An Efficient Deep Learning-Based Skin Cancer Classifier for an Imbalanced Dataset.

Efficient skin cancer detection using images is a challenging task in the healthcare domain. In today's medical practices, skin cancer detection is a time-consuming procedure that may lead to a patient's death in later stages. The diagnosis of skin cancer at an earlier stage is crucial for the success rate of complete cure. The efficient detection of skin cancer is a challenging task. Therefore, the numbers of skilful dermatologists around the globe are not enough to deal with today's healthcare. The huge difference between data from various healthcare sector classes leads to data imbalance problems. Due to data imbalance issues, deep learning models are often trained on one class more than others. This study proposes a novel deep learning-based skin cancer detector using an imbalanced dataset. Data augmentation was used to balance various skin cancer classes to overcome the data imbalance. The Skin Cancer MNIST: HAM10000 dataset was employed, which consists of seven classes of skin lesions. Deep learning models are widely used in disease diagnosis through images. Deep learning-based models (AlexNet, InceptionV3, and RegNetY-320) were employed to classify skin cancer. The proposed framework was also tuned with various combinations of hyperparameters. The results show that RegNetY-320 outperformed InceptionV3 and AlexNet in terms of the accuracy, F1-score, and receiver operating characteristic (ROC) curve both on the imbalanced and balanced datasets. The performance of the proposed framework was better than that of conventional methods. The accuracy, F1-score, and ROC curve value obtained with the proposed framework were 91%, 88.1%, and 0.95, which were significantly better than those of the state-of-the-art method, which achieved 85%, 69.3%, and 0.90, respectively. Our proposed framework may assist in disease identification, which could save lives, reduce unnecessary biopsies, and reduce costs for patients, dermatologists, and healthcare professionals.

COVID 19 pandemic: Effect on management of patients with breast cancer; single center retrospective cohort study.

BACKGROUND: (SARS-COV-2) infection, led to a pandemic affecting many countries, resulting in hospitals diverting most of their resources to fight the pandemic. Breast cancer, already a healthcare dilemma, is also affected in this scenario. Our aim was to find out the impact of COVID-19 on presentation of breast cancer stage and its effects on overall onco-surgical management. METHODS: This cohort single-centered retrospective review was carried out at our hospital, over a period of 18 months. Females with known breast cancer were included in the study. Data was collected on performas by a single researcher. Effect of COVID pandemic on presentation stage and its impact on overall management was studied. SPSS 23.0 used for data analysis. A 95% CI was used. Descriptive statistics were presented as range/means. Categorical data was analyzed by Fisher exact test, t-test was applied to numerical data, p value ≤ 0.05 was considered significant. RESULTS: Out of 87 patients presenting with suspicious lump, 69 who had malignancy on histo-pathology were included in study. Twelve out of 69 were COVID positive. Sixty patients presented with advanced stage (≥stage 2b) out of which 21 underwent upstaging of disease due to delay in presentation/management. We found that 9 out of 12 (majority) Covid positive patients had disease upstaging. Overall main reason for delay in presentation was found to be unawareness of disease. CONCLUSION: We concluded that COVID-19 pandemic had no impact on presentation delay, breast cancer management/treatment and disease upstaging as compared to figures available for our population before the pandemic. However, our study showed significant correlation between disease upstaging and COVID status. This led us to reconsider our preformed protocols for COVID positive breast cancer patients. Our results can be used by future researchers to investigate if COVID itself can contributes in patho-physiology of upstaging in breast cancer or not.

Single tube multiplex PCR assay for the identification of banned meat species.

Food adulteration has a direct impact on public health, religious faith, fair-trades, and wildlife. In the present study, a reliable and sensitive assay has been developed for verifying meat adulteration in food chain. The multiplex PCR system was optimised for identification of chicken, cow/buffalo, sheep/goat, horse/donkey, pork, and dog DNAs in a single reaction mixture simultaneously. The primers were designed using 12 S rRNA gene sequences with fragment size in the range of 113 bp to 800 bp, which can be easily visualised on agarose gel electrophoresis making the technique economical. After validation of accuracy, specificity, and sensitivity, commercially available meat products (n = 190) were screened, comprising both raw and cooked meat samples. The results demonstrated a high rate of adulteration (54.5%) in meat products. The technique developed here can be easily used for screening of different meat products for export and import purposes as well as for food inspection and livestock diagnostic laboratories.