Revolutionizing Skin Cancer Detection with Artificial Intelligence
Ameliorating the monitoring of patients’ skin evolution is now made possible thanks to artificial intelligence. This innovative technology allows for documenting the progression of moles and visible lesions “with a high level of confidence”.
Cutting-edge technologies combined with artificial intelligence could provide valuable assistance in skin cancer screening.
The Vectra WB360, a machine already present in certain medical centers, is capable of photographing almost the entire surface of a patient’s skin in a single shot, using 92 high-definition sensors. This enables the scanner to provide a mapping of visible lesions and moles. “The doctor can then, remotely, choose to zoom in on one that appears suspicious to analyze it,” explains Isabelle, the hospital director possessing a Vectra WB360 machine, who leads the company France Dermatologie Territoires. “Today, the machine cannot yet provide a diagnosis,” specifies Jilliana Monnier, a dermatologist. That is to say, affirm whether a certain lesion is a melanoma. The goal will be to develop AI algorithms capable of easily and quickly identifying new, evolving, or suspicious lesions on the skin as a whole.
A cancer requiring precise monitoring, melanoma is a skin tumor that resembles a mole but often exhibits the following characteristics: asymmetry, irregular borders, multiple colors, enlargement, or change in appearance. The number of new cases per year has steadily increased over the past two or three decades. However, thanks to improved screening and the introduction of new treatments, the death rate has tended to stabilize in recent years. Every year in France, approximately 18,000 cases of melanoma are discovered, the most aggressive of skin cancers, resulting in 2,000 deaths.
“Since the late 1990s, many practices have equipped themselves with so-called digital dermoscopy machines, which allow for taking photos of the skin and then comparing them in successive appointments to monitor the progression,” recounts Luc Thomas, a skin cancer specialist, and practitioner at the University Hospital of Lyon. Previously capable of photographing the skin cm² by cm², the machines can now capture almost the entire body surface.
Detecting melanoma “with a high level of confidence”, Ali Khachloud, co-founder of SquareMind, announces “we have developed an AI that will soon be available on the market, capable of detecting the evolution of these moles with ‘a high level of confidence'”. The device enables the acquisition of very high-resolution full-body imaging.
Practitioners hope to be able to rely on the assistance of artificial intelligence. By automatically documenting the skin surface, they will be able to create a complete history of lesions and moles of these patients.
In a time where dermatological services are diminishing, automating certain time-consuming steps of melanoma screening will allow for more precise patient monitoring, explains Jilliana Monnier.