Peri-Implant Bone Loss Measurement Using a Region-Based Convolutional Neural Network on Dental Periapical Radiographs

Abstract

Determining the peri-implant marginal bone level on radiographs is challenging because the boundaries of the bones around implants are often unclear or the heights of the buccal and lingual bone levels are different. Therefore, a deep convolutional neural network (CNN) was evaluated for detecting the marginal bone level, top, and apex of implants on dental periapical radiographs. An automated assistant system was proposed for calculating the bone loss percentage and classifying the bone resorption severity. A modified region-based CNN (R-CNN) was trained using transfer learning based on Microsoft Common Objects in Context dataset. Overall, 708 periapical radiographic images were divided into training (n = 508), validation (n = 100), and test (n = 100) datasets. The training dataset was randomly enriched by data augmentation. For evaluation, average precision, average recall, and mean object keypoint similarity (OKS) were calculated, and the mean OKS values of the model and a dental clinician were compared. Using detected keypoints, radiographic bone loss was measured and classified. No statistically significant difference was found between the modified R-CNN model and dental clinician for detecting landmarks around dental implants. The modified R-CNN model can be utilized to measure the radiographic peri-implant bone loss ratio to assess the severity of peri-implantitis.

A pilot study of a deep learning approach to detect marginal bone loss around implants

“…3 ). These findings differed from those of Cha et al [ 28 ], whose dataset included various implants with different implant-abutment junctions. In that study, the most coronal thread of the implant was used as a threshold position.…”

“…The inclusion criteria were as follows: periapical radiographs of dental implants, appropriate radiation exposure, and radiographs of dental implants acquired in parallel. The exclusion criteria were as follows: excessively bright or dark images precluding distinguishment of marginal bone around dental implants, severely distorted images of dental implants, and/or graft material hindering observation of the alveolar bone [ 28 ]. Each digital radiograph was exported with a resolution of 96 dpi and size of approximately 300–500 × 300–400 pixels.…”

“…Based on Faster R-CNN, the Mask R-CNN method was developed; this can detect targets in images and provides high-quality segmentation results [ 34 ]. To our knowledge, few studies have used Faster R-CNN for detection of marginal bone loss around dental implants on periapical radiographs [ 28 ].…”

Deep learning approach for guiding three‐dimensional computed tomography reconstruction of lower limbs for robotically‐assisted total knee arthroplasty

“…[28][29][30] Recently, emerging studies showed that AI can be used in orthopaedics. [31][32][33] For example, Yeh et al 30 showed that an AI-baed automatic alignment measure system can locate spinal anatomic landmarks with a high accuracy and produce radiographic parameters that correlated well with operator-based measurements. Yabu et al 34 also demonstrated that convolutional neural network could detect new osteoporotic vertebral fractures utilising magnetic resonance images with performance comparable to that of spine surgeons.…”

Aplicación de la inteligencia artificial en Odontología

“…Además, se desarrollaron la DCNN y CNN (google net, inception V3 para la clasificación de los implantes dentales 14 siendo altamente efectivo en clasificar implantes de formas similares de diferentes tipos de implantes en comparación con odontólogos. Así mismo, para detectar periimplantitis Cha et al 15 utilizaron CNN, no encontrando diferencia significativa entre el modelo CNN y el de periodoncistas. También se ha analizado la detección y clasificación de fracturas de los implantes utilizando 3 DCNN (convolutional neural network (DCNN) architectures (VGGNet-19, GoogLeNet, Inception.V3 and automated DCNN) 16 con una precisión de 0,80.…”