Artificial intelligence (AI) pinpoints thyroid nodules noticed on thyroid ultrasound that are unlikely to be cancerous. The technology reduces a large number of unnecessary biopsies.
Thyroid nodules are widespread. Fine needle aspiration biopsy is used to diagnose thyroid cancer. However, most biopsies produce benign (noncancerous) results and are potentially avoidable, according to study lead researcher Nikita Pozdeyev, M.D., Ph.D., of the University of Colorado Anschutz Medical Campus in Aurora, Colo.
‘Researchers demonstrated that using AI analysis of ultrasound images to rule out thyroid cancer and avoid biopsy is possible.’
In the new study, researchers used machine learning, a type of AI, to analyze ultrasound images of thyroid nodules. Machine learning is using mathematical data models to help a computer learn without direct instruction.
AI Platform Identifies Thyroid Cancer
More than 30,000 images from 621 thyroid nodules were used to train the machine-learning model that classifies thyroid nodules as “cancer” or “no cancer.” The model was tested on a different set of 145 nodules collected at another healthcare system.
The AI-based model achieved a sensitivity (ability not to miss cancer) of 97%, and a specificity (ability to correctly identify cancer) of 61%.
“This study demonstrates that the ultrasound-based AI classifier of thyroid nodules achieves sensitivity comparable to that of thyroid biopsy with fine-needle aspiration,” Pozdeyev said.
Advertisement
“We believe this is a good next step to improving patient care and avoiding unnecessary procedures,” he said. He noted that prospective clinical trials are needed before this tool can be accepted as a standard of care.
“This technology could assist radiologists and endocrinologists in choosing which thyroid nodules should undergo biopsy, especially those in the community who may not review many thyroid ultrasound images.”
Source: Eurekalert
Advertisement
