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

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.

Study Overview

• Status: Recruiting
• Conditions: Thyroid Cancer
• Intervention / Treatment: Other: No Need for Supplementary Pathological Examination; Diagnostic test: Supplementary Pathological Examination

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.

• Study Type: Interventional
• Enrollment (Estimated): 300
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Bo Wang Professor; Phone Number: 13959123550; Email: wangbo@fjmu.edu.cn

Study Locations

• China
  • Fujian
    • Fuzhou, Fujian, China, 350001
      • Recruiting
      • Fujian Medical University Union Hospital
      • Contact: Bo Wang Professor; Phone Number: +13959123550; Email: wangbo@fjmu.edu.cn

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: No

Description

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 Plan

How is the study designed?

Design Details

• Primary Purpose: Diagnostic
• Allocation: Randomized
• Interventional Model: Single Group Assignment
• Masking: None (Open Label)

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Other: Concordant Group; Patients in whom the detection and diagnostic results of thyroid nodules and lymph nodes are consistent between traditional two-dimensional ultrasound and AI-assisted ultrasound.	Other: No Need for Supplementary Pathological Examination; For the same thyroid nodule, if there is discordance between the interpretations of AI-assisted ultrasound and traditional two-dimensional ultrasound, there is no need for supplementary fine needle aspiration biopsy or intraoperative biopsy.
Other: Discordant Group; Patients in whom the detection and diagnostic results of thyroid nodules and lymph nodes differ between traditional two-dimensional ultrasound and AI-assisted ultrasound.	Diagnostic test: Supplementary Pathological Examination; For the same thyroid nodule, if there is discordance between the interpretations of AI-assisted ultrasound and traditional two-dimensional ultrasound, supplementary fine needle aspiration biopsy or intraoperative biopsy will be performed to clarify the nature of the nodule.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Supplementary Pathological Examination	For patients who have completed traditional two-dimensional color ultrasound and AI-assisted ultrasound, record whether a supplementary pathological examination was conducted.	One day after surgery
Change in Treatment Decision	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.	One day after surgery

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Traditional Two-Dimensional Color Ultrasound Findings	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.	Preoperative
AI-Assisted Ultrasound Interpretation Results	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.	Preoperative
Supplementary Pathological Examination Results	For patients who underwent supplementary pathological examination, record the results of their pathological examination.	One day Postoperative
Postoperative Pathology Report	Record the presence of thyroid lesions and lymph node metastasis in the postoperative pathology report.	One day after the postoperative pathology report is released
Statistical Indicators	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	One day after the postoperative pathology report is released
Statistical Indicator missed diagnosis rate.	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.	One day after the postoperative pathology report is released
Statistical Indicator positive predictive value	Using pathological evidence as the gold standard positive predictive value	One day after the postoperative pathology report is released
Statistical Indicator Youden index	Using pathological evidence as the gold standard Youden index.	One day after the postoperative pathology report is released

Collaborators and Investigators

• Sponsor: Fujian Medical University

Study record dates

Study Major Dates

• Study Start (Actual): July 1, 2024
• Primary Completion (Estimated): June 30, 2025
• Study Completion (Estimated): June 30, 2025

Study Registration Dates

• First Submitted: June 9, 2024
• First Submitted That Met QC Criteria: July 11, 2024
• First Posted (Actual): July 12, 2024

Study Record Updates

• Last Update Posted (Actual): September 26, 2024
• Last Update Submitted That Met QC Criteria: September 24, 2024
• Last Verified: September 1, 2024

More Information

Terms related to this study

• Keywords: Ultrasound; Artificial Intelligence; Thyroid Cancer; Preoperative Assessment
• Additional Relevant MeSH Terms: Neoplasms; Neoplasms by Site; Endocrine System Diseases; Endocrine Gland Neoplasms; Head and Neck Neoplasms; Thyroid Diseases; Thyroid Neoplasms
• Other Study ID Numbers: AI-base PCD

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No