A Computer-aided (CADx）System in Real-time Characterization of Colorectal Ulcerative Diseases

Construction and Validation of a Computer-aided (CADx）System in Real-time Characterization of Colorectal Ulcerative Diseases: A Multicenter, Retrospective Study

The goal of this observational study is to construct and validate a Computer-aided (CADx）System in Real-time Characterization of Colorectal Ulcrerative Diseases. The main question it aims to answer are to demonstrate whether the newly developed CADx system has a high-level diagnostic accuracy in predicting characterization of colorectal ulcerative diseases.

It is a multi-center, retrospective study. The study retrospectively collected colonoscopy images and videos of colorectal ulcers (including colorectal cancer, Crohn's disease, Ulcerative colitis, Intestinal tuberculosis and ischemic enteritis). A training cohort will be developed from majority of the included cases, followed by a validation cohort with the remaining cases. A CADx system in real-time characterization of colonic ulcer diseases was constructed using artificial intelligence to extract endoscopic features from the training set. Subsequently, the performance of the CADx system was preliminarily tested through the validation set.

Study Overview

• Status: Recruiting
• Conditions: Colorectal Ulcers; Computer-aided System
• Intervention / Treatment: Diagnostic test: Colonoscopy images and videos

Detailed Description

The goal of this observational study is to construct and validate a Computer-aided (CADx）System in Real-time Characterization of Colorectal Ulcrerative Diseases. Endoscopic photos and videos will be retrieved from existing database in the study centers. For each colorectal ulcer, different endoscopic views will be captures.Relevant baseline demographics, laboratory reports, imaging reports, endoscopy reports and histopathology results will be collected for analysis. The location, size and morphology of each colonic lesion will be recorded. The diagnosis of all colorectal ulcerative disease was comprehensively evaluated by independent pathologists and gastroenterologists. In our study, we will focus on the following subtypes of colorectal ulcerative lesions:

1. colorectal cancer (CA);
2. Crohn's disease (CD);
3. Ulcerative colitis (UC);
4. intestinal tuberculosis (ITB);
5. ischemic colitis (IC). All data will be de-identified before central processing to ensure confidentiality. A project-specific serial number will be used to represent each individual subject. All clinical data and de-identified endoscopic images will be kept confidential and will not be shared with any third party.

A training cohort will be developed from majority of the included cases, followed by a validation cohort with the remaining cases. The endoscopic images and videos will be prepared to train the convoluted neural network and recurrent neural network by selecting appropriate regions of interest (ROI). Multiple ROI within the same colorectal ulcerative disease will be collected to reduce selection bias. Annotation and validation of endoscopic images will be performed by research team. The images will be further segmented into tiles of the same size for further processing. Deep learning algorithms will be applied to learn and extract features on the image and video data. We will develop the recurrent convolutional network to leverage the complementary information of visual and temporal features extracted from the video. Validation data are also created under the same principle which enable cross-validation for model accuracy.

• Study Type: Observational
• Enrollment (Estimated): 1000

Contacts and Locations

• Study Contact: Name: Xiaobei Luo, PhD; Phone Number: 17688881428; Email: luoxiaobei63@126.com

Study Locations

• China
  • Undefined
    • Guangzhou, Undefined, China, undefined
      • Recruiting
      • Nanfang Hospital, Southern Medical University
      • Contact: Xiaobei Luo, PhD; Phone Number: 17688881428; Email: luoxiaobei63@126.com

Participation Criteria

Eligibility Criteria

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

• Sampling Method: Probability Sample

Study Population

They underwent endoscopic examination and are found to have ulcerative lesions in the large intestine.

Description

Inclusion Criteria:

1. They underwent endoscopic examination and are found to have ulcerative lesions in the large intestine;
2. They have endoscopic images and videos captured and stored during colonoscopy which are available to be retrieved;
3. They have the complete medical records and clear diagnosis.

Exclusion Criteria:

1)Poor quality endoscopic images and videos defined as:

1. Incomplete visualization of the colorectal ulcer due to technical reasons (e.g. out-of-focus, motion-blurred or insufficient illumination);
2. Artifacts due to mucus, air bubbles, stool, or blood. 2)Obscured view due to poor bowel preparation; 3)Incomplete medical record; 4)Prior history of intestinal resection, fistula, or anastomosis.

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Colorectal ulcers; Colonoscopy images and videos of colorectal ulcers.	Diagnostic test: Colonoscopy images and videos; A CADx system in real-time characterization of colonic ulcer diseases was constructed using artificial intelligence to extract endoscopic features from the training set. Subsequently, the performance of the CADx system was preliminarily tested through the validation set.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
The diagnostic accuracy	The diagnostic accuracy (area under receiver operating characteristic curves, AUROC) of newly developed CADx system in prediction of Characterization of Colorectal Ulcerative Diseases.	From 2023-06 to 2024-06

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Sensitivity	The diagnostic sensitivity of newly developed CADx system in prediction of Characterization of Colorectal Ulcerative Diseases.	From 2023-06 to 2024-06
Specificity	The diagnostic specificity of newly developed CADx system in prediction of Characterization of Colorectal Ulcerative Diseases.	From 2023-06 to 2024-06

Collaborators and Investigators

• Sponsor: Nanfang Hospital, Southern Medical University
• Collaborators: Prince of Wales Hospital, Shatin, Hong Kong; Wuxi People's Hospital; ZhuHai Hospital; The Second Affiliated Hospital of the Chinese University of Hong Kong (Shenzhen)

Study record dates

Study Major Dates

• Study Start (Actual): June 1, 2023
• Primary Completion (Estimated): June 1, 2024
• Study Completion (Estimated): June 1, 2024

Study Registration Dates

• First Submitted: January 7, 2024
• First Submitted That Met QC Criteria: January 7, 2024
• First Posted (Actual): January 17, 2024

Study Record Updates

• Last Update Posted (Actual): January 17, 2024
• Last Update Submitted That Met QC Criteria: January 7, 2024
• Last Verified: January 1, 2024

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Pathologic Processes; Ulcer
• Other Study ID Numbers: NFEC-2023-330

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No