Clinical Trials Logo

Clinical Trial Summary

The aim of the present study is to develop and evaluate a computer-based methods for automated and improved detection and classification of different colorectal lesions, especially polyps. For this purpose first, pit pattern and vascularization features of up to 1000 polyps with a size of 10 mm or smaller will be detected and stored in our web based picture database made by a zoom BLI colonoscopy. These polyps are going to be imaged and subsequently removed for histological analysis. The polyp images are analyzed by a newly developed deep learning computer algorithm. The results of the deep learning automatic classification (sensitivity, specificity, negative predictive value, positive predictive value and accuracy) are compared to those of human observers, who were blinded to the histological gold standard.

In a second approach we are planning to use LCI of the colon, rather than the usual white light. Here, we will determine, whether this technique could improve the detection of flat neoplastic lesions, laterally spreading tumors, small pedunculated adenomas and serrated polyps. The polyps are called serrated because of their appearance under the microscope after they have been removed. They tend to be located up high in the colon, far away from the rectum. They have been definitely shown to be a type of precancerous polyp and it is possible that using LCI will make it easier to see them, as they can be quite difficult to see with standard white light.


Clinical Trial Description

Computer-based Classification and Differentiation of Colorectal Polyps Using Blue Light Imaging (BLI)

Purpose

Recent studies have shown that optical chromoendoscopy with narrow-band imaging (NBI) of Fuji Intelligent Color Enhancement (FICE) is a powerful diagnostic tool for the differentiation between neoplastic and non-neoplastic colorectal polyps. Linked color imaging (LCI) and blue laser imaging (BLI) are two new imaging systems used in endoscopy which are recently developed. BLI was developed to compensate for the limitations of NBI. BLI shows a bright image of the digestive mucosa, enabling the detailed visualization of both the microstructure and microvasculature. The ELUXEO™ endoscopic system powered by Fujifilm's unique 4-LED (light-emitting diode) Multi Light™ technology sets a new standard in light intensity and electronic chromoendoscopy imaging. By combining four different wavelengths and the specific application of intensified from light spectra created by the integrated light source, this technology allows to easily switch between the three imaging modes White Light, Blue Light Imaging (BLI) and Linked Colour Imaging (LCI). Blue light imaging (BLI) is a new system for image-enhanced electronic chromoendoscopy, since the 410 nm LED visualizes vascular microarchitecture, similar to narrow band imaging, and a 450 nm provides white light by excitation. According to three recently published reports, the diagnostic ability of polyp characterization using blue light imaging compares favorably with narrow band imaging. No published data are available to date regarding computer assisted polyp characterization with blue light imaging.

The aim of the present study is to develop and evaluate a computer-based method for automated classification of small colorectal polyps on the basis of pit pattern and vascularization features. In this prospective study up to 1000 polyps with a size of 10 mm or smaller should be detected and stored in our web based picture database made by a zoom BLI colonoscopy. These polyps were imaged and subsequently removed for histological analysis. The polyp images were analyzed by a newly developed deep learning computer algorithm. The proposed computer-based method consists of several steps: picture annotation, preprocessing, vessel segmentation, feature extraction and classification, parameterization, and finally train and test of the multiple neural layer algorithms. The results of the deep learning automatic classification (sensitivity, specificity, negative predictive value, positive predictive value and accuracy) were compared to those of human observers, who were blinded to the histological gold standard.

Condition Colorectal Polyps with a size less then 10 mm

Study Type:

Observational

Study Design:

Observational Model: Cohort Time Perspective: Prospective

Official Title:

Computer-based Classification and Differentiation of Colorectal Polyps Using Fujifilm Blue Light Imaging (BLI)

Linked color imaging (LCI) and magnifying blue laser imaging (BLI) are two new imaging systems used in endoscopy which are recently developed. The newly developed LCI system (FUJIFILM Co.) creates clear and bright endoscopic images by using short-wavelength narrow-band laser light combined with white laser light on the basis of BLI technology. LCI makes red areas appear redder and white areas appear whiter. Thus, it is easier to recognize a slight difference in color of the mucosa. The aim the present study to determine if using LCI of the colon, rather than the usual white light on the colon, will improve the detection of flat neoplastic lesions, laterally spreading tumors, small pedunculated adenomas and serrated polyps. The polyps are called serrated because of their appearance under the microscope after they have been removed. They tend to be located up high in the colon, far away from the rectum. They have been definitely shown to be a type of precancerous polyp and it is possible that using LCI will make it easier to see them, as they can be quite difficult to see with standard white light. ;


Study Design


Related Conditions & MeSH terms


NCT number NCT03234725
Study type Observational
Source Bács-Kiskun County Teaching Hospital
Contact
Status Completed
Phase
Start date October 1, 2016
Completion date September 30, 2018

See also
  Status Clinical Trial Phase
Completed NCT04192565 - A Prospective Investigation of the ColubrisMX ELS System N/A
Completed NCT04516785 - Reducing Colonoscopies in Patients Without Significant Bowel Disease
Recruiting NCT05381792 - Serial Gut Microbiome and Bacterial Gene Markers Changes After Endoscopic Resection of Colorectal Advanced Neoplasia
Withdrawn NCT05606081 - Predicting Risk for Post-polypectomy Colorectal Cancer N/A
Recruiting NCT05576506 - Application of Hyperspectral Imaging Analysis Technology in the Diagnosis of Colorectal Cancer Based on Colonoscopic Biopsy
Active, not recruiting NCT03796884 - Linaclotide in Treating Patients With Stages 0-3 Colorectal Cancer Phase 2
Completed NCT05508503 - A Study on a Blood-based Dual-target Test for CRC Detection
Recruiting NCT02935049 - Evaluation of the Resection of Adenoma and Colic Adenocarcinoma by EMR Piecemeal or EMR/ESD Hybrid Technique N/A
Completed NCT05477836 - Feasibility and Safety of MiWEndo-assisted Colonoscopy N/A
Active, not recruiting NCT05754229 - Accuracy of Real Time Characterization in Artificial Intelligence-assisted Colonoscopy N/A
Active, not recruiting NCT05740137 - Adenoma Detection Rate in Artificial Intelligence-assisted Colonoscopy N/A
Completed NCT05913453 - Technical Failure During Colorectal Endoscopic Full Thickness Resection (EFTR): The "Through Thick and Thin" Study
Recruiting NCT05261932 - Research on Endoscopic Precision Biopsy.
Completed NCT02521727 - To Investigate Risk of Colorectal Neoplasms in First-degree Relatives of Patients With Non-advanced Adenomas
Completed NCT02226185 - Study of Berberine Hydrochloride in Prevention of Colorectal Adenomas Recurrence Phase 2/Phase 3
Completed NCT00298545 - Effect of Vitamin D and Calcium on Genes in the Colon Phase 1
Completed NCT03268655 - Ginger and Gut Microbiome (GINGER) N/A
Active, not recruiting NCT04952129 - Optimal Selenium for Bowel Polyps (OSCAR) Phase 1
Recruiting NCT04444908 - Development and Validation of an Artificial Intelligence-assisted Strategy Selection System for Colonoscopy Cleaning
Completed NCT03943758 - a Low-residue Diet for Bowel Preparation N/A