Analysis of New Endoscopic Features and Variable Stiffness in Colonoscopy: Prospective Randomised Trial
- Conditions
- Colorectal Adenomatous PolypColorectal Adenoma
- Registration Number
- NCT03234725
- Lead Sponsor
- Bács-Kiskun County Teaching Hospital
- 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.
- Detailed 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.
Recruitment & Eligibility
- Status
- COMPLETED
- Sex
- All
- Target Recruitment
- 1000
- 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
- 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.
Study & Design
- Study Type
- OBSERVATIONAL
- Study Design
- Not specified
- Primary Outcome Measures
Name Time Method Inter-observer agreement among the 5 experts 2 years 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.
diagnostic value of the computer algorithm 2 years diagnostic value of the computer algorithm (sensitivity, specificity, negative predictive value, positive predictive value, accuracy) \[ Time Frame: 10 months \] \[ Designated as safety issue: No \]
Number of detected serrated polyps 2 years Number of Detected Proximal Serrated lesions, flat polyps and colorectal adenomas in proximal colon
Number of detected polyps 2 years Quantity of total number of colorectal adenomas found in the colon during colonoscopy was recorded and compared.
the accuracy of the NICE (NBI International Colorectal Endoscopic) criteria using FICE versus BLI Eluxeo technology 2 years 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.
Propofol need for deep sedation 2 years The main efficacy parameter is the amount of Propofol used for deep sedation during colonoscopy, expressed as the mean for each group.
Cecal intubation rate 2 years The proportion of colonoscopy procedures resulting in successful intubation of the cecum.
- Secondary Outcome Measures
Name Time Method Comparison of accuracy of BLI and LCI pictures 2 years Comparison of accuracy of BLI and LCI pictures with and without zoom on the final diagnosis (neoplastic or non-neoplastic polyp) as compared to histology
Improvement of adenoma detection rate by using LCI imaging comparing with that under white endoscopy 2 years Improvement of adenoma detection rate by using LCI imaging comparing with that under white endoscopy
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 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 in diagnoses with high-confidence on a video-library of 120 polyps reviewed by 5 experts (ML, SZM, OL, SZA, DZS)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.
diagnostic interobserver variability based on the computer algorithm 2 years diagnostic interobserver variability based on the computer algorithm
Time-to-cecum 2 years Time from initial insertion of colonoscope until successful intubation of the cecum (min)
Ancillary maneuvers to facilitate procedure 2 years A number of added maneuvers, including abdominal pressure, repositioning of the patient, endoscope loop reduction techniques, used to facilitate advancement of the endoscope during the procedure.
Trial Locations
- Locations (1)
Bács Kiskun County and Teaching Hospital
🇭🇺Kecskemét, Nyiri Street 38, Hungary