Skin lesion segmentation (SLS) in dermoscopic images is a crucial task for automated diagnosis of melanoma. In this paper, we present a robust deep learning SLS model, so-called SLSDeep, which is represented as an encoder-decoder network. The encoder network is constructed by dilated residual layers, in turn, a pyramid pooling network followed by three convolution layers is used for the decoder. Unlike the traditional methods employing a cross-entropy loss, we investigated a loss function by combining both Negative Log Likelihood (NLL) and End Point Error (EPE) to accurately segment the melanoma regions with sharp boundaries. The robustness of the proposed model was evaluated on two public databases: ISBI 2016 and 2017 for skin lesion analysis towards melanoma detection challenge. The proposed model outperforms the state-of-the-art methods in terms of segmentation accuracy. Moreover, it is capable to segment more than 100 images of size 384 × 384 per second on a recent GPU.

Background Convalescent plasma has been widely used to treat COVID-19 and is under investigation in numerous randomized clinical trials, but results are publicly available only for a small number of trials. The objective of this study was to assess the benefits of convalescent plasma treatment compared to placebo or no treatment and all-cause mortality in patients with COVID-19, using data from all available randomized clinical trials, including unpublished and ongoing trials (Open Science Framework, https://doi.org/10.17605/OSF.IO/GEHFX). Methods In this collaborative systematic review and meta-analysis, clinical trial registries (ClinicalTrials.gov, WHO International Clinical Trials Registry Platform), the Cochrane COVID-19 register, the LOVE database, and PubMed were searched until April 8, 2021. Investigators of trials registered by March 1, 2021, without published results were contacted via email. Eligible were ongoing, discontinued and completed randomized clinical trials that compared convalescent plasma with placebo or no treatment in COVID-19 patients, regardless of setting or treatment schedule. Aggregated mortality data were extracted from publications or provided by investigators of unpublished trials and combined using the Hartung–Knapp–Sidik–Jonkman random effects model. We investigated the contribution of unpublished trials to the overall evidence. Results A total of 16,477 patients were included in 33 trials (20 unpublished with 3190 patients, 13 published with 13,287 patients). 32 trials enrolled only hospitalized patients (including 3 with only intensive care unit patients). Risk of bias was low for 29/33 trials. Of 8495 patients who received convalescent plasma, 1997 died (23%), and of 7982 control patients, 1952 died (24%). The combined risk ratio for all-cause mortality was 0.97 (95% confidence interval: 0.92; 1.02) with between-study heterogeneity not beyond chance (I2 = 0%). The RECOVERY trial had 69.8% and the unpublished evidence 25.3% of the weight in the meta-analysis. Conclusions Convalescent plasma treatment of patients with COVID-19 did not reduce all-cause mortality. These results provide strong evidence that convalescent plasma treatment for patients with COVID-19 should not be used outside of randomized trials. Evidence synthesis from collaborations among trial investigators can inform both evidence generation and evidence application in patient care.

No abstract

An outbreak of Monkeypox has been reported in 75 countries so far, and it is spreading in fast pace around the world. The clinical attributes of Monkeypox resemble those of Smallpox, while skin lesions and rashes of Monkeypox often resemble those of other poxes, for example, Chickenpox and Cowpox. These similarities make Monkeypox detection challenging for healthcare professionals by examining the visual appearance of lesions and rashes. Additionally, there is a knowledge gap among healthcare professionals due to the rarity of Monkeypox before the current outbreak. Motivated by the success of artificial intelligence (AI) in COVID-19 detection, the scientific community has shown an increasing interest in using AI in Monkeypox detection from digital skin images. However, the lack of Monkeypox skin image data has been the bottleneck of using AI in Monkeypox detection. Therefore, recently, we introduced the Monkeypox Skin Image Dataset 2022, the largest of its kind so far. In addition, in this paper, we utilize this dataset to study the feasibility of using state-of-the-art AI deep models on skin images for Monkeypox detection. Our study found that deep AI models have great potential in the detection of Monkeypox from digital skin images (precision of 85%). However, achieving a more robust detection power requires larger training samples to train those deep models.

The aim of the study was to assess the antibody response to the ChAdOx1-nCoV vaccine in individuals who were not previously infected by COVID-19. Patients and Methods: All people aged 18-65 years who received their first vaccination with ChAdOx1-nCoV from March to May 2021 were approached for inclusion. Individuals with sufficient antibody titers against SARS-CoV-2 infection before vaccination were considered previously infected and were excluded from the analysis. We observed viral spike protein RBD-S1-specific IgG antibody levels at day 28 of the first dose of vaccination and day 14 of the second dose of vaccination (74 days from index vaccination). An optical density ratio (ODR) of >1.1 was considered to have a positive antibody response, 0.8 to 1.1 borderline and <0.8 was denoted as negative. Informed consent was ensured before enrollment, and ethical principles conformed with the current Declaration of Helsinki. Results: This observational study comprised 769 infection-naïve individuals (mean age 40.5 years, 38.9% female). Spike-specific IgG antibody responses elicited after the first and second doses of vaccine were 99.9% and 100%, respectively. The median ODR was 5.43 (interquartile range [IQR]: 4.32-6.98) and 10.90 (IQR 9.02-11.90) after the first and second doses. Higher age was associated with lower antibody levels after both dosages. However, no sex-specific variation was seen. People with comorbidity had a lower antibody level after the second dose. Tenderness (51.46%) and fever (19.30%) were the most common local and systemic side effects after vaccination. Conclusion:This study was one of the earlier attempts in the country to assess the antibody response to ChAdOx1-nCoV vaccine recipients. The results imply that general people should be encouraged to take the vaccine at their earliest.

Objectives General: To assess the safety, efficacy and dose response of convalescent plasma (CP) transfusion in severe COVID-19 patients Specific: a. To identify the appropriate effective dose of CP therapy in severe patients b. To identify the efficacy of the therapy with their end point based on clinical improvement within seven days of treatment or until discharge whichever is later and in-hospital mortality c. To assess the clinical improvement after CP transfusion in severe COVID-19 patients d. To assess the laboratory improvement after CP transfusion in severe COVID-19 patients Trial Design This is a multicentre, multi-arm phase II Randomised Controlled Trial. Participants Age and sex matched COVID-19 positive (by RT-PCR) severe cases will be enrolled in this trial. Severe case is defined by the World Health Organization (W.H.O) clinical case definition. The inclusion criteria are 1. Respiratory rate > 30 breaths/min; PLUS 2. Severe respiratory distress; or SpO2 ≤ 88% on room air or PaO2/FiO2≤ 300 mm of Hg, PLUS 3. Radiological (X-ray or CT scan) evidence of bilateral lung infiltrate, AND OR 4. Systolic BP < 90 mm of Hg or diastolic BP <60 mm of Hg. AND/OR 5. Criteria 1 to 4 AND or patient in ventilator support Patients’ below18 years, pregnant and lactating women, previous history of allergic reaction to plasma, patients who have already received plasma from a different source will be excluded. Patients will be enrolled at Bangabandhu Sheikh Mujib Medical University (BSMMU) hospital, Dhaka medical college hospital (DMCH) and Mugda medical college hospital (MuMCH). Apheretic plasma will be collected at the transfusion medicine department of SHNIBPS hospital, ELISA antibody titre will be done at BSMMU and CMBT and neutralizing antibody titre will be checked in collaboration with the University of Oxford. Patients who have recovered from COVID-19 will be recruited as donors of CP. The recovery criteria are normality of body temperature for more than 3 days, resolution of respiratory symptoms, two consecutively negative results of sputum SARS-CoV-2 by RT-PCR assay (at least 24 hours apart) 22 to 35 days of post onset period, and neutralizing antibody titre ≥ 1:160. Intervention and comparator This RCT consists of three arms, a. standard care, b. standard care and 200 ml CP and c. standard care and 400 ml CP. Patients will receive plasma as a single transfusion. Intervention arms will be compared to the standard care arm. Main outcomes The primary outcome will be time to clinical improvement within seven days of treatment or until discharge whichever is later and in-hospital mortality. The secondary outcome would be improvement of laboratory parameters after therapy (neutrophil, lymphocyte ratio, CRP, serum ferritin, SGPT, SGOT, serum creatinine and radiology), length of hospital stay, length of ICU stay, reduction in proportion of deaths, requirement of ventilator and duration of oxygen and ventilator support. Randomisation Randomization will be done by someone not associated with the care or assessment of the patients by means of a computer generated random number table using an allocation ratio of 1:1:1. Blinding (masking) This is an open level study; neither the physician nor the patients will be blinded. However, the primary and secondary outcome (oxygen saturations, PaO2/FiO2, BP, day specific laboratory tests) will be recorded using an objective automated method; the study staff will not be able to influence the recording of these data. Number to be randomised (sample size) No similar study has been performed previously. Therefore no data are available that could be used to generate a sample size calculation. This phase II study is required to provide some initial data on efficacy and safety that will allow design of a larger study. The trial will recruit 60 participants (20 in each arm). Trial Status Protocol version 1.4 dated May 5, 2020 and amended version 1.5, dated June 16, 2020. First case was recruited on May 27, 2020. By August 10, 2020, the trial had recruited one-third (21 out of 60) of the participants. The recruitment is expected to finish by October 31, 2020. Trial registration Clinicaltrials.gov ID: NCT04403477. Registered 26 May, 2020 Full Protocol The full protocol is attached as an additional file, accessible from the Trial’s website (Additional file 1). In the interest in expediting dissemination of this material, the familiar formatting has been eliminated; this letter serves as a summary of the key elements of the full protocol.

Monkeypox has emerged as a fast-spreading disease around the world and an outbreak has been reported in 42 countries so far. Although the clinical attributes of Monkeypox are similar to that of Smallpox, skin lesions and rashes caused by Monkeypox often resemble that of other pox types, e.g., Chickenpox and Cowpox. This scenario makes an early diagnosis of Monkeypox challenging for the healthcare professional just by observing the visual appearance of lesions and rashes. The rarity of Monkeypox before the current outbreak further created a knowledge gap among healthcare professionals around the world. To tackle this challenging situation, scientists are taking motivation from the success of supervised machine learning in COVID-19 detection. However, the lack of Monkeypox skin image data is making the bottleneck of using machine learning in Monkeypox detection from skin images of patients. Therefore, in this project, we introduce the Monkeypox Skin Image Dataset (MSID), the largest of its kind so far. We used web-scrapping to collect Monkeypox, Chickenpox, Smallpox, Cowpox and Measles infected skin as well as healthy skin images to build a comprehensive image database and made it publicly available. We believe that our database will facilitate the development of baseline machine learning algorithms for early Monkeypox detection in clinical settings. Our dataset is available in the following Kaggle link: https://www.kaggle.com/datasets/arafathussain/monkeypox-skinimage-dataset-2022.

No abstract