A new preprocessing approach to improve the performance of CNN-based skin lesion classification.

Skin lesion is one of the severe diseases which in many cases endanger the lives of patients on a worldwide extent. Early detection of disease in dermoscopy images can significantly increase the survival rate. However, the accurate detection of disease is highly challenging due to the following reasons: e.g., visual similarity between different classes of disease (e.g., melanoma and non-melanoma lesions), low contrast between lesions and skin, background noise, and artifacts. Machine learning models based on convolutional neural networks (CNN) have been widely used for automatic recognition of lesion diseases with high accuracy in comparison to conventional machine learning methods. In this research, we proposed a new preprocessing technique in order to extract the region of interest (RoI) of skin lesion dataset. We compare the performance of the most state-of-the-art CNN classifiers with two datasets which contain (1) raw, and (2) RoI extracted images. Our experiment results show that training CNN models by RoI extracted dataset can improve the accuracy of the prediction (e.g., InceptionResNetV2, 2.18% improvement). Moreover, it significantly decreases the evaluation (inference) and training time of classifiers as well.

The pre-efficacy phase testing for PAfitME™-A behavioral physical activity intervention to manage moderate and severe symptoms among advanced stage cancer patients.

Fatigue and pain are the most frequently reported symptoms among advanced-stage cancer patients. Although physical activity (PA) is known to improve the aforementioned symptoms, few patients demonstrate the physically active behavior that adheres to the clinical guidelines regarding PA. The current article presents an exemplar that used the National Institute of Health's Obesity-Related Behavioral Intervention Trial (ORBIT) model and developed a behavioral intervention known as the personalized Physical Activity intervention with fitness graded Motion Exergames (PAfitME™). There were two phases of testing in the ORBIT model presented in the current paper. In Phase I testing, a standardized exergame prescription was evaluated by an advisory board and a single-case study was used to evaluate the personalized exergame prescription with personalization of the fitness levels. In Phase IIa, a within-group pre- and posttest design was used to evaluate the personalized exergame prescriptions with personalization of the fitness levels, self-efficacy, and variation in fatigue/pain. Subsequently, a complete intervention package was developed in accordance with a logic model, driven from the result of the Phase IIa testing with clinically significant findings. Currently, PAfitME™ is under Phase IIb testing in a randomized clinical trial with a control group. PAfitME™ employs a personalized approach to initiate and promote physically active behavior, to facilitate the management of fatigue and pain in cancer patients. Positive results from an efficacy trial would support the use of PAfitME™ in the management of fatigue and pain in advanced-stage cancer patients.