MedPath

Clinical Application of AI-assisted Ultrasound Technology in the Preoperative Evaluation of Thyroid Cancer

Not Applicable
Not yet recruiting
Conditions
Thyroid Cancer
Interventions
Diagnostic Test: Supplementary Pathological Examination
Other: No Need for Supplementary Pathological Examination
Registration Number
NCT06498674
Lead Sponsor
Fujian Medical University
Brief Summary

This study aims to explore the application of AI-assisted ultrasound technology in the preoperative assessment of thyroid cancer. Traditional ultrasound examination data from thyroid cancer patients will be collected, and AI systems will be utilized to detect and diagnose thyroid nodules and lymph nodes. In cases where there is disagreement between the two-dimensional ultrasound and AI system results, further confirmation will be sought through biopsy. Subsequently, pathological results will serve as the "gold standard" for comparison between the AI system and traditional ultrasound examination results, assessing their accuracy and reliability. Through this research endeavor, a more accurate and reliable method for preoperative assessment of thyroid cancer is aspired to be offered, thereby supporting clinical decision-making and paving the way for novel applications of AI in the field of medical imaging diagnosis.

Detailed Description

This study aims to investigate the application of AI-assisted ultrasound technology in the preoperative assessment of thyroid cancer. Traditional ultrasound examination data from patients with thyroid cancer, including two-dimensional ultrasound images, color Doppler flow images, and detailed characteristics of thyroid nodules and lymph nodes such as number, size, morphology, echogenicity, margins, calcifications, and aspect ratio, will be collected. Prior to surgery, a reassessment will be conducted using AI-assisted ultrasound technology, and the detection and diagnostic results of thyroid nodules and lymph nodes by the AI system will be recorded. In cases where there is discrepancy between the results of two-dimensional ultrasound and the AI system, fine needle aspiration biopsy or intraoperative biopsy will be performed for further confirmation of their nature. Post-surgery, the pathological results of each nodule will serve as the "gold standard" for comparative analysis between the AI system and traditional two-dimensional ultrasound examinations. The accuracy of the AI system in detecting and localizing nodules will be analyzed, and its sensitivity, specificity, and accuracy will be calculated to evaluate its diagnostic efficacy and reliability in the preoperative assessment of thyroid cancer. Through this research, a more accurate and reliable adjunctive diagnostic method for the preoperative assessment of thyroid cancer is aimed to be provided to assist clinical decision-making. Additionally, new avenues and directions for the application of AI in the field of medical imaging diagnosis will be explored.

Recruitment & Eligibility

Status
NOT_YET_RECRUITING
Sex
All
Target Recruitment
300
Inclusion Criteria
  • Patients with preoperative pathological confirmation of thyroid malignant tumors undergoing surgical treatment.
  • Patients with benign thyroid tumors, such as thyroid adenomas causing compressive symptoms, undergoing surgical treatment.
  • Patients with complete and high-quality traditional two-dimensional color ultrasound images.
  • Complete postoperative pathology reports.
  • Willingness to participate in this clinical trial and signing of informed consent.
Exclusion Criteria
  • Patients with a history of neck surgery or radiotherapy.
  • Patients with a history of malignant tumors in other parts of the body.
  • Patients with thyroid dysfunction.
  • Incomplete or poor-quality traditional two-dimensional color ultrasound images.
  • Incomplete postoperative pathology reports.
  • Refusal to participate in this clinical trial.

Study & Design

Study Type
INTERVENTIONAL
Study Design
SINGLE_GROUP
Arm && Interventions
GroupInterventionDescription
Discordant GroupSupplementary Pathological ExaminationPatients in whom the detection and diagnostic results of thyroid nodules and lymph nodes differ between traditional two-dimensional ultrasound and AI-assisted ultrasound.
Concordant GroupNo Need for Supplementary Pathological ExaminationPatients in whom the detection and diagnostic results of thyroid nodules and lymph nodes are consistent between traditional two-dimensional ultrasound and AI-assisted ultrasound.
Primary Outcome Measures
NameTimeMethod
Change in Treatment DecisionOne day after surgery

For patients who have completed traditional two-dimensional color ultrasound, AI-assisted ultrasound, and undergone supplementary pathological examination, record whether there was a change in the surgical approach or scope.

Supplementary Pathological ExaminationOne day after surgery

For patients who have completed traditional two-dimensional color ultrasound and AI-assisted ultrasound, record whether a supplementary pathological examination was conducted.

Secondary Outcome Measures
NameTimeMethod
Statistical Indicator positive predictive valueOne day after the postoperative pathology report is released

Using pathological evidence as the gold standard positive predictive value

AI-Assisted Ultrasound Interpretation ResultsPreoperative

Record ultrasound image features such as number, size, morphology, echogenicity, margins, calcifications, and TI-RADS score of thyroid nodules and lymph nodes under AI-assisted ultrasound.

Statistical Indicator missed diagnosis rate.One day after the postoperative pathology report is released

Using pathological evidence as the gold standard, construct contingency tables for both preoperative traditional two-dimensional color ultrasound and AI-assisted ultrasound, missed diagnosis rate.

Supplementary Pathological Examination ResultsOne day Postoperative

For patients who underwent supplementary pathological examination, record the results of their pathological examination.

Statistical Indicator Youden indexOne day after the postoperative pathology report is released

Using pathological evidence as the gold standard Youden index.

Traditional Two-Dimensional Color Ultrasound FindingsPreoperative

Record ultrasound image features such as number, size, morphology, echogenicity, margins, calcifications, and TI-RADS score of thyroid nodules and lymph nodes under traditional two-dimensional color ultrasound.

Postoperative Pathology ReportOne day after the postoperative pathology report is released

Record the presence of thyroid lesions and lymph node metastasis in the postoperative pathology report.

Statistical IndicatorsOne day after the postoperative pathology report is released

Using pathological evidence as the gold standard, construct contingency tables for both preoperative traditional two-dimensional color ultrasound and AI-assisted ultrasound, calculate sensitivity, specificity

Trial Locations

Locations (1)

Fujian Medical University Union Hospital

🇨🇳

Fuzhou, Fujian, China

© Copyright 2025. All Rights Reserved by MedPath