Seoul: Researchers have developed an artificial intelligence (AI) system that can accurately classify skin disorders, predict malignancy, and suggest primary treatment options, an advance that may be integrated with smartphones to act as a diagnostic aid for clinicians.
The study, published in the Journal of Integrative Dermatology, noted that the diagnostic accuracy of dermatologists as well as the general public can be significantly improved by using this system.
According to the researchers from Seoul National University in South Korea, skin diseases are common, but visiting a dermatologist to distinguish malignant from benign conditions is difficult in several parts of the world.
“Recently, there have been remarkable advances in the use of AI in medicine. For specific problems, such as distinguishing between melanoma and nevi, AI has shown results comparable to those of human dermatologists,” said study co-author Jung-Im Na from the Seoul National University in South Korea.
“However, for these systems to be practically useful, their performance needs to be tested in an environment similar to real practice, which requires classifying malignant versus benign lesion,” Na added.
He said such a system also needs to distinguishing skin cancer from numerous other skin disorders including inflammatory and infectious conditions
In the current study, the scientists developed an AI system capable of predicting malignancy, suggesting treatment options, and classifying skin disorders.
They collected 2,20,000 images of Asians and Caucasians with 174 skin diseases and trained complex, self-learning neural network systems to interpret those images.
The researchers found that the algorithm could diagnose 134 skin disorders, and suggest primary treatment options, render multi-class classification among disorders, and enhance the performance of medical professionals through AI.
Compared with the performance of 21 dermatologists, 26 dermatology residents, and 23 members of the general public, they said its performance was similar to that of the dermatology residents, but slightly below that of the dermatologists.
According to the study, half of the malignancies may have been missed by the general public without referral to specialists.
“Our results suggest that our algorithm may serve as an Augmented Intelligence that can empower medical professionals in diagnostic dermatology,” Na said.
“Rather than AI replacing humans, we expect AI to support humans as Augmented Intelligence to reach diagnoses faster and more accurately,” he added.
The researchers cautioned that AI cannot definitively interpret images that it is not trained to interpret even when the problem presented is straightforward.
Citing an example they said an algorithm trained only to differentiate between cancerous melanoma and pigmented skin lesions called nevi, cannot differentiate between an image of a nail hematoma and either a melanoma or a nevus.
If the shape of the hematoma is irregular, the researchers explained, the algorithm may diagnose it as melanoma.
They also added that the algorithm was trained and tested using high quality images, and its performance is generally suboptimal if the input images are of low quality.
“We anticipate that the use of our algorithm with a smartphone could encourage the public to visit specialists for cancerous lesions such as melanoma that might have been neglected otherwise,” Na said.
However, he added that there are issues with the quality or composition of photographs taken by the general public that may affect the results of the algorithm.
“If the algorithm’s performance can be reproduced in the clinical setting, it will be promising for the early detection of skin cancer with a smartphone,” Na said.
“We hope that future studies will evaluate the utility and performance of our algorithms in a clinical setting,” he added. (AGENCIE)