Automated Triage of Thyroid Cancer

73-year-old man with papillary carcinoma of left lobe of thyroid. Screen shot shows example of thyroid nodule annotation (segmentation and TI-RADS annotation) performed on ultrasound image in longitudinal projection with electronic Physician Annotation Device software (Stanford Medicine Radiology). Radiologists performed nodule segmentation by selecting points (red) on nodule outline (green), while controlling smoothing of outline polygon by means of spline interpolation.


January 30, 2020 — According to an article published ahead-of-print in the April issue of the American Journal of Roentgenology (AJR), a Stanford University team has developed a quantitative framework able to sonographically differentiate between benign and malignant thyroid nodules at a level comparable to that of expert radiologists, which may prove useful for establishing a fully automated system of thyroid nodule triage.

Alfiia Galimzianova et al. retrospectively collected ultrasound images of 92 biopsy-confirmed nodules, which were annotated by two expert radiologists using the American College of Radiology’s Thyroid Imaging Reporting and Data System (TI-RADS).

In the researchers’ framework, nodule features of echogenicity, texture, edge sharpness, and margin curvature properties were analyzed in a regularized logistic regression model to predict nodule malignancy. Authenticating their method with leave-one-out cross-validation, the Stanford team used ROC AUC, sensitivity, and specificity to compare the framework’s results with those obtained by six expert annotation-based classifiers.

The AUC of the proposed framework measured 0.828 (95% CI, 0.715–0.942) — "greater than or comparable,” Galimzianova noted, “to that of the expert classifiers”—whose AUC values ranged from 0.299 to 0.829 (p = 0.99).

Additionally, in a curative strategy at sensitivity of 1, use of the framework could have avoided biopsy in 20 of 46 benign nodules — statistically significantly higher than three expert classifiers. In a conservative strategy at specificity of 1, the framework could have helped to identify 10 of 46 malignancies — statistically significantly higher than five expert classifiers.  

“Our results confirm the ultimate feasibility of computer-aided diagnostic systems for thyroid cancer risk estimation,” concluded Galimzianova. “Such systems could provide second-opinion malignancy risk estimation to clinicians and ultimately help decrease the number of unnecessary biopsies and surgical procedures.”

For more information: www.arrs.org


Related Content

News | Radiology Business

May 29, 2024 — Strategic Radiology added a third California member to the nation’s leading coalition of independent ...

Time May 29, 2024
arrow
News | Lung Imaging

May 24, 2024 — Smokers who have small abnormalities on their CT scans that grow over time have a greater likelihood of ...

Time May 24, 2024
arrow
News | Radiation Therapy

May 23, 2024 — RaySearch Laboratories AB and C-RAD announced a collaboration agreement, aiming at jointly developing ...

Time May 23, 2024
arrow
News | Artificial Intelligence

May 22, 2024 — Lunit, a leading provider of AI-powered solutions for cancer diagnostics and therapeutics, recently ...

Time May 22, 2024
arrow
News | Artificial Intelligence

May 21, 2024 — According to a newly-published study of nearly 5,000 screening mammograms interpreted by an FDA-approved ...

Time May 21, 2024
arrow
News | Oncology Information Management Systems (OIMS)

May 21, 2024 — RaySearch Laboratories AB announced that the oncology information system RayCare* 2024A has been ...

Time May 21, 2024
arrow
News | Proton Therapy

May 21, 2024 — IBA, a world leader in particle accelerator technology, announced that it has signed a contract with the ...

Time May 21, 2024
arrow
News | Point-of-Care Ultrasound (POCUS)

May 20, 2024 — Exo (pronounced “echo”), a medical imaging software and devices company, announced the release of Exo ...

Time May 20, 2024
arrow
News | Radiology Business

May 20, 2024 — Associated Medical Professionals of NY (A.M.P.) announced that internationally recognized radiation ...

Time May 20, 2024
arrow
News | ASTRO

May 17, 2024 — Registration opens today for the American Society for Radiation Oncology's (ASTRO) 66th Annual Meeting ...

Time May 17, 2024
arrow
Subscribe Now