Prediction of Mediastinal Station IV Lymph Node Metastasis in Non-small Cell Lung Cancer

NCT06496360 | Recruiting

• 1 other identifier: KLYY-202404-041
• Study Type: observational
• Target: 150
• Locations: 1 country
• Sites: 1

Brief Summary

Mediastinal lymph node metastasis is a common metastasis pathway of non-small cell lung cancer (NSCLC), and its occurrence is closely related to the lymphatic drainage pattern, which is different in different pulmonary lobe NSCLC, which poses a challenge for the formulation of individualized treatment strategies. Accurate staging is the prerequisite for accurate treatment of NSCLC. Computed Tomograph (CT) examination is an important tool for evaluating mediastinal lymph node metastasis, which is crucial for making treatment plan and evaluating patient prognosis. However, it is difficult to diagnose metastatic lymph nodes with insignificant imaging features. Especially metastatic lymph nodes in areas 4 and 7. Both zone 4 and zone 7 are hot spots for mediastinal lymph node metastasis. However, clinical guidelines do not make clear provisions on lymph node dissection in zone 4, which makes preoperative clinical staging and prognosis evaluation of patients with NSCLC particularly important. By integrating and analyzing a large amount of data in CT images, the newly emerging CT radiomics technology captures subtle features that may be overlooked in conventional CT scans, showing great application prospects in the accuracy of non-invasive diagnosis of lymph node metastasis. This study aims to explore the mediastinal drainage pattern and the role of CT in evaluating mediastinal lymph node metastasis, in order to provide valuable imaging evidence for accurately judging mediastinal lymph node metastasis of NSCLC, formulating appropriate lymph node dissection scope, optimizing treatment strategy, and improving patient prognosis.

Conditions

Non-small Cell Lung Cancer

Outcome Measures

Primary Outcomes (2)

• Area under the Curve(AUC)

  To evaluate the ability and clinical practicability of the model to predict lymph node metastasis

  June 2025

• Receiver operator characteristic curve(ROC)

  Sensitivity and specificity of different models under different thresholds

  June 2025

Study Arms (2)

Case

Diagnostic Test: Artificial Intelligence

Control

Diagnostic Test: Artificial Intelligence

Interventions

Artificial Intelligence DIAGNOSTIC_TEST

The model employs machine learning algorithms to analyze CT imaging data of patients with non-small cell lung cancer. It focuses on the identification and assessment of features of the mediastinal fourth group lymph nodes, including size, shape, margins, and density. By extracting features related to lymph node metastasis, the model assists doctors in making more accurate diagnoses.

Case; Control

Eligibility Criteria

• Sex: all
• Healthy Volunteers: No
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

The clinical and pathological data of newly diagnosed patients with non-small cell lung cancer admitted to cardiothoracic Surgery Department of Qilu Hospital were retrospectively collected. Inclusion criteria included patients who had undergone pathological examination of the fourth group of lymph nodes at initial visit and enhanced CT scan within two weeks prior to surgery

You may qualify if:

• Surgical resection and systematic lymph node dissection were performed in the department of thoracic surgery, and the postoperative pathological findings were confirmed as NSCLC and complete pathological diagnostic data were retained.
• Chest CT enhancement scan was completed within 2 weeks prior to surgery
• Image quality meets analysis standards and clinical data is complete.
• Lymph nodes that were pathologically confirmed to be metastatic or non-metastatic at station 4 were selected

You may not qualify if:

• Preoperative chemoradiotherapy or other treatment
• Distant metastasis or other malignant tumors are present
• Incomplete clinical data or image artifacts
• No metastatic or non-metastatic lymph nodes were found at station 4

Sponsors & Collaborators

• Qilu Hospital of Shandong University: lead

Study Sites (1)

Qilu Hospital of Shandong University

Jinan, Shandong, 250063, China

RECRUITING

Related Publications (7)

• Siegel RL, Miller KD, Wagle NS, Jemal A. Cancer statistics, 2023. CA Cancer J Clin. 2023 Jan;73(1):17-48. doi: 10.3322/caac.21763.

  PMID: 36633525 BACKGROUND

• Takano N, Ariyasu R, Koyama J, Sonoda T, Saiki M, Kawashima Y, Oguri T, Hisakane K, Uchibori K, Nishikawa S, Kitazono S, Yanagitani N, Ohyanagi F, Horiike A, Gemma A, Nishio M. Improvement in the survival of patients with stage IV non-small-cell lung cancer: Experience in a single institutional 1995-2017. Lung Cancer. 2019 May;131:69-77. doi: 10.1016/j.lungcan.2019.03.008. Epub 2019 Mar 21.

  PMID: 31027701 BACKGROUND

• Zhou D, Yue D, Zhang Z, Tian P, Feng Y, Liu Z, Zhang B, Wang M, Zhao X, Wang C. Prognostic significance of 4R lymph node dissection in patients with right primary non-small cell lung cancer. World J Surg Oncol. 2022 Jul 1;20(1):222. doi: 10.1186/s12957-022-02689-w.

  PMID: 35778770 BACKGROUND

• Shamji FM, Beauchamp G, Sekhon HJS. The Lymphatic Spread of Lung Cancer: An Investigation of the Anatomy of the Lymphatic Drainage of the Lungs and Preoperative Mediastinal Staging. Thorac Surg Clin. 2021 Nov;31(4):429-440. doi: 10.1016/j.thorsurg.2021.07.005.

  PMID: 34696855 BACKGROUND

• Hanaoka J, Yoden M, Okamoto K, Kaku R, Ohshio Y. Mediastinal lymph node evaluation, especially at station 4L, in left upper lobe lung cancer. J Thorac Dis. 2022 Sep;14(9):3321-3334. doi: 10.21037/jtd-22-537.

  PMID: 36245624 BACKGROUND

• Mascalchi M, Zompatori M. Mediastinal Lymphadenopathy in Lung Cancer Screening: A Red Flag. Radiology. 2022 Mar;302(3):695-696. doi: 10.1148/radiol.212501. Epub 2021 Nov 23. No abstract available.

  PMID: 34812678 BACKGROUND

• Yoshida Y, Saeki N, Yotsukura M, Nakagawa K, Watanabe H, Yatabe Y, Watanabe SI. Visualization of patterns of lymph node metastases in non-small cell lung cancer using network analysis. JTCVS Open. 2022 Oct 13;12:410-425. doi: 10.1016/j.xjon.2022.10.003. eCollection 2022 Dec.

  PMID: 36590713 BACKGROUND

MeSH Terms

Conditions

Carcinoma, Non-Small-Cell Lung

Interventions

Artificial Intelligence

Condition Hierarchy (Ancestors)

Carcinoma, Bronchogenic; Bronchial Neoplasms; Lung Neoplasms; Respiratory Tract Neoplasms; Thoracic Neoplasms; Neoplasms by Site; Neoplasms; Lung Diseases; Respiratory Tract Diseases

Intervention Hierarchy (Ancestors)

Algorithms; Mathematical Concepts

Central Study Contacts

Yanru Kang, postgraduate

CONTACT

18334864091; 2083884573@qq.com

Study Design

• Study Type: observational
• Observational Model: OTHER
• Time Perspective: CROSS SECTIONAL
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: June 12, 2024
• First Posted: July 11, 2024
• Study Start: August 1, 2024
• Primary Completion: November 1, 2024
• Study Completion: June 1, 2025
• Last Updated: August 7, 2024

Record last verified: 2024-04

Data Sharing

• IPD Sharing: Will not share

Locations

CN (1)