Clinical Study on the Accuracy of Real-time AI-assisted Endocytoscopy in the Diagnosis of Colorectal Diminutive Polyps

Colorectal cancer (CRC) is the third most common malignant tumor in the world and the second largest cause of cancer-related death [1]. Colonoscopy is considered the preferred method of screening for colorectal cancer, and early and resectable detection of colorectal neoplastic lesions can significantly reduce colorectal cancer morbidity and mortality. In recent years, with the continuous development of endoscopic diagnostic techniques and the standardization and strengthening of endoscopist training, the detection rate of colorectal polyps has increased year by year. As the number of endoscopic excisions increases, the costs associated with endoscopic excision and pathological diagnosis of excised specimens increase year by year. Research results showed that about 90% of the detected polyps were small polyps (6-9 mm) and diminutive polyps (≤5 mm), and nearly half of them were non-neoplastic polyps, so endoscopic resection and histopathological examination were not required [2, 3]. In order to reduce unnecessary pathological examination and endoscopic treatment, the American Society of Digestive Endoscopy proposed PIVI strategies: "excise and discard" and "diagnose and do not excise" strategies.

Endocytoscopy is a kind of ultra-high magnification endoscopy. Combined with chemical staining and narrow-band imaging technology, endoscopists can observe and judge the nuclear morphology, glandular duct morphology and microvascular morphology of colorectal lesions by naked eye, thus realizing the purpose of real-time biopsy in vivo. However, it takes a lot of experience accumulation to improve the judgment accuracy of endoscopy images, and endoscopy doctors have certain subjective judgments and errors in the process of judging results. Therefore, in order to solve this problem, Artificial Intelligence (AI) is proposed clinically. Our center has developed an artificial intelligence assisted diagnosis system based on endocytoscopy to assist endocytoscopy in judging the nature of colorectal lesions. However, whether this artificial intelligence assisted diagnosis system is accurate in judging the nature of colorectal diminutive polyps and is suitable for widespread promotion and application of PIVI strategy lacks relevant clinical data. This study intends to carry out this clinical study to verify the diagnostic accuracy of this artificial intelligence in the diagnosis of colorectal diminutive polyps.

Study Overview

• Status: Recruiting
• Conditions: Colorectal Polyp

• Study Type: Observational
• Enrollment (Estimated): 600

Contacts and Locations

• Study Contact: Name: Mingqing Liu, Docror; Phone Number: +8613204300453; Email: liumq23@mails.jlu.edu.cn

Study Locations

• China
  • Jilin
    • Changchun, Jilin, China, 130021
      • Recruiting
      • First Hospital of Jilin University
      • Contact: Mingqing Liu; Phone Number: +8613204300453; Email: liumq23@jlu.edu.cn

Participation Criteria

Eligibility Criteria

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

• Sampling Method: Probability Sample

Study Population

patients with colorectal lesions

Description

Inclusion Criteria:

• colorectal lesions

Exclusion Criteria:

• lesions lacking high-quality images;
• Inflammatory bowel disease, familial adenomatous polyposis and other special diseases;
• submucosal tumors;
• Pathological diagnosis of inflammatory polyps, Peutz-Jeghers polyps, juvenile polyps, lymphoma and other pathological types.

Study Plan

How is the study designed?

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Time Frame
Negative predictive value	2025-12-31
sensitivity	2025-12-31
specificity	2025-12-31
accurary	2025-12-31

Collaborators and Investigators

• Sponsor: The First Hospital of Jilin University
• Investigators: Principal Investigator: Hong Xu, Docror, The First Hospital of Jilin University

Study record dates

Study Major Dates

• Study Start (Actual): February 5, 2025
• Primary Completion (Estimated): December 31, 2025
• Study Completion (Estimated): December 31, 2025

Study Registration Dates

• First Submitted: January 20, 2025
• First Submitted That Met QC Criteria: January 20, 2025
• First Posted (Actual): March 25, 2025

Study Record Updates

• Last Update Posted (Actual): March 25, 2025
• Last Update Submitted That Met QC Criteria: March 5, 2025
• Last Verified: January 1, 2025

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Pathological Conditions, Anatomical; Polyps
• Other Study ID Numbers: 25K014-001

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No