Performance of deep learning object detection technology in the detection and diagnosis of maxillary sinus lesions on panoramic radiographs

Abstract

<jats:sec><jats:title>Objective:</jats:title><jats:p> The first aim of this study was to determine the performance of a deep learning object detection technique in the detection of maxillary sinuses on panoramic radiographs. The second aim was to clarify the performance in the classification of maxillary sinus lesions compared with healthy maxillary sinuses. </jats:p></jats:sec><jats:sec><jats:title>Methods:</jats:title><jats:p> The imaging data for healthy maxillary sinuses (587 sinuses, Class 0), inflamed maxillary sinuses (416 sinuses, Class 1), cysts of maxillary sinus regions (171 sinuses, Class 2) were assigned to training, testing 1, and testing two datasets.Alearning process of 1000 epochs with the training images and labelswas performed using DetectNet, and a learning model was created. The testing 1 and testing two images were applied to the model, and the detection sensitivities and the false-positive rates per image were calculated. The accuracies, sensitivities and specificities were determined for distinguishing the inflammation group (Class 1) and cyst group (Class 2) with respect to the healthy group (Class 0). </jats:p></jats:sec><jats:sec><jats:title>Results:</jats:title><jats:p> Detection sensitivities of healthy (Class 0) and inflamed (Class 1) maxillary sinuses were 100% for both testing 1 and testing two datasets, whereas they were 98 and 89% for cysts of the maxillary sinus regions (Class 2). False-positive rates per image were nearly 0.00. Accuracies, sensitivities and specificities for diagnosis maxillary sinusitis were 90–91%, 88–85%, and 91–96%, respectively; for cysts of the maxillary sinus regions, these values were 97–100%, 80–100%, and 100–100%, respectively. </jats:p></jats:sec><jats:sec><jats:title>Conclusion:</jats:title><jats:p> Deep learning could reliably detect the maxillary sinuses and identify maxillary sinusitis and cysts of the maxillary sinus regions. </jats:p></jats:sec><jats:sec><jats:title>Advances in knowledge:</jats:title><jats:p> This study using a deep leaning object detection technique indicated that the detection sensitivities of maxillary sinuses were high and the performance of maxillary sinus lesion identification was ≧80%.In particular, performance of sinusitis identification was ≧90%. </jats:p></jats:sec>

Applications of artificial intelligence in dentistry: A comprehensive review

“…Example of a general CNN architecture. 169 CNN, convolutional neural network in maxillary sinus lesions on panoramic radiographs, 72 oral squamous cell carcinoma segmentation in whole-slide imaging (WSI), 61 gingivitis segmentation in intraoral images, 79 the segmentation of periodontal bone loss and stage periodontitis classification using panoramic radiographs, 73 lesion segmentation using CT images, 80 or dental caries segmentation using near-infrared transillumination images. 53 The segmentation of other oral surfaces has also been widely explored in literature by using dental radiographs, [99][100][101][102] intraoral ultrasound imaging, 97 3D intraoral scans, 96 or CBCT Scans.…”

“…Therefore, several works have segmented the disease prior to the diagnosis for a range of diseases and a range of image types. This approach has been useful, for instance, in maxillary sinus lesions on panoramic radiographs, 72 oral squamous cell carcinoma segmentation in whole‐slide imaging (WSI), 61 gingivitis segmentation in intraoral images, 79 the segmentation of periodontal bone loss and stage periodontitis classification using panoramic radiographs, 73 lesion segmentation using CT images, 80 or dental caries segmentation using near‐infrared transillumination images 53 …”

Performance of deep learning technology for evaluation of positioning quality in periapical radiography of the maxillary canine

“…lesions [5], and segmentation of teeth [6,7] and the mental foramen [8]. Regarding periapical radiographs, several applications have been reported, including automatic film mounting [9], teeth detection and numbering [10], and segmentation of teeth and lesions [11].…”

“…In recent years, progress in computer capacity has enabled us to apply deep learning (DL) techniques to the medical and dental fields, and it has been reported to be effective in many applications in the field of oral and maxillofacial radiology, including classification of maxillary sinusitis [ 3 ], object detection of jaw cysts/tumors [ 4 ] and maxillary sinus lesions [ 5 ], and segmentation of teeth [ 6 , 7 ] and the mental foramen [ 8 ]. Regarding periapical radiographs, several applications have been reported, including automatic film mounting [ 9 ], teeth detection and numbering [ 10 ], and segmentation of teeth and lesions [ 11 ].…”

Automated Segmentation of Articular Disc of the Temporomandibular Joint in Magnetic Resonance Images Using Deep Learning: A Proof-of-Concept Study

“…Arti cial intelligence (AI) is gaining attention in various clinical disciplines and the dental eld is no exception, with AI-based applications having been studied to streamline dental and oral care and improve the health of more people at a low cost [8][9][10][11][12] . Such AI-based applications should free dental professionals from time-consuming routine tasks and ultimately promote personalized, predictive, preventive, and participatory dental care 13 .…”