Join the club for FREE to access the whole archive and other member benefits.

Image-based prediction of skin cancer clinical management decisions by AI

Deep learning could improve diagnosis of non-white skin lesions if trained correctly

15-Aug-2021

Key points from article :

There is a persistent disconnect between the diagnosis of what a skin disease is and how it is managed.

Researchers found new artificial intelligence (AI) tool that could act as a second opinion for dermatologists.

When considering the best course of action for following up on potentially cancerous skin spots.

Predicts appropriate clinical management steps based on an image of a diseased area of skin.

Tool looks at an image of skin then recommends either a clinical follow-up, immediate excision, or no action.

They designed a software program using publicly available datasets with images of diseased skin.

AI model was able to sort images based on relevant clinical features and predict the clinical management.

Allowed the tool to assess 100 skin photos, then compared the model’s outputs.

Model had better agreement with the aggregated recommendations.

Prioritize clinical management over diagnosis would be invaluable to BIPOC people.

Needs training with non-white samples to be effective in the populations that need it most.

Research by Simon Fraser University published in Scientific reports.

Mentioned in this article:

Click on resource name for more details.

Kumar Abhishek

PhD student in the School of Computing Science at Simon Fraser University

Scientific Reports

Scientific Journal providing information from all areas of the natural sciences

Simon Fraser University (SFU)

Public research university.

Topics mentioned on this page:
AI in Healthcare, Cancer