. Video endoscopy is the most used diagnostic modality for gastrointestinal polyps. But, because it is an operator dependent procedure, several human factors can lead to misdetection of polyps. Computer aided polyp detection can reduce polyp miss detection rate and assists doctors in finding the most important regions to pay attention to. In this paper, an automatic system has been proposed as a support to gastrointestinal polyp detection. This system captures the video streams from endoscopic video and, in the output, it shows the identified polyps. Color wavelet (CW) features and convolutional neural network (CNN) features of video frames are extracted and combined together which are used to train a linear support vector machine (SVM). Evaluations on standard public databases show that the proposed system outperforms the state-of-the-art methods, gaining accuracy of 98.65%, sensitivity of 98.79%, and specificity of 98.52%.