The goal of this observational study is to establish a video/image library dataset of complete endoscopy or partial colonoscopy procedures for patients with rectal cancer or inflammatory bowel disease (IBD). With this video/image library, the aims are:
* to develop and validate novel AI-empowered solutions to automatically detect and report endoscopy quality metrics * to develop automated endoscopy reporting solutions, auditing, and educational tools for residents and fellows to enhance their endoscopy skills.
The hypothesis is that a heterogeneous video/image library will provide:
* comprehensive and robust source material to develop AI models * real-time quality feedback at the end of an endoscopy procedure.
≥ 18 y.o.
indication of undergoing a screening, surveillance, diagnostic, or therapeutic upper (EGD) or lower (colonoscopy) endoscopy
Coagulopathy defined as an elevated INR ≥ 2.5
Platelet count ≤ 50,000/mm3
Emergency endoscopy
Poor general health defined as the American Society of Anesthesiologists physical status class >3
All eligible patients presenting at the CHUM for an upper or lower endoscopy will be approached for this study.
Other
Prospective
Not listed
EGD documented data
For EGD procedures, the following data will be documented: the exact time to reach the GE junction, the diaphragmatic hiatus, body/fondus/antrum of stomach, duodenum, procedural time during EGD, complications (immediate and late: first 24h post-procedure and 14 days post-procedure, respectively), the use of a distal attachment cap, insufflation and desufflation, cardiac retroflexion for facilitating visualization of mucosa during EGD, the use of existing AI platforms that increase lesion detection (CADe) and classification (CADx), the AI classification (autonomous CADx diagnosis), the endoscopists' ODs without CADx, the endoscopists' ODs after seeing the diagnosis from CADx (CADx-assisted diagnosis), the performance of endoscopists (measured with detection rates such as ADR, AADR, SSLDR, PDR, or with detection counts such as APC).
Colonoscopy documented data
For colonoscopy procedures, the following data will be documented: the exact time to reach the caecum, caecum intubation, the exact time of the visualisation of each anatomical landmarks, confirmed time of each lesion, ulcer, polyp visualised by the endoscopist, withdrawal time, mucosal inspection time, and complications (immediate and late: 24h post-procedure and 14 days post-procedure, respectively), the use of existing AI platforms that increase lesion detection (CADe) and classification (CADx), the AI classification (autonomous CADx diagnosis), the endoscopists' ODs without CADx, the endoscopists' ODs after seeing the diagnosis from CADx (CADx-assisted diagnosis), the performance of endoscopists (measured with detection rates such as ADR, AADR, SSLDR, PDR, or with detection counts such as APC). In the case of patients with rectal cancer, any active disease, such as tumor recurrence will be documented.
Polyp, lesion, or ulcer-related characteristics
For upper and lower endoscopies, polyp, lesion, or ulcer-related characteristics will be documented: anatomical location, size estimated by the endoscopists, surface and vascular pattern and morphology. Any other pathological findings with the description of severity and anatomical location will be documented. Any biopsies taken during the procedure, and their location will be documented, including the number and a description of the biopsied tissue, as well as the reason for the biopsy.
IBD data
In case of IBD indication, Crohn's disease and ulcerative colitis endoscopic characteristics will be graded and documented. The inflammation, ulceration/erosion, stricture, bleeding, and their related severity or extent in each colon segment will be documented. The endoscopic characteristics of the colon will also be documented, using components of the Mayo Score / DAI for Ulcerative Colitis, including vessels and bleeding.
Hiatal hernia data
In case of hiatal hernia, the size of the hernia along with the related type will be documented.
GERD data
In case of esophagitis (GERD), the Los Angeles classification of esophagitis will be used to define the grade and extent of the inflammation. The MUSE classification system will also be used to categorise esophageal lesions and strictures.
Click on the lead sponsor to view all of their trials.
