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
- AI Expands Across Heart Failure Care Continuum to Improve Management
- Microneedle Sensor Enables Continuous Monitoring of Drug Clearance
- 3D Brain Imaging Marker Predicts Surgical Outcomes in Dementia-Causing Hydrocephalus
- Printed Artificial Neurons Stimulate Natural Brain Circuits
- Review Advances Precision Care Pathway for Meningioma Management
- Synthetic Biology Approach Enables On-Demand Liver Tissue Growth
- Bioinspired Imaging System Identifies Cancerous Lymph Nodes Intraoperatively
- Portable AI Device Enables Low-Cost Screening for Anterior Eye Diseases
- FDA-Cleared ECG Software Powers Real-Time Cardiac Monitoring at Scale
- Collaboration Brings Continuous Monitoring to Metabolic Care Management
- Low-Frequency Wireless Sensor Monitors Arterial Stiffening and Blood Pressure
- FDA-Cleared Transseptal Access Device Enables Site-Specific Left Atrial Puncture
- AI Tool Estimates CPAP Effect on Cardiovascular Risk in Sleep Apnea
- Wearable AI Tool Predicts Hospitalization Risk in Heart Failure
- Real-Time Imaging Guides CPR to Improve Perfusion
- AI Tool Predicts Post-Therapy Barrett’s Esophagus Recurrence
Channels
Artificial Intelligence
view channel
AI Model Uses Eye Imaging to Identify Risk of Major Systemic Diseases
Early detection of systemic disease risk remains a persistent challenge in population health screening. Cardiometabolic conditions such as diabetes, heart disease, and stroke often progress without symptoms... Read more
AI Platform Interprets Real-Time Wearable Data for Parkinson’s Management
Parkinson’s disease presents fluctuating motor and non-motor symptoms that complicate day-to-day self-management and clinical decision-making. Care teams require timely, longitudinal insight into medication... Read more
Critical Care
view channel
AI Expands Across Heart Failure Care Continuum to Improve Management
Heart failure (HF) is a chronic, progressive syndrome with high morbidity and mortality that drives frequent hospital readmissions and variable responses to therapy. Persistent heterogeneity in presentation... Read more
Microneedle Sensor Enables Continuous Monitoring of Drug Clearance
Early identification of kidney and liver dysfunction is essential when dosing nephrotoxic or hepatotoxic drugs, yet clinicians often rely on intermittent blood tests that can miss evolving injury.... Read more
Surgical Techniques
view channel
Smart Fracture Implant Monitors Healing and Delivers Adaptive Support
Fracture care is hindered by a monitoring gap between fixation and the first follow-up radiograph, leaving clinicians without early, objective feedback on healing. Delayed detection of impaired union can... Read more
Novel GERD Device Demonstrates Long-Term Safety in Real-World Study
Gastroesophageal reflux disease affects over 1 billion people worldwide, and many patients ultimately require procedural management. Surgical options exist but may introduce adverse effects such as dysphagia,... Read more
Pulsed Field Ablation Technology Showcases One-Year AF Outcomes
Catheter ablation for atrial fibrillation is drawing interest in nonthermal energy modalities that aim to spare non‑cellular tissue while creating durable lesions. Pulsed field ablation techniques that... Read more
Flexible Graphene Cortical Interface Enables Real-Time Mapping During Tumor Surgery
Safe, precise functional mapping during brain tumor surgery is critical to preserving speech and movement. Conventional metal electrodes can be rigid and less sensitive, limiting their ability to conform... Read morePatient Care
view channel
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
Revolutionary Automatic IV-Line Flushing Device to Enhance Infusion Care
More than 80% of in-hospital patients receive intravenous (IV) therapy. Every dose of IV medicine delivered in a small volume (<250 mL) infusion bag should be followed by subsequent flushing to ensure... Read more
Health IT
view channel
Automated System Classifies and Tracks Cardiogenic Shock Across Hospital Settings
Cardiogenic shock remains a difficult, time-sensitive emergency, with delayed identification driving poor outcomes and persistently high mortality. Many cases go undocumented even at advanced stages, hindering... Read more
Voice-Driven AI System Enables Structured GI Procedure Documentation
Documentation during gastrointestinal (GI) procedures often competes with real-time clinical decision-making and imposes a significant cognitive burden on physicians. Manual data entry and post-procedure... Read more
EMR-Based Tool Predicts Graft Failure After Kidney Transplant
Kidney transplantation offers patients with end-stage kidney disease longer survival and better quality of life than dialysis, yet graft failure remains a major challenge. Although a successful transplant... Read more
Printable Molecule-Selective Nanoparticles Enable Mass Production of Wearable Biosensors
The future of medicine is likely to focus on the personalization of healthcare—understanding exactly what an individual requires and delivering the appropriate combination of nutrients, metabolites, and... Read morePoint of Care
view channel
Business
view channel
Johnson & Johnson Launches AI-Driven Cardiac Mapping System
Johnson & Johnson has introduced the CARTOSOUND SONATA Module for the CARTO System at the Heart Rhythm Society (HRS) 2026 meeting in Chicago. The module uses artificial intelligence with the CARTO... Read more
