Endoscopy 2020; 52(S 01): S17
DOI: 10.1055/s-0040-1704059
ESGE Days 2020 oral presentations
Friday, April 24, 2020 08:30 – 10:30 Endoscopy in flames Liffey Hall 1
© Georg Thieme Verlag KG Stuttgart · New York

MUCOSAL CAPILLARY PATTERN RECOGNITION WITH REAL-TIME COMPUTER-BASED IMAGE ANALYSIS DETECTS HISTOLOGICAL REMISSION IN ULCERATIVE COLITIS

P Bossuyt
1   University Hospitals Leuven, Department of Gastroenterology and Hepatology, Leuven, Belgium
2   Imelda General Hospital, Department of Gastroenterology, Bonheiden, Belgium
,
G De Hertogh
3   University Hospitals Leuven, Department of Pathology, Leuven, Belgium
,
T Eelbode
4   University Hospitals Leuven, Medical Imaging Research Center, Leuven, Belgium
,
S Vermeire
1   University Hospitals Leuven, Department of Gastroenterology and Hepatology, Leuven, Belgium
,
R Bisschops
1   University Hospitals Leuven, Department of Gastroenterology and Hepatology, Leuven, Belgium
› Author Affiliations
Further Information

Publication History

Publication Date:
23 April 2020 (online)

 

Aims The management of Ulcerative Colitis (UC) requires objective targets. Automated endoscopic systems that correlate with histology can be objective and predictive for sustained remission. The infiltration of neutrophils is associated with irregularities of the pericryptal capillaries. We aimed to develop an objective automated endoscopic tool to assess histological remission based on the evaluation of the morphology of the pericryptal capillaries during endoscopy.

Methods We used a prototype endoscope with short wave-length monochromatic light from a LED system. This enables to evaluate the superficial (< 200µm) mucosal architecture. The image analysis algorithm includes two steps. First, bleeding was assessed by pattern recognition. Samples with bleedings were automatically classified as non-remission. Second, the degree of congestion of the capillaries was measured (maximal localized density estimation after morphological hessian based vessel recognition) to assess an ideal cut off value to identify histological remission (Geboes score (GBS) < 2B.1). Consecutive patients with UC were evaluated. To test the reliability of the algorithm and standard endoscopic scores, the results were correlated with the GBS.

Results Fifty eight patients with UC (53% male, median age 41y IQR 38-56, disease duration 7.1y IQR 2.4-16.4) with 113 evaluable segments (89% rectum or sigmoid) were included. The correlation between GBS and MES, UCEIS was good (r= 0.76, 0.75 respectively). The automated image analysis algorithm detected histological remission with a high performance (sens 0.79, spec 0.90) compared to UCEIS (sens 0.95, spec 0.69) and MES (sens 0.98, spec 0.61), resulting in a positive predictive value of 0.83, 0.65 and 0.59 for the automated image analysis algorithm, UCEIS and MES respectively. The algorithm detects histological remission with high accuracy (86%).

Conclusions Mucosal capillary pattern recognition based on image analysis with short wave-length monochromatic light detected histological remission with high accuracy in UC. This technique provides an objective and quantitative tool to assess histological remission.