A real-time, computer-aided diagnosis (CAD) algorithm was found to assess histologic activity with high accuracy in patients with ulcerative colitis (UC), according to findings published in Gastroenterology.
The CAD algorithm uses images from a prototype endoscope with a single short wavelength monochromatic LED light illumination, which enables real-time evaluation of the mucosal architecture to a depth of about 50 to 200 µm. Of note, the CAD algorithm is “the first endoscopic system that optically visualizes the pericryptal vascular structures without additional need for a contrast agent,” according to the study authors.
The researchers prospectively assessed patients with UC for planned endoscopy at an outpatient clinic in Belgium. A total of 58 patients with a median age of 41 years (interquartile range, IQR 38-56) were included in the analysis. Most of these patients (53%) were male, and the disease duration was 7.1 years (IQR 2.4-16.4). The evaluation encompassed 113 evaluable segments (89% rectum or sigmoid).
The investigators obtained white light and monochromatic light images in different magnification modes and sampled biopsies in the corresponding region. All images were scored using the Mayo Endoscopic Subscore (MES) and the Ulcerative Colitis Endoscopic Index of Severity (UCEIS); biopsies were scored according to the Geboes score. The CAD algorithm was developed based on these data.
The CAD algorithm detected histologic remission with a high performance (sensitivity 0.79, specificity 0.90), compared with UCEIS (sensitivity 0.95, specificity 0.69) and MES (sensitivity 0.98, specificity 0.61), resulting in a positive predictive value for histologic remission of 0.83, 0.65, and 0.59 for the CAD algorithm, UCEIS, and MES, respectively.
“The CAD algorithm detects histologic remission with high accuracy (86%) vs MES (74%) and UCEIS (79%) and indicates in an objective way if a treatment target of histologic remission is reached,” the study authors stated, adding that further validation of the CAD algorithm’s efficacy in an independent cohort is necessary.
The findings represent a novel, real-time, automated evaluation of specific changes in the mucosal pericryptal vascular structures associated with UC disease activity, according to the research group. These relevant changes are linked to the infiltration of inflammatory cells in the colonic wall but are currently difficult to quantify in vivo.
“The automated system has the potential to provide instant and accurate histologic scoring of the colonic mucosa. It is a promising tool for objective evaluation of endoscopic/histologic mucosal healing in a treat-to-target approach in patients with ulcerative colitis. In the current state, the CAD algorithm does not replace standard biopsies to confirm remission and to assess other features [such as] infections and dysplasia,” the investigators concluded.
Disclosures: This study received technical support from Fujifilm, Tokyo, Japan. Several study authors declared affiliations with the pharmaceutical industry. Please see the original reference for a full list of author’s disclosures.
Bossuyt P, De Hertogh G, Eelbode T, Vermeire S, Bisschops R. Computer aided diagnosis with monochromatic light endoscopy for scoring histological remission in ulcerative colitis Gastroenterology. Published October 12, 2020. doi: 10.1053/j.gastro.2020.09.053