Adversarial Training Based Domain Adaptation of Skin Cancer Images.

Skin lesion datasets used in the research are highly imbalanced; Generative Adversarial Networks can generate synthetic skin lesion images to solve the class imbalance problem, but it can result in bias and domain shift. Domain shifts in skin lesion datasets can also occur if different instruments or imaging resolutions are used to capture skin lesion images. The deep learning models may not perform well in the presence of bias and domain shift in skin lesion datasets. This work presents a domain adaptation algorithm-based methodology for mitigating the effects of domain shift and bias in skin lesion datasets. Six experiments were performed using two different domain adaptation architectures. The domain adversarial neural network with two gradient reversal layers and VGG13 as a feature extractor achieved the highest accuracy and F1 score of 0.7567 and 0.75, respectively, representing an 18.47% improvement in accuracy over the baseline model.

Skin Cancer Detection Using Deep Learning-A Review.

Skin cancer is one the most dangerous types of cancer and is one of the primary causes of death worldwide. The number of deaths can be reduced if skin cancer is diagnosed early. Skin cancer is mostly diagnosed using visual inspection, which is less accurate. Deep-learning-based methods have been proposed to assist dermatologists in the early and accurate diagnosis of skin cancers. This survey reviewed the most recent research articles on skin cancer classification using deep learning methods. We also provided an overview of the most common deep-learning models and datasets used for skin cancer classification.

Understanding COVID-19 Vaccine Hesitancy in Ethnic Minorities Groups in the UK.

COVID-19 vaccines have been developed and administered at record pace in order to curtail the impact of the COVID-19 pandemic. Vaccine hesitancy has impacted uptake unequally across different groups. This study explores the drivers for vaccine hesitancy in ethnic minority groups in the UK, the impact of social media on vaccine hesitancy and how vaccine hesitancy may be overcome. Twelve semi-structured interviews were conducted, coded and thematically analyzed with participants from ethnic minority groups in the UK who identified as vaccine hesitant. Social media played a significant role in vaccine hesitancy. For those who considered themselves healthy, seeing misinformation of extreme side effects relating to COVID-19 vaccinations on social media resulted in the opinion that the risk of vaccination is greater than risk from COVID-19 infection. For women, misinformation on social media regarding fertility was a reason for delaying or not getting vaccinated. Participants who had sources of information they trusted in outside of social media were more likely to choose to get vaccinated. This study identified the broad spectrum of views on vaccine hesitancy in ethnic minority groups in the UK. Enabling factors such as a desire to travel, and positive public health messaging can increase vaccine uptake, whereas a lack of trusted sources of information may cause vaccine hesitancy. Further research is required to combat misinformation and conspiracy theories. Effective methods include actively responding and disproving the misinformation. For an inclusive vaccination programme that reduces health inequality, policy makers should build trust amongst marginalized communities and address their concerns through tailored public health messaging.