This research aims to review the attempts of researchers in response to the new and disruptive technology of skin cancer applications in terms of evaluation and benchmarking, in order to identify the research landscape from the literature into a cohesive taxonomy. An extensive search was conducted for articles dealing with ‘skin cancer’, ‘apps’ and ‘smartphone’ or ‘mHealth’ in different variations to find all the relevant articles in three main databases, namely, “Web of Science”, “Science Direct”, and “IEEE explore”. These databases are considered wide enough to cover medical and technical literature. The final classification scheme outcome of the dataset contained 110 articles that were classified into four classes: development and design; analytical; evaluative and comparative; and review and survey studies. Afterwards, another filtering process was achieved based on the evaluation criteria error rate within the dataset, time complicity and reliability, which are used in skin cancer applications. The final classification scheme outcome of the dataset contained 89 articles distributed in mapping and crossover with four sections concluded from 110 articles. Development and design studies, analytical studies, evaluative and comparative studies and articles of reviews and surveys comprised of 48.3146%, 22.4719%, 16.8539% (15), and 12.3595% (11) of the reviewed articles, respectively. The basic features of this evolving approach were identified in these aspects. We also determined open issues in terms of evaluation and benchmarking that hamper the utility of this technology. Furthermore, with the exception of the 89 papers reviewed, the new recommendation pathway solution was described in order to improve the measurement process for smartphone-based skin cancer diagnosis applications.

A review on smartphone skin cancer diagnosis apps in evaluation and benchmarking: coherent taxonomy, open issues and recommendation pathway solution

Objective: This research aims to survey the efforts of researchers in response to the new and disruptive technology of skin cancer apps, map the research landscape from the literature onto coherent...

A Systematic Review on Smartphone Skin Cancer Apps: Coherent Taxonomy, Motivations, Open Challenges and Recommendations, and New Research Direction

Deep learning has become an extremely popular method in recent years, and can be a powerful tool in complex, prior-knowledge-required areas, especially in the field of biomedicine, which is now facing the problem of inadequate medical resources. The application of deep learning in disease diagnosis has become a new research topic in dermatology. This paper aims to provide a quick review of the classification of skin disease using deep learning to summarize the characteristics of skin lesions and the status of image technology. We study the characteristics of skin disease and review the research on skin disease classification using deep learning. We analyze these studies using datasets, data processing, classification models, and evaluation criteria. We summarize the development of this field, illustrate the key steps and influencing factors of dermatological diagnosis, and identify the challenges and opportunities at this stage. Our research confirms that a skin disease recognition method based on deep learning can be superior to professional dermatologists in specific scenarios and has broad research prospects.

Opportunities and Challenges: Classification of Skin Disease Based on Deep Learning

A survey, review, and future trends of skin lesion segmentation and classification

In the world today there are number of skin diseases which are found in humans, animals and plants. The illness caused by bacteria or infections will be known as skin disease like yeast infection, allergy, eczema, brown spot. These skin diseases have dangerous effect on skin and they keep on spreading over time. To control them from spreading it is necessary to identify these diseases at their starting stages. We adopted many technologies to identify these diseases like image processing, artificial neural network, data mining etc. Now a day's image processing is most effective for detection of these kinds of skin diseases. It uses different techniques to identify the part affected by disease like feature extraction, filtering, image pre-processing, image segmentation etc. It also identifies the affected areas color as well as the form of affected area. The paper conducts the review of various image processing techniques which are used for diagnosis of skin diseases in recent time. Analysis of the different methodologies and their performances that are utilized in these techniques of skin diseases diagnosis also be done.

https://ieeexplore.ieee.org/iel7/8168943/8226083/08226102.pdf

Comprehensive review of techniques used to detect skin lesion

Mobile Teledermatology appears nowadays as a promising tool with the potential to empower patients to adopt an active role in managing their own health status, while facilitates the early diagnosis of skin cancers. The main objective of this work is to create a mobile-based prototype to analyze skin lesions based on supervised classification. The presented self-monitoring system collects, processes and storages information of skin lesions through the automatic extraction and classification of specific visual features. The selected features are based on the ABCD rule, which considers 4 visual criteria considered highly relevant for the detection of malignant melanoma. The algorithms used to extract and classify these features are briefly described, as well as the overall system requirements and architecture.

Luas Rosado

Papers

A prototype for a mobile-based system of skin lesion analysis using supervised classification