AI may diagnose skin lesions more accurately than human

AI may diagnose skin lesions more accurately than human

In a new study, researchers found that when it comes to the diagnosis of pigmented skin lesions, artificial intelligence (AI) is better than human.

They found that AI could achieve clearly better results, yet their current abilities cannot replace humans.

The research was conducted by a team from the Medical University of Vienna.

In the study, the International Skin Imaging Collaboration (ISIC) and the MedUni Vienna organized an international challenge to compare the diagnostic skills of 511 physicians with 139 computer algorithms.

A database of more than 10.000 images was used as a training set for computer algorithms.

This database includes benign (moles, sun spots, senile warts, angiomas, and dermatofibromas) and malignant pigmented lesions (melanomas and other types of skin cancer).

Each participant had to diagnose 30 randomly selected images out of a test-set of 1511 images.

The researchers found that the best humans diagnosed 18.8 out of 30 cases correctly, the best AI achieved 25.4 correct diagnoses.

The team says two-thirds of all participating AI algorithms were better than humans, and this result had been evident in similar trials during the past years.

They also mention that although the algorithms were clearly superior in this experiment, this does not mean that the machines will replace humans in the diagnosis of skin cancer.

This is because the computer only analyzes an optical snapshot and is really good at it.

In real life, however, the diagnosis is a much more complex task. Doctors 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.

Despite the impressive performance of AI there, is still room for improvement.

For example, the machines were much less accurate in the diagnosis of lesions that came from centers that did not provide training images.

The team also says that experience was important for human performance.

The most experienced doctors with at least ten years of experience in the diagnosis of pigmented skin lesions performed best.

The lead author of the study is Philipp Tschandl from the MedUni Vienna.

The study is published in the journal The Lancet Oncology.

Copyright © 2019 Knowridge Science Report. All rights reserved.