9th International Conference on Pervasive Computing Technologies for Healthcare

Research Article

A Novel Framework for Supervised Mobile Assessment and Risk Triage of Skin Lesions

Download54 downloads
  • @INPROCEEDINGS{10.4108/icst.pervasivehealth.2015.259254,
        author={Lu\^{\i}s Rosado and Maria Vasconcelos and Fernando Correia and Nuno Costa},
        title={A Novel Framework for Supervised Mobile Assessment and Risk Triage of Skin Lesions},
        proceedings={9th International Conference on Pervasive Computing Technologies for Healthcare},
        publisher={IEEE},
        proceedings_a={PERVASIVEHEALTH},
        year={2015},
        month={8},
        keywords={malignant melanoma detection abcd rule of dermatoscopy mobile monitoring image analysis},
        doi={10.4108/icst.pervasivehealth.2015.259254}
    }
    
  • Luís Rosado
    Maria Vasconcelos
    Fernando Correia
    Nuno Costa
    Year: 2015
    A Novel Framework for Supervised Mobile Assessment and Risk Triage of Skin Lesions
    PERVASIVEHEALTH
    ICST
    DOI: 10.4108/icst.pervasivehealth.2015.259254
Luís Rosado1, Maria Vasconcelos1, Fernando Correia1,*, Nuno Costa1
  • 1: Fraunhofer Portugal AICOS
*Contact email: fernando.correia@fraunhofer.pt

Abstract

Mobile Teledermatology is a promising tool with the potential to empower patients to adopt an active role in managing their own health status. The main objective of this work is to create a mobile-based framework for risk triage and early diagnosis of skin cancers, with the active involvement of an online community of dermatologists. The presented prototype is composed by the following components: 1) Mobile Application for the patients; 2) Back-end Server that hosts the image processing module and database; and 3) Web Interface for the dermatologists. Using the mobile application, the patients can send a check-up to the back-end server, composed by an image and additional information of the considered skin lesion. The check-up image is automatically analyzed using supervised classification, according to the ABCD Rule and Overall Risk. The system generates an analysis report for each check-up, which will assist the doctors in the check-up risk assessment. After the doctor’s validation, a report is sent to the patient’s mobile application, and the validated data is used to retrain the supervised classifiers. The overall system architecture and functionalities are briefly described.