A multicentre study of the i-scan endoscopy in Ulcerative Colitis
Research type
Research Study
Full title
A multicentre, international validation study of the i-scan endoscopic scoring system and a new histologic scoring system to define subtle mucosal inflammation in ulcerative colitis.
IRAS ID
222806
Contact name
Marietta Iacucci
Contact email
Sponsor organisation
University of Birmingham
Clinicaltrials.gov Identifier
RG_17-050, Research Governance (Sponsor Ref)
Duration of Study in the UK
3 years, 0 months, days
Research summary
Summary of Research
This is multicentre prospective observational clinical and endoscopic study. We aim to study the colonic mucosa of ulcerative colitis (UC) patients with different grades of inflammation with high definition conventional white light endoscopy, followed by virtual electronic chromoendoscopy – this will be performed with the same equipment by easily using the switches on the hand-piece of the scope and turning on I-SCAN Pentax (I-SCAN 1,2 and I-SCAN 3). This medical equipment is CE marked. This is regularly done in clinical practice, but not in a systematic manner. The mucosal biopsies will be taken from the same regions of interest where I-SCAN will be undertaken, at least 2 biopsies from each of segment involved from the disease as normal standard of practice to assess inflammation in UC. The endoscopic inflammation would be evaluated and assessed based on the most severe lesions. In this proposal, we seek to develop and validate an I-SCAN inflammatory activity score scheme to assess patients with quiescent, mild, moderate and severe UC. We will conduct the multicentre international validation and reliability study of the UC I-SCAN activity score and histological scoring system.
The international investigators aim that these virtual endoscopic techniques, involving high definition I-SCAN modes 1, 2, 3 and the more refined histological scores (ECAP and RHI), may be more accurate and informative in assessing the severity of UC, subtle inflammation changes and mucosal healing (compared with High definition standard white light endoscopy) then this might help us to better understand the endoscopic predictive findings of flare –up or response to therapy in UC. The achievement of mucosal healing can change the natural history of the disease and can reduce the complication such as hospitalisation, the rate of colectomy and mortality. All clinical decisions will still be taken using standard Mayo score by referring physician.Summary of Results
Summary of i-scan results for online end of study report A total of 307 patients with Ulcerative Colitis from 11 international Centres were included in the study. A total of 302 patients with complete datasets, which included histological and endoscopic data, were included in the final analysis.
In this large prospective real-life international study, the recently developed PICaSSO * score correlated strongly with histological scores. It showed better correlation than the Mayo Endoscopic Score and Ulcerative Colitis Endoscopic Index of Severity (UCEIS) score in predicting histological remission. PICaSSO also detected histologic remission and predicted favourable outcome at 6 and 12 months.
Data collected in the study were also used to develop a new simple histological index for UC – the Paddington International virtual ChromoendoScopy ScOre Histologic Remission Index (PHRI). This was designed to be implemented into an artificial intelligence (AI) model to detect histological remission. PHRI provided excellent diagnostic accuracy, excellent correlation to endoscopic activity, minimal inter-rater variability and excellent prediction of long-term clinical outcome. An AI algorithm based on PHRI was able to accurately determine histological remission.
Further, we developed and validated the first VCE artificial intelligence system able to accurately distinguish in real-time endoscopic activity and remission in UC colonoscopy videos of both WLE and VCE. Our system predicted the underlying histologic activity and the occurrence of adverse clinical outcomes. We developed a computer tool to detect inflammation in colonoscopy videos, both in white-light-endoscopy and virtual-chromoendoscopy of ulcerative colitis. Additionally our system estimates the histological activity and predicts clinical outcomes.What is the impact of the study on clinical practice Endoscopic and histological remission are important targets to achieve in patients with Ulcerative Colitis. Various scores may be used to define disease activity. However, they can be complex to use and show inter-rater variability (scores differ between users).
PICaSSO can accurately define endoscopic remission and detect histological remission in patients with UC. It also showed better interobserver agreement than other scores. Therefore, PICaSSO may be useful in clinical practice and clinical trials.
The use AI models for histological evaluation can complement and support pathologists’ expertise.
Our system accurately distinguished inflammation and healing of the intestine and clinical outcomes from colonoscopy videos. This is the first computer model developed to detect inflammation/healing using VCE through the PICaSSO score and the first computer tool providing endoscopic, histologic, and clinical assessment.What were the limitations of the study
The gastroenterologists and histopathologists involved in the current study were all experienced and further real-life study is needed to reproduce the results in less experienced specialists.Video quality may impact the system performance but by selecting high quality videos the performance improves further. All procedures were performed with Pentax platform, potentially limiting the generalizability of results. However, PICaSSO has been validated with other platforms too. Further validation in a large prospective study is needed and is ongoing.
*Paddington International Virtual Chromoendoscopy Score Study publications Iacucci, M et al (2021) An international multicentre real-life prospective study of electronic chromendoscopy score PICaSSO in Ulcerative Colitis, Gastrenterology 160 (5) p1558-1569.
Gui, X et al (2022) PICaSSO Histologic Remission Index (PHRI) in ulcerative colitis: development of a novel simplified histological score for monitoring mucosal healing and predicting clinical outcomes and its applicability in an artificial intelligence system, Gut. EPub 16 February 2022. doi:10.1136/gutjnl-2021-326376Iacucci M et al 2022 A Virtual Chromoendoscopy Artificial Intelligence system to detect endoscopic and histologic activity/remission and predict clinical outcomes in Ulcerative Colitis ECCO conference 2022 and manuscript submitted
REC name
West Midlands - Solihull Research Ethics Committee
REC reference
17/WM/0223
Date of REC Opinion
8 Jun 2017
REC opinion
Favourable Opinion