SkinAI™
SkinAI™ is a suite of machine learning pipelines that perform preliminary assessments for a variety of skin conditions and adds Artificial Intelligence workflow to the Skinopathy EMR™ platform.
About SkinAI™
The pandemic has placed an incredible burden on the healthcare system, and, unfortunately, skin cancer screenings have plummeted resulting in an alarming trend where initial late-stage skin cancer diagnoses are increasing at a rapid pace.
SkinAI™ technology was created so that people who fear the threat of skin disease or skin cancer could get a preliminary analysis as to the urgency of their lesions, without the need to wait months for an appointment or risk close contact with someone with Covid19.
Since the technology is geographically agnostic, we are also able to deploy it to under-serviced regions and provide people with unparalleled access to healthcare.
About SkinAI™
SkinAI™ technology was created so that people who fear the threat of skin disease or skin cancer could get a preliminary analysis as to the urgency of their lesions, without the need to wait months for an appointment or risk close contact with someone with Covid19.
Since the technology is geographically agnostic, we are also able to deploy it to under-serviced regions and provide people with unparalleled access to healthcare.
What we have created is a Convolutional Neural Network (CNN)-based technology geared for skin abnormalities.
CNN’s are mostly used for analyzing images. The most famous application being the “Re-Captcha” security feature found on many websites, which is a process that trains such CNNs.
However, instead of using our AI to determine the difference between a fire hydrant and a bus, we are using this technology to determine the difference between a mole and a cancerous lesion.
SkinAI™ is a light-load AI that features an integrated feedback loop process that continuously refines our precision and accuracy.
However, since our technology is geared for the public and not trained physicians with dermatoscopes, we created a secondary database that more accurately reflected the type of real-world images patients are likely to submit.
The substantial variance in both focus and field of view allowed us to do real-world testing of our model and compare those results with the pristine HAM10000 database.
Eventually, SkinAI will be trained for a variety of skin concerns that include burns, wounds, and other ailments.