Why is this study being done? RET gene alterations occur in only 5-10 % of papillary thyroid cancers, but they can change how surgeons treat the disease. Gene testing is costly and not always performed, so many RET-positive tumours are missed. Researchers have built a computer program (artificial-intelligence or "AI" model) that reads routine thyroid ultrasound images and predicts whether the tumour carries a RET alteration and whether the cancer has already spread to lymph-nodes in the side of the neck.
What will happen in this study?
About 800 adults who are scheduled for thyroid-cancer surgery will take part. Each participant will:
* have a standard pre-operative ultrasound exam (no extra scanning time), * give a routine fine-needle sample for a 14-gene panel test (results in 24 h), and * allow the AI model to analyse the ultrasound images in the background. Doctors making treatment decisions will not see the AI result. After surgery, the research team will compare the AI predictions with the gene-panel result and the final pathology report.
Main goal: To find out how accurately the AI model detects RET alterations. Secondary goals: To measure the model's ability to predict lymph-node spread, and to compare costs between ultrasound-only prediction and full gene testing.
Benefits and risks: Participants will receive the current standard of care; there is no added risk beyond the usual ultrasound and needle biopsy. The study could lead to faster, less expensive ways to identify high-risk thyroid cancers in the future.
Age 18-75 years, able to provide written informed consent.
Pre-operative ultrasound findings highly suggestive of papillary thyroid carcinoma.
Planned thyroidectomy (any extent) at a participating institution.
Willing to undergo rapid 11-gene next-generation sequencing (NGS) panel and allow use of ultrasound DICOM images for AI analysis.
Prior thyroid or major neck surgery.
Known medullary thyroid carcinoma, anaplastic carcinoma, or metastatic disease outside the neck.
Multiple endocrine neoplasia (MEN) syndromes or clinical suspicion of multi-gland disease.
Pregnant or breastfeeding.
Consecutive adults with ultrasound-suspected papillary thyroid carcinoma scheduled for thyroidectomy at participating centers.
Cohort
Retrospective
AI-Ultrasound RET Prediction
Diagnostic testDeep-learning algorithm that analyses thyroid ultrasound DICOM images and outputs a probability score for RET gene alteration and lateral-neck lymph-node metastasis; run offline, results blinded to treating surgeons.
Area Under the ROC Curve (AUC) for AI-Ultrasound Detection of RET Alterations
The receiver-operating-characteristic area under the curve comparing the AI-generated probability score against the reference 14-gene next-generation sequencing (NGS) result for RET fusion or point mutation. AUC calculated with 95 % confidence interval via DeLong method.
Sensitivity and Specificity of AI-Ultrasound for Detecting RET Alterations
Using the threshold that maximized the Youden index in the development set, calculate sensitivity (true-positive rate) and specificity (true-negative rate) of the AI model versus 11-gene NGS reference for RET fusion or point mutation. Results reported with 95 % confidence intervals.
Click on the lead sponsor to view all of their trials.
Fujian Medical University
Lead sponsor
Fujian Medical University Union Hospital
Sponsor institution
This trial is not recruiting at the moment. You can still explore other options:
