AI Identifies Noncancerous Thyroid Nodules on Ultrasound Images and Reduces Biopsies
|
By HospiMedica International staff writers Posted on 13 Jun 2022 |
|
Thyroid nodules are very common. Fine needle aspiration biopsy is used to diagnose thyroid cancer. However most biopsies produce benign (non-cancerous) results and are potentially avoidable. Now, a new study has found that artificial intelligence (AI) can be used to identify thyroid nodules seen on thyroid ultrasound that are very unlikely to be cancerous, reducing a large number of unnecessary biopsies.
In the new study, researchers at the University of Colorado Anschutz Medical Campus (Aurora, CO, USA) used machine learning, a type of AI, to analyze ultrasound images of thyroid nodules. Machine learning is the process of using mathematical models of data to help a computer learn without direct instruction. 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 to not miss cancer) of 97%, and a specificity (ability to correctly identify a 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,” said study lead researcher Nikita Pozdeyev, M.D., Ph.D., of the University of Colorado Anschutz Medical Campus.
“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.
“We demonstrated that using AI analysis of ultrasound images to rule out thyroid cancer and avoid biopsy is definitely possible,” he said. “This technology could assist radiologists and endocrinologists in choosing which thyroid nodules should undergo biopsy, especially those in the community who may not review a large number of thyroid ultrasound images.”
Related Links:
University of Colorado Anschutz Medical Campus
Latest Critical Care News
- Sweat-Sensing Fingertip Patch Continuously Tracks Parkinson’s Medication Levels
- Postoperative Treatment Windows Enable Targeted Glioblastoma Therapy
- New Medical Masks and Gowns Support Protection Across Care Settings
- FDA Clears Software for Objective Assessment of Cognitive Function
- Stretchable Antenna Enables Reliable Wearable ECG Monitoring During Motion
- FDA Clears Noninvasive Test for Elevated Pulmonary Capillary Wedge Pressure
- FDA-Cleared Index Enables Pediatric-Specific Sedation Monitoring
- Smart Ring Continuously Monitors Glucose and Ketones from Passive Sweat
- Invisible Skin Sensors Could Transform Everyday Biosignal Monitoring
- Patient-Specific Artery-on-a-Chip Refines Stroke Risk Stratification
- Existing Cardiovascular Risk Calculators Predict Several Common Cancers
- New Neurovascular Guidewire Enhances Access and Control in Stroke Thrombectomy
- AI Tool Automates EEG Analysis and Flags Clinically Relevant Abnormalities
- New Risk Models Improve Sudden Cardiac Arrest Prediction
- Low-Cost Antiseptic Regimen Reduces Bacteria Linked to Newborn Infections
- Collaborative ICU Admission Process Cuts Time to Critical Care Involvement by Half
Channels
Artificial Intelligence
view channel
AI-Powered Brain-Body Interface Supports Movement and Sensation Recovery
Neurological injuries such as stroke and spinal cord trauma frequently leave patients with profound motor and sensory deficits that limit independence. Rehabilitation may restore some movement, but recovery... Read more
New AI Tool Identifies Support Needs in Spinal Cord Stimulation
Chronic pain patients implanted with spinal cord stimulation systems often need timely therapy adjustments and education between clinic visits. Detecting subtle changes in behavior or device use that precede... Read more
Critical Care
view channel
Sweat-Sensing Fingertip Patch Continuously Tracks Parkinson’s Medication Levels
Parkinson’s disease is a progressive neurodegenerative disorder that disrupts motor control and daily functioning. Clinicians rely on levodopa to manage symptoms, yet dosing is difficult as therapeutic... Read more
Postoperative Treatment Windows Enable Targeted Glioblastoma Therapy
Glioblastoma, an aggressive primary brain cancer in adults, almost always recurs after surgery because residual cells infiltrate surrounding brain tissue. Postoperative chemoradiotherapy typically begins... Read more
![Image: Researchers demonstrated a soft, printable hydrogel electrode that conforms to the skin while recording physiological signals. The material maintained close contact during movement and under wet conditions, offering a potential platform for future wearable health-monitoring technologies (Photo courtesy of Huanyu \](https://globetechcdn.com/mobile_hospimedica/images/stories/articles/article_images/2026-07-29/image294812238_1.jpg "Image: Researchers demonstrated a soft, printable hydrogel electrode that conforms to the skin while recording physiological signals. The material maintained close contact during movement and under wet conditions, offering a potential platform for future wearable health-monitoring technologies (Photo courtesy of Huanyu \")
Surgical Techniques
view channel
New AR Technology Provides Real-Time Guidance During ACL Surgery
Precision during arthroscopic procedures is critical, yet intra-articular orientation can be challenging, and technical errors may compromise outcomes. In anterior cruciate ligament reconstruction, tunnel... Read more
New Technique Rapidly Produces Patient-Specific Vascular Grafts During Surgery
Trauma and vascular disease often demand rapid reconstruction of damaged blood vessels to restore perfusion and prevent limb loss or death. Small-diameter conduits remain a major bottleneck because suitable... Read more
Patient Care
view channel
AI Avatar Doctor Improves Patient Understanding Before Radiotherapy
Radiation oncology consultations require patients to grasp complex concepts quickly, yet anxiety and information overload often undermine understanding and informed consent. Poor comprehension can also... Read more
Wearable Sleep Data Predict Adherence to Pulmonary Rehabilitation
Chronic obstructive pulmonary disease (COPD) is a long-term lung disorder that makes breathing difficult and often disturbs sleep, reducing energy for daily activities. Limited engagement in pulmonary... Read more
Health IT
view channel
New Cloud Platform Streamlines Capsule Endoscopy Workflow and Reporting
Capsule endoscopy programs depend on coordinated acquisition, review, and reporting to support gastrointestinal services. Managing these activities across practices and health systems requires reliable... Read more
Smartwatch Monitoring Identifies Abnormal Vital Signs Before Routine Checks
Post-surgical inpatients often undergo frequent vital signs checks that interrupt rest and require substantial nursing time. Intermittent manual observations can also delay recognition of early physiological... Read more
Point of Care
view channel
New Brain Ultrasound Platform Enables Bedside Postoperative Imaging
Transporting postoperative patients for CT or MRI can create operational burdens, delays, and disruptions in care. Bedside visualization may help reduce transport demands, lower radiation exposure, and... Read more
Handheld Ultrasound Expands Point-of-Care Imaging Access in Brazil
Rapid access to diagnostic imaging is essential across hospitals, emergency departments, clinics, and municipal health systems, but large markets still face uneven availability, particularly in rural regions.... Read more
Business
view channel
AI Care Platform Adds Quantitative MRI Analysis for Multiple Sclerosis
Neurodegenerative diseases such as multiple sclerosis require timely identification and coordinated, long-term management. As health systems seek consistent decision-making at scale, quantitative neuroimaging... Read more
