Modular Neural Networks for Osteoporosis Detection in Mandibular Cone-Beam Computed Tomography Scans

• Published in: Tomography (Ann Arbor) Vol. 9; no. 5; pp. 1772 - 1786
• Main Authors: Namatevs, Ivars, Nikulins, Arturs, Edelmers, Edgars, Neimane, Laura, Slaidina, Anda, Radzins, Oskars, Sudars, Kaspars
• Format: Journal Article
• Language: English
• Published: MDPI AG 22.09.2023; MDPI
• Subjects: Algorithms; artificial intelligence; CBCT; Computational linguistics; convolutional neural network; CT imaging; deep learning; dentistry; Language processing; Medical imaging equipment; Natural language interfaces; Neural networks; Osteoporosis; Technical Note; Latvia
• ISSN: 2379-139X; 2379-1381; 2379-139X
• DOI: 10.3390/tomography9050141

In this technical note, we examine the capabilities of deep convolutional neural networks (DCNNs) for diagnosing osteoporosis through cone-beam computed tomography (CBCT) scans of the mandible. The evaluation was conducted using 188 patients’ mandibular CBCT images utilizing DCNN models built on the ResNet-101 framework. We adopted a segmented three-phase method to assess osteoporosis. Stage 1 focused on mandibular bone slice identification, Stage 2 pinpointed the coordinates for mandibular bone cross-sectional views, and Stage 3 computed the mandibular bone’s thickness, highlighting osteoporotic variances. The procedure, built using ResNet-101 networks, showcased efficacy in osteoporosis detection using CBCT scans: Stage 1 achieved a remarkable 98.85% training accuracy, Stage 2 minimized L1 loss to a mere 1.02 pixels, and the last stage’s bone thickness computation algorithm reported a mean squared error of 0.8377. These findings underline the significant potential of AI in osteoporosis identification and its promise for enhanced medical care. The compartmentalized method endorses a sturdier DCNN training and heightened model transparency. Moreover, the outcomes illustrate the efficacy of a modular transfer learning method for osteoporosis detection, even when relying on limited mandibular CBCT datasets. The methodology given is accompanied by the source code available on GitLab.