Using deep learning to identify tumor origins from lymph node samples

A Multicenter Study on Predicting Tumor Origin Based on Deep Learning of Lymph Node Puncture Cytology

This study is trying to see if a new computer program can help find out where tumors that spread to lymph nodes come from, and how it compares to the work of human doctors.

Quick facts

• Study type: Observational
• Enrollment: 10000 (estimated)
• Sex: All
• Sponsor: West China Hospital (other)
• Locations: 1 site (Chengdu, Sichuan)
• Trial ID: NCT06810349 on ClinicalTrials.gov

What this trial studies

This study aims to develop a deep learning model that analyzes cytological images from lymph node punctures to predict the origins of tumors that have metastasized to lymph nodes. The model will be constructed using data collected from patients at West China Hospital and will be validated with a large test set to assess its performance. Additionally, the study will compare the accuracy of the deep learning model against human pathologists in diagnosing these cytology smears.

Who should consider this trial

Good fit: Ideal candidates for this study are patients with lymph node metastases and unknown primary tumor origins who have provided relevant clinical data.

Not a fit: Patients with known primary tumor origins or those not undergoing lymph node puncture procedures may not benefit from this study.

Why it matters

Potential benefit: If successful, this approach could lead to more accurate and timely identification of tumor origins, improving treatment decisions for patients with unknown primary tumors.

How similar studies have performed: While the use of deep learning in medical diagnostics is gaining traction, this specific application in predicting tumor origins from lymph node cytology is relatively novel and has not been extensively tested.

Eligibility criteria

Inclusion Criteria:

* From West China Hospital of Sichuan University (October 1, 2008-August 31, 2024) with corresponding clinical data, including age, sex, specimen puncture site, pathologic diagnosis, pathologic type, whether immunocytochemistry was added, clinical diagnosis, lesion site, co-morbidities, history of malignancy, treatment modality, occurrence of postoperative complications, total number of days of hospitalization postoperatively, and survival time;
* From the Department of Pathology of the First Affiliated Hospital of Zhengzhou University, the Sichuan Provincial Cancer Hospital, and the Cancer Hospital of the Chinese Academy of Medical Sciences (January 1, 2020-August 31, 2024) with corresponding clinical data, including age, sex, specimen puncture site, pathologic diagnosis, pathologic type, whether immunocytochemistry was added, clinical diagnosis, lesion site, co-morbidities, history of malignancy, treatment modality, occurrence of postoperative complications, total number of days of hospitalization postoperatively, and survival time.

Exclusion Criteria:

* Images lacking any supporting clinical or pathologic evidence to support a primary origin and its corresponding clinical information;
* Blank, poorly focused, and low-quality images containing severe artifacts and their corresponding clinical information.

Where this trial is running

Chengdu, Sichuan

• West China Hospital of Sichuan University — Chengdu, Sichuan, China (RECRUITING)

Study contacts

• Study coordinator: Jianyong Lei

Conditions: Lymph Nodes With Tumor Metastasis, Primary unknown tumor origin, Deep learning, Cytopathology