CT and Endoscopic Biopsy Image-Based Deep Learning for Predicting Left Recurrent Laryngeal Nerve Lymph Node Metastasis in Esophageal Cancer

N/AActive Not RecruitingNCT07074535

Daping Hospital and the Research Institute of Surgery of the Third Military Medical University500 enrolled

Overview

The goal of this observational study is to develop a predictive model for left recurrent laryngeal nerve (RLN) lymph node metastasis using deep learning algorithms. The model will be developed using clinical data from previous esophageal cancer surgeries, including preoperative CT imaging, and histopathological images from gastroscopic biopsies. The model will also be validated through prospective clinical trials to guide the intraoperative lymph node dissection, thereby reducing postoperative risks of RLN injury.

Study Type

OBSERVATIONAL

Enrollment

500

Conditions

Esophageal Squamous Cell Cancer (SCC)Recurrent Laryngeal Nerve Palsy Deep Learning Postoperative Complication

Eligibility

Sex: ALLMin age: 18 YearsMax age: 80 Years

Medical Language ↔ Plain English

Inclusion Criteria: * Preoperative gastroscopic biopsy confirmed esophageal squamous cell carcinoma； * The patient underwent esophagectomy with lymph nodes dissection along the left recurrent laryngeal nerve. Exclusion Criteria: * The patient's medical records are incomplete； * The patient refused to participate in the trial.

Outcomes

Primary Outcomes

AUROC (Area Under the Receiver Operating Characteristic Curve)

The discriminant ability of the comprehensive evaluation model at different thresholds (positive vs. negative)

Time frame: From enrollment to the end of treatment at 4 weeks