Identification of Ulcers and Erosions by the Novel Pillcam™ Crohn's Capsule Using a Convolutional Neural Network: A Multicentre Pilot Study.

BACKGROUND AND AIMS: Capsule endoscopy is a central element in the management of patients with suspected or known Crohn's disease. In 2017, PillCam™ Crohn's Capsule was introduced and demonstrated to have greater accuracy in the evaluation of extension of disease in these patients. Artificial intelligence [AI] is expected to enhance the diagnostic accuracy of capsule endoscopy. This study aimed to develop an AI algorithm for the automatic detection of ulcers and erosions of the small intestine and colon in PillCam™ Crohn's Capsule images. METHODS: A total of 8085 PillCam™ Crohn's Capsule images were extracted between 2017 and 2020, comprising 2855 images of ulcers and 1975 erosions; the remaining images showed normal enteric and colonic mucosa. This pool of images was subsequently split into training and validation datasets. The performance of the network was subsequently assessed in an independent test set. RESULTS: The model had an overall sensitivity and specificity of 90.0% and 96.0%, respectively. The precision and accuracy of this model were 97.1% and 92.4%, respectively. In particular, the algorithm detected ulcers with a sensitivity of 83% and specificity of 98%, and erosions with sensitivity and specificity of 91% and 93%, respectively. CONCLUSION: A deep learning model capable of automatically detecting ulcers and erosions in PillCam™ Crohn's Capsule images was developed for the first time. These findings pave the way for the development of automatic systems for detection of clinically significant lesions, optimizing the diagnostic performance and efficiency of monitoring Crohn's disease activity.

Histological Outcomes and Predictive Value of Faecal Markers in Moderately to Severely Active Ulcerative Colitis Patients Receiving Infliximab.

BACKGROUND AND AIMS: Histological healing has emerged as a promising therapeutic goal in ulcerative colitis. This is especially important in the context of biological therapies. The objectives of the present study were to investigate the ability of infliximab to induce histological remission in ulcerative colitis [UC] patients and to explore the utility of faecal calprotectin and lactoferrin in predicting histological activity. METHODS: Multi-centre, single-cohort, open-label, 52-week trial including moderately to severely biological-naïve UC patients receiving intravenous infliximab [5mg/kg]. The primary outcome was the proportion of patients with histological remission [Geboes index ≤ 3.0] after 8 weeks of treatment, scored by two independent pathologists. RESULTS: Twenty patients were included. The rate of histological remission increased from 5% at baseline to 15% and 35% at Week 8 and Week 52, respectively. At Week 8, 40% of patients were in clinical remission [Mayo ≤ 2] and 45% achieved mucosal healing [Mayo endoscopy subscore 0-1]. At Week 52, 25% of patients had clinical, endoscopic and histological remission. Faecal calprotectin and lactoferrin showed the highest correlation with histological activity at Week 8 (area under the curve [AUC] 94%, p = 0.017; and 96%, p = 0.013, respectively) and both markers revealed an excellent positive predictive value for this outcome at this time point [100%, p = 0.017; and 94%, p = 0.013, respectively]. CONCLUSIONS: Infliximab was able to induce histological remission. There was a good agreement between histology and faecal biomarkers. Faecal calprotectin and lactoferrin were good predictors of histological remission. Our data support inclusion of histology as a treatment target complementary to endoscopy in clinical trials when evaluating therapeutic response in UC.