NOV 12, 2021 10:00 AM PST

Available Data for Cancer-Diagnosing AI Lacking Diverse Imagery

WRITTEN BY: Ryan Vingum

The use of artificial intelligence to diagnose and monitor health conditions is on the rise. At its most basic level, AI uses outside data from which to learn and make predictions about particular problems and scenarios. The better the dataset, the more AI can learn, allowing for more precise predictions.

In healthcare and medicine, AI has been applied in a number of contexts: it’s been used to make predictions about which drugs will be successful in clinical trials; it’s also been used to generate clinically valid and effective treatment plans. Overall, research suggests that AI can perform at least as well, if not better, than humans when it comes to making decisions about diagnosis and treatment.

This same technology has been applied to the detection of cancer, with significant success. When it comes to skin cancer, however, researchers suggest that there is a serious lack of diversity in the data AI uses to make diagnostic decisions. Specifically, there is a lack of diversity in the datasets of skin cancer patient imagery used to “teach” AI programs.

In a new study published in Lancet Digital Health, researchers reviewed all the freely available data sets of skin lesion images, analyzing over 100,000 pictures. Researchers found that much of the data available in these sets was lacking important contextual details. For example, only 2 of 21 sets of images included images taken with a dermatoscope, a specialized tool used to take pictures of skin lesions that could be cancerous.  

The most interesting finding was around ethnic information contained in the images. Among pictures that had skin color noted, only 11 out of 2,436 were images of brown or dark skin, raising red flags for researchers. 

Dr. David Wen, the study’s lead author, noted that in “the majority of datasets, lots of important information about the images and patients in these datasets wasn't reported. There was limited information on who, how and why the images were taken. This has implications for the programs developed from these images, due to uncertainty around how they may perform in different groups of people, especially in those who aren't well represented in datasets, such as those with darker skin. This can potentially lead to the exclusion or even harm of these groups from AI technologies.” 

AI is only as good as the data it has available to it—without a diversity of patient imagery to help diagnose skin cancer in a wide range of patients, AI’s real-world applications are limited. 

Sources: Science Daily; The Lancet Digital Health; Future Healthcare Journal 

About the Author
  • Science writer and editor, with a focus on simplifying complex information about health, medicine, technology, and clinical drug development for a general audience.
You May Also Like
NOV 09, 2021
Clinical & Molecular DX
Device Scavenges Body Heat, Allows Crowds to Gather Safely
NOV 09, 2021
Device Scavenges Body Heat, Allows Crowds to Gather Safely
If efforts to maintain public safety amidst the ongoing pandemic have taught us one thing, it’s that we need bette ...
NOV 11, 2021
Technology
Chatty Chatbots Learn to Cope with Figurative Language
NOV 11, 2021
Chatty Chatbots Learn to Cope with Figurative Language
Researchers investigate methods to improve dialogue system engagement with natural language
DEC 08, 2021
Clinical & Molecular DX
Scaling Down to Go Big: An Overview of the Lab-on-a-Chip
DEC 08, 2021
Scaling Down to Go Big: An Overview of the Lab-on-a-Chip
By Julianne Davis - Technical Writer and Support Scientist at Biotium The Rise of the Lab-on-a-Chip With the advent of m ...
DEC 01, 2021
Space & Astronomy
The Two Closest Supermassive Black Holes
DEC 01, 2021
The Two Closest Supermassive Black Holes
A team of international researchers have observed the center of galaxy NGC 7727 and found two supermassive black holes ( ...
DEC 06, 2021
Technology
Solar-Powered Robots That Could Clean Up Oil Spills
DEC 06, 2021
Solar-Powered Robots That Could Clean Up Oil Spills
Oil spills at sea can be a devastating consequence of offshore drilling for fossil fuels. They can affect local plants a ...
DEC 27, 2021
Cancer
Improving Immunotherapy with a Novel Nanoparticle
DEC 27, 2021
Improving Immunotherapy with a Novel Nanoparticle
Malignant pleural effusion (MPE) occurs in cancer patients experiencing a buildup of fluid and tumor cells in the pleura ...
Loading Comments...