Skin cancer is one of the most common cancers in the world. The rate of skin cancer increased dramatically during the latest four decades and continues to rise in many places nowadays. Due to the lack of dermatologists and frequent misdiagnosis, many people may have skin cancer without knowing it.
Late-stage skin cancers spreads to internal organs and become fatal. Early stage skin cancer can be cured with a high survival rate (98%), while the 5-year survival rate for skin cancer is extremely low (15%). Therefore, early detection is the key of fighting skin cancer.
The use of artificial intelligence (AI) in research of skin cancer detection has received tremendous attention in last decade. Many software dedicated to detect melanoma using AI have been developed such as SkinVision and MoleMapper, to name a few. However, most of developed apps share the limitation of classification being not detailed enough hence they could not help users to make decision on what to do next with their lesions.
Supported by iToBoS, one of the biggest European projects for fighting skin cancer, Torus Actions has developed a novel AI solution for early detection of skin cancer. This AI solution is designed not only for medical professionals but also for patients or non-professional users to monitor their skin regularly. Therefore, it is designed to classify the lesions as detailed as possible and help the users understand the diagnosis as well as guide them to make a good decision on what to do next with their lesions.
Skin Cancer AI developed by Torus Actions makes a very detailed classification of lesions with more than 100 categories, including both melanoma and non-melanoma skin cancers as well as other benign tumours that might mimic skin cancers. Moreover, Skin Cancer AI is integrated a cancer risk system that contains six levels: (5) risk of high-grade cancer, (4) risk of cancer, (3) risk of cancer or pre-cancer, (2) check more to rule out cancer, (1) probably benign but monitor, (0) cancer sign not found.
The cancer risk level 5 suggests a high risk of invasive melanoma or other high-grade skin cancers such as Merkel Cell Carcinoma. The level 4 suggests a high risk of melanoma in situ or non-melanoma skin cancers such as Basal Cell Carcinoma or Squamous Cell Carcinoma. The level 3 suggests a significant risk of cancer or high risk of pre-cancer or borderline cases such as Actinic Keratosis, Spitz nevus or dysplastic nevus. The level 2 suggests a low but still significant risk of cancer or pre-cancer, therefore, it advises users to check more to rule out skin cancer. The level 1 suggest a low but still significant risk of pre-cancer or borderline cases, therefore, it advises users to monitor the lesions. Finally, the level 0 implies that no sign of cancer was found from the lesion.
The cancer risk level is calculated based on the scores of classes and sub-classes in detailed diagnosis provided by Skin Cancer AI.
Visit Torus Actions website https://www.torus.ai/ for more information about their novel Skin Cancer AI and cancer risk system.