AI and the Early Detection of Skin Cancer

AI and the Early Detection of Skin Cancer

May is Skin Cancer Awareness Month, highlighting the importance of regular skin checks and alerting us to some startling facts. Did you know skin cancer is the most common form of cancer in the United States and 1 in 5 Americans develop skin cancer before the age of 70?

The majority of skin cancers are caused by too much sun exposure, the CDC recommends practicing sun safety to reduce your risk of skin cancer. Yearly visits with your dermatologist and monthly skin self-checks support early detection and diagnosis. Artificial intelligence (AI) can also play a role in early detection. This week’s Domain Knowledge explores the role AI can play in the detection of skin cancer.

The three main types of skin cancer are basal cell carcinoma, squamous cell carcinoma, and melanoma. Basal cell and squamous cell carcinomas are very treatable when diagnosed early. The most serious of the three is melanoma, causing most all skin cancer deaths. Early detection of melanoma is closely tied to the five-year survival rate, which is 99% if found before the cancer has spread to the lymph nodes.

The identification of suspicious pigmented lesions (SPLs) is one way primary care physicians can help with the early identification of a potential melanoma. However, using SPLs as a melanoma indicator can be difficult as there is often a high volume on the skin, and most are not cancerous. This is where AI comes into play and has the potential to have the greatest impact, as the evaluation process from a photo is much faster than a manual inspection. This process serves as a primary screening that would lead to further evaluation.

Jonathan Kentley from the Memorial Sloan Kettering Cancer Center claims AI will not only help identify melanoma from SPLs, but also help dermatologists determine other skin conditions for a more complete evaluation of patients. Though this research is still experimental, AI intended to detect skin cancer can be applied to skin photo imaging in many similar ways. Derm.AI, for example, uses AI detection of skin lesions to improve telemedical dermatology screening.

AI used in skin cancer detection reads normal photographs of human skin, and anybody with a smartphone camera can capture these images. There are quite a few apps in development, working to utilize AI to give everyone instant access to skin screening. One example is the new dermatology camera recently approved by the FDA. Currently, the limiting factor is not enough data to validate phone app skin cancer screening, and users should be cautious about the results. Seeing your dermatologist is still the best course of action in getting screened, but it’s always a good idea to self-evaluate for any changes.

That’s a wrap for this week’s review of news and happenings in the healthcare AI space. In closing, I’ll leave you with an invitation to learn more about the benefits of using an AI Hub to manage multiple applications across your clinical needs and offer you a personal demo of Ferrum’s platform and growing AI catalog.

If you have AI tips, suggestions, or resources you’d like to share leave us a note below, and please feel free to suggest topics you would like to see covered in future posts.

Picture of Alex Uy

Alex Uy

Alex is a recent UC San Diego graduate with a degree in economics and communications. His focus is digital marketing, and he has a passion for technology driven healthcare solutions.

Contact Us

CASE STUDY

ARA Health Specialists

Use the button below to download your free case study and learn how our approach to validation has improved the number of clinically significant findings in AI software.

CASE STUDY

Sutter Health

Use the button below to download your free case study and learn how our approach to validation has improved the number of clinically significant findings in AI software.