JMIR Publications

ABSTRACT

Background:

Skin cancer is the most common cancer type affecting humans. Traditional skin cancer diagnosis methods are costly, require a professional physician, and take time. Hence, to aid in diagnosing skin cancer, Artificial Intelligence (AI) tools are being used, including shallow and deep machine learning-based techniques that are trained to detect and classify skin cancer using computer algorithms and deep neural networks.

Objective:

The aim of this study is to identify and group the different types of AI-based technologies used to detect and classify skin cancer. The study also examines the reliability of the selected papers by studying the correlation between the dataset size and number of diagnostic classes with the performance metrics used to evaluate the models.

Methods:

We conducted a systematic search for articles using IEEE Xplore, ACM DL, and Ovid MEDLINE databases following the PRISMA Extension for Scoping Reviews (PRISMA-ScR) guidelines. The study included in this scoping review had to fulfill several selection criteria; to be specifically about skin cancer, detecting or classifying skin cancer, and using AI technologies. Study selection and data extraction were conducted by two reviewers independently. Extracted data were synthesized narratively, where studies were grouped based on the diagnostic AI techniques and their evaluation metrics.

Results:

We retrieved 906 papers from the 3 databases, but 53 studies were eligible for this review. While shallow techniques were used in 14 studies, deep techniques were utilized in 39 studies. The studies used accuracy (n=43/53), the area under receiver operating characteristic curve (n=5/53), sensitivity (n=3/53), and F1-score (n=2/53) to assess the proposed models. Studies that use smaller datasets and fewer diagnostic classes tend to have higher reported accuracy scores.

Conclusions:

The adaptation of AI in the medical field facilitates the diagnosis process of skin cancer. However, the reliability of most AI tools is questionable since small datasets or low numbers of diagnostic classes are used. In addition, a direct comparison between methods is hindered by a varied use of different evaluation metrics and image types.