Multimodal Deep Learning for Lymph Node Metastasis in Thyroid Cancer

A Multicenter Study on Developing a Multimodal Deep Learning Model Based on Color Doppler Ultrasound for Predicting Lymph Node Metastasis and Cancer Staging in Papillary Thyroid Carcinoma

Papillary thyroid carcinoma (PTC) is the most common endocrine malignancy in clinical practice, accounting for approximately 85% of all thyroid malignancies. The occurrence of cervical lymph node metastasis further increases the risk of local tumor recurrence and distant metastasis, thereby reducing patient survival rates. Pathological examinations reveal that approximately 30-80% of PTC patients have lymph node metastasis. Early detection of metastatic lymph nodes and the development of individualized treatment plans are crucial for improving patient prognosis. Currently, the primary method for diagnosing lymph node metastasis is ultrasound-guided fine-needle aspiration, but its accuracy is limited by sample quality and carries a risk of false-negative results. In recent years, deep learning technology has demonstrated significant potential in the field of medical image analysis. Therefore, the investigators aim to develop a deep learning model based on neck ultrasound to more accurately predict lymph node metastasis.

Study Overview

• Status: Not yet recruiting
• Conditions: Papillary Thyroid Carcinoma
• Intervention / Treatment: Other: not intervention

• Study Type: Observational
• Enrollment (Estimated): 3200

Contacts and Locations

• Study Contact: Name: Jianyong Lei; Phone Number: +86 19983137992; Email: leijianyong@scu.edu.cn
• Study Contact Backup: Name: Yu Feng; Email: 1350502131@qq.com

Study Locations

• China
  • Sichuan
    • Chengdu, Sichuan, China, 610041
      • West China Hospital of Sichuan University
      • Contact: Yu Feng; Phone Number: +86 15183042703; Email: 1350502131@qq.com
      • Contact: Jianyong Lei; Phone Number: +86 19983137992; Email: leijianyong@scu.edu.cn

Participation Criteria

Eligibility Criteria

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

• Sampling Method: Non-Probability Sample

Study Population

Clinical data from patients who underwent thyroidectomy at West China Hospital of Sichuan University and its affiliated branch hospitals between October 2020 and October 2025 were retrospectively collected and analyzed.

Description

Inclusion Criteria:

Cases aged 18-80 years who underwent thyroid ultrasound examination and postoperative pathological examination of the thyroid.

Cases with a first-time diagnosis of papillary thyroid carcinoma. Cases who underwent lymph node dissection

Exclusion Criteria:

Cases aged <18 years or >80 years. Cases with poor-quality ultrasound images. Cases with incompletely visualized nodules. Cases with images showing multiple distinct lesions. Cases belonging to special populations. Cases with concurrent other tumors. Cases with a history of thyroid cancer resection

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Papillary thyroid carcinoma group	Other: not intervention; This is a retrospective observational study in which participants will not undergo any interventions, and only data collection and analysis will be performed on the participants.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Area Under the Receiver Operating Characteristic Curve for a Multimodal Deep Learning Model Based on Cervical Ultrasound in Predicting Lymph Node Metastasis	The researcher will employ a multimodal deep learning model that integrates preoperative cervical color Doppler ultrasound images with corresponding structured text reports. The final output of the model is a predicted probability of lymph node metastasis for each patient (a continuous value between 0 and 1). This predicted probability will be compared with postoperative histopathological diagnosis results (the gold standard). A receiver operating characteristic curve will be plotted for the model, and its area under the curve will be calculated.This is the gold standard metric for evaluating the discriminative ability of a binary classification model (metastasis vs. non-metastasis). A higher AUC value indicates stronger overall discriminative power of the model.	Within 2 months after the completion of subject enrollment
Sensitivity of a Multimodal Deep Learning Model Based on Cervical Ultrasound for Predicting Lymph Node Metastasis	This metric aims to evaluate the ability of the constructed multimodal deep learning model to correctly identify patients with papillary thyroid carcinoma who truly have cervical lymph node metastasis, under the optimal diagnostic threshold. Researchers need to collect the number of patients diagnosed with lymph node metastasis through postoperative pathology, as well as the number of patients predicted as "positive" (i.e., predicted to have metastasis) by the model, in order to calculate the sensitivity of the cervical ultrasound-based multimodal deep learning model in predicting lymph node metastasis. Calculation formula: Sensitivity = Number of true positive patients / Total number of positive patients confirmed by postoperative pathology.	Within 2 months after the completion of subject enrollment.
Specificity of a Multimodal Deep Learning Model Based on Cervical Ultrasound for Predicting Lymph Node Metastasis	This metric aims to evaluate the ability of the constructed multimodal deep learning model to correctly rule out patients with papillary thyroid carcinoma who have not developed cervical lymph node metastasis, under the optimal diagnostic threshold. Researchers need to collect the number of patients diagnosed without lymph node metastasis via postoperative pathology, as well as the number of patients predicted by the model as "negative" (i.e., predicted to have no metastasis), in order to calculate the specificity of the cervical ultrasound-based multimodal deep learning model in predicting lymph node metastasis. Calculation formula: Specificity = Number of true negative patients / Total number of negative patients confirmed by postoperative pathology.	Within 2 months after the completion of subject enrollment.

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
The pathologically confirmed lymph node metastasis rate in the study cohort	It refers to the percentage of patients with at least one metastatic lymph node confirmed by postoperative pathological examination, relative to the total number of individuals in the corresponding study population. Researchers need to collect the number of patients diagnosed with lymph node metastasis through postoperative pathological examination.	Within 2 months after the completion of subject enrollment
Adjusted Odds Ratios for Clinical Factors Associated with Pathologically Confirmed Lymph Node Metastasis	Researchers need to collect the outcome variable (i.e., postoperatively pathologically confirmed lymph node metastasis status) and its exposure variables (such as the specific location of the primary tumor within the thyroid gland, maximum tumor diameter, patient age, etc.). Using these variables, the adjusted odds ratios are calculated to reflect, after adjusting for other confounding factors, how many times more likely patients with a specific exposure characteristic (e.g., tumor located in the upper pole) are to have lymph node metastasis compared to patients in the reference group (e.g., tumor located in the lower pole).	Within 2 months after the completion of subject enrollment
The weighted Kappa coefficient for the consistency between model-predicted pTNM stage and pathological stage	Researchers need to collect and record the model-predicted pTNM stage and the patient's true pTNM stage to evaluate the consistency between the model-predicted complete pTNM stage and the pathological stage.	Within 2 months after the completion of subject enrollment

Collaborators and Investigators

• Sponsor: West China Hospital

Study record dates

Study Major Dates

• Study Start (Estimated): January 1, 2026
• Primary Completion (Estimated): March 1, 2026
• Study Completion (Estimated): May 1, 2026

Study Registration Dates

• First Submitted: December 9, 2025
• First Submitted That Met QC Criteria: December 22, 2025
• First Posted (Actual): December 23, 2025

Study Record Updates

• Last Update Posted (Actual): December 23, 2025
• Last Update Submitted That Met QC Criteria: December 22, 2025
• Last Verified: December 1, 2025

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Endocrine System Diseases; Neoplasms by Site; Neoplasms; Neoplasms by Histologic Type; Thyroid Neoplasms; Endocrine Gland Neoplasms; Head and Neck Neoplasms; Neoplasms, Glandular and Epithelial; Adenocarcinoma; Carcinoma; Thyroid Diseases; Adenocarcinoma, Papillary; Thyroid Cancer, Papillary
• Other Study ID Numbers: 2025(2352)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED

Drug and device information, study documents

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