A hierarchical deep learning approach for diagnosing impacted canine-induced root resorption via cone-beam computed tomography

• Main Authors: Zeynab Pirayesh (Author), Hossein Mohammad-Rahimi (Author), Saeed Reza Motamedian (Author), Sepehr Amini Afshar (Author), Reza Abbasi (Author), Mohammad Hossein Rohban (Author), Mina Mahdian (Author), Mitra Ghazizadeh Ahsaie (Author), Mina Iranparvar Alamdari (Author)
• Format: Book
• Published: BMC, 2024-08-01T00:00:00Z.
• Subjects: article
• Online Access: Connect to this object online.

Abstract Objectives Canine-induced root resorption (CIRR) is caused by impacted canines and CBCT images have shown to be more accurate in diagnosing CIRR than panoramic and periapical radiographs with the reported AUCs being 0.95, 0.49, and 0.57, respectively. The aim of this study was to use deep l...