AI better than humans at diagnosing skin lesions
When it comes to the diagnosis of pigmented skin lesions, artificial intelligence is superior to humans.
That’s according to a new study conducted under the supervision of the Medical University of Vienna, which saw human experts ‘compete’ against computer algorithms. The results of the competition have been published in The Lancet Oncology.
The International Skin Imaging Collaboration (ISIC) and MedUni Vienna organised an international challenge to compare the diagnostic skills of 511 physicians with 139 computer algorithms from 77 different machine learnings labs. A database of more than 10,000 images, which was established in cooperation with The University of Queensland (UQ), was used as a training set for the machines. This database includes benign (moles, sun spots, senile warts, angiomas and dermatofibromas) and malignant pigmented lesions (melanomas, basal cell carcinoma and pigmented squamous cell carcinoma).
Each participant had to diagnose 30 randomly selected images out of a test-set of 1511 images — and the result was unequivocal. While the best humans (typically those with at least 10 years of experience) diagnosed 18.8 out of 30 cases correctly, the best machines achieved 25.4 correct diagnoses. This did not surprise first author Philipp Tschandl from the MedUni Vienna, who said, “Two-thirds of all participating machines were better than humans; this result had been evident in similar trials during the past years.”
Despite the impressive performance of AI, the researchers believe there is still room for improvement, as the machines were significantly less accurate in the diagnosis of lesions that came from centres that did not provide training images. There are also other factors that mean they are not likely to replace humans in the diagnosis of skin cancer anytime soon.
“The computer only analyses an optical snapshot and is really good at it — in real life, however, the diagnosis is a complex task,” Tschandl explained. “Physicians usually examine the entire patient and not just single lesions. When humans make a diagnosis they also take additional information into account, such as the duration of the disease, whether the patient is at high or low risk, and the age of the patient, which was not provided in this study.”
Nanostructured layers boast countless potential properties — but how can the most suitable...
The goal was to design and deploy a decision-support tool using AI capabilities — mostly...
Sydney start-ups DetectED-X and LENS Immersive have each launched tools designed to take the...