Analysis of New Endoscopic Features and Variable Stiffness in Colonoscopy: Prospective Randomised Trial

NCT03234725 | Completed DMC

• 1 other identifier: Deep001
• Study Type: observational
• Target: 1,000
• Locations: 1 country
• Sites: 1

Brief 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.

Conditions

Colorectal Adenoma; Colorectal Adenomatous Polyp

Keywords

Blue light imaging; Linked color imaging; Optical histology; Adenoma detection rate; Variable stiffness; Deep learning

Outcome Measures

Primary Outcomes (7)

• diagnostic value of the computer algorithm

  diagnostic value of the computer algorithm (sensitivity, specificity, negative predictive value, positive predictive value, accuracy) \[ Time Frame: 10 months \] \[ Designated as safety issue: No \]

  2 years

• Number of detected serrated polyps

  Number of Detected Proximal Serrated lesions, flat polyps and colorectal adenomas in proximal colon

  2 years

• Number of detected polyps

  Quantity of total number of colorectal adenomas found in the colon during colonoscopy was recorded and compared.

  2 years

• the accuracy of the NICE (NBI International Colorectal Endoscopic) criteria using FICE versus BLI Eluxeo technology

  the accuracy of the NICE criteria using FICE versus BLI Eluxeo technology without optical zoom for differentiating between the non-neoplastic and neoplastic histotypes in diagnoses with high-confidence on a video-library of 120 polyps reviewed by 5 experts. 5 experts will review pictures from a web-library of subcentimetric polyps removed and histologically verified and will assess each of the three NICE criteria (colour/vascularization/surface), and classify the lesion as neoplastic or non-neoplastic with low or high confidence.

  2 years

• Inter-observer agreement among the 5 experts

  Inter-observer agreement among the 5 experts \[ Time Frame: up to 6 months \] \[ Designated as safety issue: No \] The inter-observer agreement, among the 5 experts, on the final diagnosis (neoplastic or non-neoplastic) and on each individual NICE criterion for each polyp will be determined by using K statistics.

  2 years

• Cecal intubation rate

  The proportion of colonoscopy procedures resulting in successful intubation of the cecum.

  2 years

• Propofol need for deep sedation

  The main efficacy parameter is the amount of Propofol used for deep sedation during colonoscopy, expressed as the mean for each group.

  2 years

Secondary Outcomes (6)

• diagnostic interobserver variability based on the computer algorithm

  2 years

• the accuracy of the NICE criteria using FICE versus BLI Eluxeo technology with 50x optical zoom for differentiating between the non-neoplastic and neoplastic histotypes

  2 years

• Comparison of accuracy of BLI and LCI pictures

  2 years

• Improvement of adenoma detection rate by using LCI imaging comparing with that under white endoscopy

  2 years

• Time-to-cecum

  2 years

Study Arms (2)

LCI out group

The whitdrawal of the colonoscop happen in LCI mode.

WL (white light) out group

The whitdrawal of the colonoscop happen in WL mode.

Eligibility Criteria

• Age: 18 Years - 99 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

All adult patients who did not meet the exclusion criteria were included in the study

You may qualify if:

• The patient must sign, understand and provide written consent for the procedure.
• Undergoing colonoscopy at our endoscopy unit for any indication in Propofol deep sedation
• Intact colon and rectum
• ASA (American Society of Anesthesiology) risk class 1, 2 or 3

You may not qualify if:

• Patients with inflammatory bowel disease;
• Patients with poor bowel preparation; (Boston score \<4)
• Female patients with pregnancy;
• Patients with mechanical bowel obstruction;
• Patients with diverticulitis or toxic megacolon;
• Patients with a history of radiation therapy to abdomen or pelvis;
• Patients with a history of severe cardiovascular, pulmonary, liver or renal disease and high ASA (\>3) risk of propofol sedation;
• Personal history of coagulation disorders or use of anticoagulants;
• Patients who are currently enrolled in another clinical investigation in which the intervention might compromise the safety of the patient's participation in this study.

Sponsors & Collaborators

• Bács-Kiskun County Teaching Hospital: lead
• Endo-Kapszula Privat Medical Center: collaborator

Study Sites (1)

Bács Kiskun County and Teaching Hospital

Kecskemét, Nyiri Street 38, 6000, Hungary

Location

Study Officials

• Laszlo Madacsy, MD,pHd

  Bács Kiskun Coeunty Teaching Hospital

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Clinical Professor

Study Record Dates

• First Submitted: July 27, 2017
• First Posted: July 31, 2017
• Study Start: October 1, 2016
• Primary Completion: September 30, 2018
• Study Completion: September 30, 2018
• Last Updated: July 10, 2019

Record last verified: 2019-07

Data Sharing

• IPD Sharing: Will not share

Locations

HU (1)