Multi-center and Multi-modal Deep Learning Study of Gastric Cancer

NCT05001321 | Unknown

• 1 other identifier: FirstHCMU_DL_oncology
• Study Type: observational
• Target: 3,300
• Locations: 1 country
• Sites: 6

Brief Summary

To assist postoperative pathological diagnosis and classification of gastric cancer by machine learning; To improve the accuracy of pathological diagnosis of gastric cancer by machine learning; To predict the effectiveness of treatment for gastric cancer by deep learning; To construct a model to predict the survival of gastric cancer patients by multimodal deep learning.

Conditions

Stomach Neoplasms

Keywords

Diagnosis; Prognosis

Outcome Measures

Primary Outcomes (8)

• Maximum diameter of tumor

  To measure the maximum diameter of tumor on preoperative enhanced abdominal CT of patients with gastric cancer.

  1 day

• Growth pattern

  To assess the growth pattern on preoperative enhanced abdominal CT of patients with gastric cancer, including endophytic, exophytic and mixed.

  1 day

• Enhancement pattern

  To assess the enhancement pattern on preoperative enhanced abdominal CT of patients with gastric cancer, including homogeneous and heterogeneous.

  1 day

• Enhancement degree

  To assess the enhancement degree on preoperative enhanced abdominal CT of patients with gastric cancer, including hypoenhancement, isoenhancement and hyperenhancement.

  1 day

• Nucleus size

  To obtain the nucleus size of postoperative H\&E stained sections and slides of gastric cancer by deep learning.

  1 day

• Nucleus shape

  To obtain the nucleus shape of postoperative H\&E stained sections and slides of gastric cancer by deep learning.

  1 day

• Distribution of pixel intensity

  To obtain the distribution of pixel intensity of postoperative H\&E stained sections and slides of gastric cancer by deep learning.

  1 day

• Texture of nuclei

  To obtain the texture of nuclei of postoperative H\&E stained sections and slides of gastric cancer by deep learning.

  1 day

Secondary Outcomes (3)

• Survival status

  1 day

• Overall survival

  1 day

• Recurrence/metastasis

  1 day

Study Arms (3)

Training Group

Based on the inclusion criteria, 2000 gastric cancer patients will be recruited in the analysis. And a model will be constructed based on deep learning.

Radiation: The whole abdomen contrast-enhanced CT scan; Other: H&E stained sections and slides

Internal Validation Group

Based on the inclusion criteria, 1000 gastric cancer patients will be recruited in this group to verify the sensitivity and specificity of the constructed model.

Radiation: The whole abdomen contrast-enhanced CT scan; Other: H&E stained sections and slides

External Validation Group

Based on the inclusion criteria, 300 gastric cancer patients from 5 other medical centers will be recruited in this group to verify the sensitivity and specificity of the constructed model.

Radiation: The whole abdomen contrast-enhanced CT scan; Other: H&E stained sections and slides

Interventions

The whole abdomen contrast-enhanced CT scan RADIATION

All the participants were measured by the whole abdomen contrast-enhanced CT scan.

External Validation Group; Internal Validation Group; Training Group

H&E stained sections and slides OTHER

HE pathological examination was performed on all specimens of enrolled patients.

External Validation Group; Internal Validation Group; Training Group

Eligibility Criteria

• Age: 18 Years - 79 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

3000 gastric cancer patients will participate in the phase I study, they will be divided into training group and internal validation group. 300 gastric cancer patients in five other medical centers will form the external validation group.

You may qualify if:

• The diagnosis of gastric cancer was confirmed by pathology;
• Preoperative enhanced abdominal CT;
• Available detailed clinical and pathological data;
• Integrated follow-up data.

You may not qualify if:

• The patients had severe underlying disease;
• Overall survival was less than 3 months;
• No detailed information could be collected.

Sponsors & Collaborators

• First Hospital of China Medical University: lead
• The Second Hospital of Shandong University: collaborator
• Chaoyang Central Hospital: collaborator
• The General Hospital of Fushun Mining Bureau: collaborator
• The fourth People's Hospital of Changzhou: collaborator
• First Hospital of Jinzhou Medical University: collaborator

Study Sites (6)

The fourth People's Hospital of Changzhou

Changzhou, Jiangsu, 213001, China

Location

Chaoyang Central Hospital

Chaoyang, Liaoning, 122099, China

Location

The General Hospital of Fushun Mining Bureau

Fushun, Liaoning, 113012, China

Location

First Hospital of Jinzhou Medical University

Jinzhou, Liaoning, 121012, China

Location

The First Affiliated Hospital of China Medical University

Shenyang, Liaoning, 110000, China

Location

The Second Hospital of Shandong University

Ji'nan, Shandong, 250033, China

Location

MeSH Terms

Conditions

Stomach Neoplasms; Disease

Condition Hierarchy (Ancestors)

Gastrointestinal Neoplasms; Digestive System Neoplasms; Neoplasms by Site; Neoplasms; Digestive System Diseases; Gastrointestinal Diseases; Stomach Diseases; Pathologic Processes; Pathological Conditions, Signs and Symptoms

Study Officials

• Kai Li, MD

  First Hospital of China Medical University

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: CASE ONLY
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Deputy Director of surgical Oncology

Study Record Dates

• First Submitted: August 1, 2021
• First Posted: August 11, 2021
• Study Start: July 1, 2021
• Primary Completion: January 31, 2022
• Study Completion: December 31, 2024
• Last Updated: August 11, 2021

Record last verified: 2021-08

Locations

CN (6)