Developing a Recognition System for Diagnosing Melanoma Skin Lesions Using Artificial Intelligence Algorithms.

In recent years, computerized biomedical imaging and analysis have become extremely promising, more interesting, and highly beneficial. They provide remarkable information in the diagnoses of skin lesions. There have been developments in modern diagnostic systems that can help detect melanoma in its early stages to save the lives of many people. There is also a significant growth in the design of computer-aided diagnosis (CAD) systems using advanced artificial intelligence. The purpose of the present research is to develop a system to diagnose skin cancer, one that will lead to a high level of detection of the skin cancer. The proposed system was developed using deep learning and traditional artificial intelligence machine learning algorithms. The dermoscopy images were collected from the PH2 and ISIC 2018 in order to examine the diagnose system. The developed system is divided into feature-based and deep leaning. The feature-based system was developed based on feature-extracting methods. In order to segment the lesion from dermoscopy images, the active contour method was proposed. These skin lesions were processed using hybrid feature extractions, namely, the Local Binary Pattern (LBP) and Gray Level Co-occurrence Matrix (GLCM) methods to extract the texture features. The obtained features were then processed using the artificial neural network (ANNs) algorithm. In the second system, the convolutional neural network (CNNs) algorithm was applied for the efficient classification of skin diseases; the CNNs were pretrained using large AlexNet and ResNet50 transfer learning models. The experimental results show that the proposed method outperformed the state-of-art methods for HP2 and ISIC 2018 datasets. Standard evaluation metrics like accuracy, specificity, sensitivity, precision, recall, and F-score were employed to evaluate the results of the two proposed systems. The ANN model achieved the highest accuracy for PH2 (97.50%) and ISIC 2018 (98.35%) compared with the CNN model. The evaluation and comparison, proposed systems for classification and detection of melanoma are presented.

Infection Control of COVID-19: Surgical Mask-Related Facial Cutaneous Artifact on FDG PET/CT.

ABSTRACT: In accordance with published international COVID-19 pandemic guidance (American College of Nuclear Medicine, British Nuclear Medicine Society, and European Association of Nuclear Medicine), the use of face masks has become an essential part of infection control for both patients and staff. A 56-year-old man with mantle cell lymphoma underwent staging FDG PET/CT, which demonstrated avid lymphadenopathy below the diaphragm and an unusual diffuse FDG uptake projected over the face, raising the suspicion of cutaneous lymphomatous involvement. On reflection of the clinical scenario and scanning conditions, cutaneous involvement was discounted; the pattern of uptake and lack of CT correlate were supportive of a cutaneous artifact related to the presence of the patient's mask.

A UK-wide survey looking at teaching and trainee confidence in teledermatology: a vital gap in a COVID-19-induced era of rapid digital transformation?

Teledermatology has had an explosive impact on the provision of dermatology services in recent times, and even more so with the unprecedented situation created by the COVID-19 pandemic. Although teledermatology is not presently a feature of the Joint Royal Colleges of Physicians Training Board (JRCPTB) curriculum for dermatology training, this is due to change imminently. Specialty trainees need training in this area to be able to confidently and competently meet the demands of the changing face of dermatology services. We surveyed dermatology registrars in training across the UK, prior to the outbreak of COVID-19, to ascertain the teledermatology teaching available and trainee confidence in this area. Our survey found that only 15% of respondents felt slightly confident in their ability to deal with teledermatology referrals and almost all (96%) felt more teaching was needed.