AI-Driven Colon Cleansing Evaluation in Capsule Endoscopy: A Deep Learning Approach.

Gastroenterology is increasingly moving towards minimally invasive diagnostic modalities. The diagnostic exploration of the colon via capsule endoscopy, both in specific protocols for colon capsule endoscopy and during panendoscopic evaluations, is increasingly regarded as an appropriate first-line diagnostic approach. Adequate colonic preparation is essential for conclusive examinations as, contrary to a conventional colonoscopy, the capsule moves passively in the colon and does not have the capacity to clean debris. Several scales have been developed for the classification of bowel preparation for colon capsule endoscopy. Nevertheless, their applications are limited by suboptimal interobserver agreement. Our group developed a deep learning algorithm for the automatic classification of colonic bowel preparation, according to an easily applicable classification. Our neural network achieved high performance levels, with a sensitivity of 91%, a specificity of 97% and an overall accuracy of 95%. The algorithm achieved a good discriminating capacity, with areas under the curve ranging between 0.92 and 0.97. The development of these algorithms is essential for the widespread adoption of capsule endoscopy for the exploration of the colon, as well as for the adoption of minimally invasive panendoscopy.

Design of a Convolutional Neural Network as a Deep Learning Tool for the Automatic Classification of Small-Bowel Cleansing in Capsule Endoscopy.

Background and objectives: Capsule endoscopy (CE) is a non-invasive method to inspect the small bowel that, like other enteroscopy methods, requires adequate small-bowel cleansing to obtain conclusive results. Artificial intelligence (AI) algorithms have been seen to offer important benefits in the field of medical imaging over recent years, particularly through the adaptation of convolutional neural networks (CNNs) to achieve more efficient image analysis. Here, we aimed to develop a deep learning model that uses a CNN to automatically classify the quality of intestinal preparation in CE. Methods: A CNN was designed based on 12,950 CE images obtained at two clinical centers in Porto (Portugal). The quality of the intestinal preparation was classified for each image as: excellent, ≥90% of the image surface with visible mucosa; satisfactory, 50-90% of the mucosa visible; and unsatisfactory, <50% of the mucosa visible. The total set of images was divided in an 80:20 ratio to establish training and validation datasets, respectively. The CNN prediction was compared with the classification established by consensus of a group of three experts in CE, currently considered the gold standard to evaluate cleanliness. Subsequently, how the CNN performed in diagnostic terms was evaluated using an independent validation dataset. Results: Among the images obtained, 3633 were designated as unsatisfactory preparation, 6005 satisfactory preparation, and 3312 with excellent preparation. When differentiating the classes of small-bowel preparation, the algorithm developed here achieved an overall accuracy of 92.1%, with a sensitivity of 88.4%, a specificity of 93.6%, a positive predictive value of 88.5%, and a negative predictive value of 93.4%. The area under the curve for the detection of excellent, satisfactory, and unsatisfactory classes was 0.98, 0.95, and 0.99, respectively. Conclusions: A CNN-based tool was developed to automatically classify small-bowel preparation for CE, and it was seen to accurately classify intestinal preparation for CE. The development of such a system could enhance the reproducibility of the scales used for such purposes.

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.

Deep learning and capsule endoscopy: automatic identification and differentiation of small bowel lesions with distinct haemorrhagic potential using a convolutional neural network.

OBJECTIVE: Capsule endoscopy (CE) is pivotal for evaluation of small bowel disease. Obscure gastrointestinal bleeding most often originates from the small bowel. CE frequently identifies a wide range of lesions with different bleeding potentials in these patients. However, reading CE examinations is a time-consuming task. Convolutional neural networks (CNNs) are highly efficient artificial intelligence tools for image analysis. This study aims to develop a CNN-based model for identification and differentiation of multiple small bowel lesions with distinct haemorrhagic potential using CE images. DESIGN: We developed, trained, and validated a denary CNN based on CE images. Each frame was labelled according to the type of lesion (lymphangiectasia, xanthomas, ulcers, erosions, vascular lesions, protruding lesions, and blood). The haemorrhagic potential was assessed by Saurin's classification. The entire dataset was divided into training and validation sets. The performance of the CNN was measured by the area under the receiving operating characteristic curve, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). RESULTS: A total of 53 555 CE images were included. The model had an overall accuracy of 99%, a sensitivity of 88%, a specificity of 99%, a PPV of 87%, and an NPV of 99% for detection of multiple small bowel abnormalities and respective classification of bleeding potential. CONCLUSION: We developed and tested a CNN-based model for automatic detection of multiple types of small bowel lesions and classification of the respective bleeding potential. This system may improve the diagnostic yield of CE for these lesions and overall CE efficiency.

Endoscopic submucosal dissection of gastrointestinal lesions on an outpatient basis.

Background: Endoscopic submucosal dissection (ESD) is usually associated with hospital admission. Objectives: To evaluate, prospectively, the feasibility, safety and efficacy of outpatient gastrointestinal ESD. Methods: Patients with suitable lesions were invited to participate. Those that dwelt more than 1 hour from the hospital, lived alone, had severe co-morbidities, were <18 years old, had duodenal lesions, or that had ESD-related complications were admitted. The remaining patients were discharged if no complications were detected. A patients' inquiry was performed. Results: Of the 164 ESD patients, 122 were outpatient-based, corresponding to 115 patients, 47% male and mean age 63 ± 12 years-old. Outpatients tended to be younger, female, to have gastric lesions, less advanced lesions, and shorter and less complicated ESDs (all p < 0.05). Outpatients' mean tumour size was 38 mm, en bloc and R0 resection rates were 88 and 78%, respectively. Seven ESD outpatients (5.7%) had complications: delayed bleeding (n = 4), pneumonitis (n = 2) or emphysema (n = 1), all managed conservatively. Colorectal location of the lesions was predictive of hospital admission (p = 0.03). In total, 97% of patients were satisfied with the outpatient strategy. Conclusion: Risks of ambulatory ESD are low and complications can be successfully managed. This strategy has high patient satisfaction. More studies are needed to evaluate its implications on costs and patients' management.