Development and validation of a feature extraction-based logical anthropomorphic diagnostic system for early gastric cancer: A case-control study.
Jia Li, Yijie Zhu, Zehua Dong...
https://pubmed.ncbi.nlm.nih.gov/35521066Actively Recruiting
Age: 18Years +
All Genders
ID07073430
Application Evaluation Research on the Artificial Intelligence-assisted Support System for the Diagnosis of Colorectal Tubular Adenoma Lesions
Led by Renmin Hospital of Wuhan University · Updated on 2026-03-25
4000
Participants Needed
1
Research Sites
N/A
Total Duration
On this page
Sponsors
R
Renmin Hospital of Wuhan University
Lead Sponsor
B
Beijing Friendship Hospital, Captial Medical University
Collaborating Sponsor
AI-Summary
What this Trial Is About
Researchers are conducting a prospective, multi-center observational study to develop and evaluate an artificial intelligence (AI)-assisted support system for diagnosing colorectal tubular adenomas. The study aims to build a comprehensive "trinity" database combining white light, magnifying chromo, and pathological images to simulate doctors' decision-making processes. This approach focuses on creating a multimodal deep learning diagnostic model and an interpretable risk prediction model for intestinal adenomas, addressing limitations in previous AI imaging models related to explainability. Participants will undergo colonoscopy examinations in two groups: a traditional colonoscopy group and an AI-assisted colonoscopy group. The AI system detects and marks polyp positions on high-definition monitors during procedures, using hollow blue boxes for polyps and hollow red boxes for adenomas. The diagnostic model is based on multimodal endoscopic LAFEQ methods combined with Narrow Band Imaging (NBI) to enhance detection accuracy. During the study, researchers will measure the accuracy of adenoma diagnosis and the AI system's ability to predict disease risk levels during endoscopy. Participants will be monitored throughout the colonoscopy procedures, with data collected from video recordings and imaging. The study seeks to improve diagnostic precision while providing clear explanations for AI-based decisions, with participation lasting through the colonoscopy process and associated evaluations.
CONDITIONS
Brief Title
Application Evaluation Research on the Artificial Intelligence-assisted Support System for the Diagnosis of Colorectal Tubular Adenoma Lesions
Who Can Participate
Age: 18Years +
All Genders
Eligibility Criteria
You may qualify if you...
- Patients aged 65 18 years who need to undergo colonoscopy, regardless of gender
- Voluntarily sign the informed consent form
- Promise to follow the research procedures and cooperate throughout the study
You will not qualify if you...
- History of abdominal or pelvic surgery or radiotherapy in the past
- Definite active lower gastrointestinal bleeding
- Existing or suspected hereditary colorectal polyposis or inflammatory bowel disease
- Uncontrolled hypertension (systolic > 160 mmHg or diastolic > 95 mmHg after treatment)
- History of stroke, coronary artery disease, or vascular disease
- Pregnant
- Unable to complete intestinal preparation
AI-Screening
AI-Powered Screening
Complete this quick 3-step screening to check your eligibility
1
2
3
Your Study Journey
Screening
Duration - 2 to 4 weeks
Participants are screened for eligibility to participate in the trial.
1 visit (in-person)
Implementation
Duration - Day of colonoscopy procedure
Participants undergo colonoscopy examinations either with traditional methods or with an AI-assisted support system to detect colorectal tubular adenoma lesions.
1 visit (in-person)
Trial Site Locations
Total: 1 location
1
Renmin Hospital of Wuhan University
Wuhan, Hubei, China
Actively Recruiting
Loading map...
Research Team
M
Mingkai Chen
How is the study designed?
Study Type
OBSERVATIONAL
Masking
N/A
Allocation
N/A
Model
N/A
Primary Purpose
N/A
Number of Arms
2
Similar Trials
Frequently Asked Questions
Have more questions? Get in touch with our team for quick support
Not the Right Trial for You?
Explore thousands of other clinical trials that might be a better match.
Sign up to get personalized trial recommendations delivered to your inbox.
Already have an account? Log in here
Published Research Related To This Trial
Advances in CRC Prevention: Screening and Surveillance.
Evelien Dekker, Douglas K Rex
https://pubmed.ncbi.nlm.nih.gov/29454795Deep learning methods for medical image fusion: A review.
Tao Zhou, QianRu Cheng, HuiLing Lu...
https://pubmed.ncbi.nlm.nih.gov/37141652Multimodal imaging for improved diagnosis and treatment of cancers.
Clare M C Tempany, Jagadeesan Jayender, Tina Kapur...
https://pubmed.ncbi.nlm.nih.gov/25204551Geometric Correspondence-Based Multimodal Learning for Ophthalmic Image Analysis.
Yan Wang, Liangli Zhen, Tien-En Tan...
https://pubmed.ncbi.nlm.nih.gov/38206778Explainable artificial intelligence (XAI) in deep learning-based medical image analysis.
Bas H M van der Velden, Hugo J Kuijf, Kenneth G A Gilhuijs...
https://pubmed.ncbi.nlm.nih.gov/35576821Multimodal deep learning for biomedical data fusion: a review.
Sören Richard Stahlschmidt, Benjamin Ulfenborg, Jane Synnergren
https://pubmed.ncbi.nlm.nih.gov/35089332Deep Learning Algorithms for Brain Imaging: From Black Box to Clinical Toolbox?
Thaddeus J Haight, Arman Eshaghi
https://pubmed.ncbi.nlm.nih.gov/36639238Impact of Artificial Intelligence on Miss Rate of Colorectal Neoplasia.
Michael B Wallace, Prateek Sharma, Pradeep Bhandari...
https://pubmed.ncbi.nlm.nih.gov/35304117Effect of artificial intelligence on novice-performed colonoscopy: a multicenter randomized controlled tandem study.
Liwen Yao, Xun Li, Zhifeng Wu...
https://pubmed.ncbi.nlm.nih.gov/37536635