Podiatry interventions

Written By Heidi Tretheway

How Cognition’s AI platform can help identify nail diseases and healthy nails

Challenge

The dermatology department of a leading hospital wanted a tool that was able to differentiate between healthy and unhealthy nails to automatically and quickly assess whether a patient needed to make an appointment with the dermatologist. The tool also needed to identify three nail diseases: melanonychia, dystrophy and onychomycosis.

Solution

Cognition’s computer vision platform, Sigma Vision, can recognize patterns with extremely high accuracy, making it ideal for this use case. The dermatology clinic had a large database of annotated nail images, healthy and unhealthy, giving Cognition the data necessary to develop a solution customized to the task: detecting and identifying nail diseases quickly and easily. 

Cognition’s team preprocessed the images to reduce variability and optimize the result of the machine learning process, fine-tuning the technology parameters for this type of images. They also developed a user interface to visualize the results in a way that the dermatologist could rapidly confirm the diagnosis of the disease.

Results

The resulting solution was able to identify healthy nails with an accuracy of 95%, and to detect and identify the three nail diseases with the following accuracies:

  • Onychomicosis: 83%

  • Dystrophy: 88%

  • Melanonychia: 94%.

Heidi Tretheway https://www.dearcmo.com
Next

Early cancer detection