Related Experiment Video
Updated: Jul 6, 2025
10:23
Screening for Melanoma Modifiers using a Zebrafish Autochthonous Tumor Model
Published on: November 13, 2012
13.7K
Using Artificial Intelligence as a Melanoma Screening Tool in Self-Referred Patients
Madeleine E Crawford1, Kiyana Kamali1, Rachel A Dorey1
1Division of Clinical Dermatology and Cutaneous Science, Department of Medicine, Dalhousie University, Halifax, NS, Canada.
Journal of Cutaneous Medicine and Surgery
|December 29, 2023
Summary
Artificial intelligence (AI) shows promise as a skin cancer screening tool for flagging potential melanomas in self-referred patients. While AI has limitations, it can aid in timely diagnosis and improve access to care for suspicious skin lesions.
Area of Science:
- Dermatology
- Medical Imaging
- Artificial Intelligence
Background:
- Early detection of melanoma is crucial for timely medical care.
- Self-referred patients with concerning skin lesions require efficient diagnostic pathways.
Purpose of the Study:
- To assess the feasibility of using artificial intelligence (AI) to identify potential melanomas in patients concerned about skin lesions.
- To evaluate AI's performance in flagging suspicious lesions compared to dermatologists.
Main Methods:
- Patients with skin lesions of concern were recruited and lesions scanned using the FotoFinder System.
- AI software analyzed lesion images, and results were compared to evaluations by experienced dermatologists.
- Suspicious lesions identified by AI or dermatologists were surgically excised for analysis.
Main Results:
- Seventeen malignancies, including 10 melanomas, were confirmed.
- AI did not flag six melanomas, which presented as diagnostically challenging atypical melanocytic proliferations.
- AI's diagnostic capability for malignancy was found to be non-inferior to dermatologists evaluating dermoscopic images.
Conclusions:
- AI can function as a practical aid in skin cancer screening for self-referred patients.
- Despite technical and diagnostic limitations, AI inclusion in screening programs can enhance timely diagnosis of skin cancer.
- AI offers valuable support in providing prompt access to diagnosis for individuals with concerning skin lesions.
