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 greater accuracy in the evaluation of extension of disease in these patients. Artificial Intelligence is expected to enhance the diagnostic accuracy of capsule endoscopy. This study aims 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 2017-2020, constituted by 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. Particularly, 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 diagnostic performance and efficiency of monitoring Crohn’s disease activity.

In this work, the analogous treatment between coupled temperature-displacement problems and material failure models is explored within the context of a commercial software (Abaqus®). The implicit gradient Lemaitre damage and phase field models are implemented utilizing the software underlying capabilities for coupled temperature-displacement problems. The heat conduction equation is made compatible with the diffusive regularization of such material models and calculations are carried out at the material point level. This bypasses the need to implement explicitly the weak form resultant from the coupling between the momentum conservation and the evolution of the diffusive field. Throughout benchmarking examples, the proposed methodology is assessed and validated by investigating typical issues risen from the considered local inelastic-based deformation models, such as mesh dependency and the difficulties to predict cracked regions.

No abstract