Three-dimensional modelling as a novel interactive tool for preoperative planning for complex perianal fistulas in Crohn's disease

Abstract

Crohn disease; Artificial intelligence; Three-dimensional imaging

Enfermedad de Crohn; Inteligencia artificial; Imagen tridimensional

Malaltia de Crohn; Intel·ligència artificial; Imatge tridimensional

Aim The aim of this study is to demonstrate the added value of three-dimensional (3D) reconstruction models and artificial intelligence for preoperative planning in complex perianal Crohn's disease. MRI is the gold standard for diagnosis of complex perianal fistulas and abscess due to its high sensitivity, but it lacks high specificity values. This creates the need for better diagnostic models such as 3D image processing and reconstruction (3D-IPR) with artificial intelligence (AI) algorithms. Method This is a prospective study evaluating the utility of 3D reconstruction models from MRI in four patients with perineal Crohn's disease (pCD). Results Four pCD patients had 3D reconstruction models made from pelvic MRI. This provided a more visual representation of perianal disease and made possible location of the internal fistula orifice, seton placement in fistula tracts and abscess drainage. Conclusion Three-dimensional reconstruction in CD-associated complex perianal fistulas can facilitate disease interpretation, anatomy and surgical strategy, potentially improving preoperative planning as well as intraoperative assistance. This could probably result in better surgical outcomes to control perianal sepsis and reduce the number of surgical procedures required in these patients.