During the last years, computer-vision-based diagnosis systems have been used in several hospitals and dermatology clinics, aiming mostly at the early detection of skin cancer, and more specifically, the recognition of malignant melanoma tumour. In this paper, we review the state of the art in such systems by first presenting the installation, the visual features used for skin lesion classification, and the methods for defining them. Then, we describe how to extract these features through digital image processing methods, i.e., segmentation, border detection, and color and texture processing, and we present the most prominent techniques for skin lesion classification. The paper reports the statistics and the results of the most important implementations that exist in the literature, while it compares the performance of several classifiers on the specific skin lesion diagnostic problem and discusses the corresponding findings.

No abstract

Cloud Computing provides functionality for managing information data in a distributed, ubiquitous and pervasive manner supporting several platforms, systems and applications. This work presents the implementation of a mobile system that enables electronic healthcare data storage, update and retrieval using Cloud Computing. The mobile application is developed using Google's Android operating system and provides management of patient health records and medical images (supporting DICOM format and JPEG2000 coding). The developed system has been evaluated using the Amazon's S3 cloud service. This article summarizes the implementation details and presents initial results of the system in practice.

This paper presents a smart phone based system for storing digital images of skin areas depicting regions of interest (lesions) and performing self-assessment of these skin lesions within these areas. The system consists of a mobile application that can acquire and identify moles in skin images and classify them according their severity into melanoma, nevus and benign lesions. The proposed system includes also a cloud infrastructure exploiting computational and storage resources. This cloud-based architecture provides interoperability and support of various mobile environments as well as flexibility in enhancing the classification model. Initial evaluation results are quite promising and indicate that the application can be used for the task of skin lesions initial assessment.

This paper presents the implementation details of a patient status awareness enabling human activity interpretation and emergency detection in cases, where the personal health is threatened like elder falls or patient collapses. The proposed system utilizes video, audio, and motion data captured from the patient's body using appropriate body sensors and the surrounding environment, using overhead cameras and microphone arrays. Appropriate tracking techniques are applied to the visual perceptual component enabling the trajectory tracking of persons, while proper audio data processing and sound directionality analysis in conjunction to motion information and subject's visual location can verify fall and indicate an emergency event. The postfall visual and motion behavior of the subject, which indicates the severity of the fall (e.g., if the person remains unconscious or patient recovers) is performed through a semantic representation of the patient's status, context and rules-based evaluation, and advanced classification. A number of advanced classification techniques have been examined in the framework of this study and their corresponding performance in terms of accuracy and efficiency in detecting an emergency situation has been thoroughly assessed.