Detection of Periapical Lesions on Panoramic Radiographs Using Deep Learning

Abstract

Dentists could fail to notice periapical lesions (PLs) while examining panoramic radiographs. Accordingly, this study aimed to develop an artificial intelligence (AI) designed to address this problem. Materials and methods: a total of 18618 periapical root areas (PRA) on 713 panoramic radiographs were annotated and classified as having or not having PLs. An AI model consisting of two convolutional neural networks (CNNs), a detector and a classifier, was trained on the images. The detector localized PRAs using a bounding-box-based object detection model, while the classifier classified the extracted PRAs as PL or not-PL using a fine-tuned CNN. The classifier was trained and validated on a balanced subset of the original dataset that included 3249 PRAs, and tested on 707 PRAs. Results: the detector achieved an average precision of 74.95%, while the classifier accuracy, sensitivity and specificity were 84%, 81% and 86%, respectively. When integrating both detection and classification models, the proposed method accuracy, sensitivity, and specificity were 84.6%, 72.2%, and 85.6%, respectively. Conclusion: a two-stage CNN model consisting of a detector and a classifier can successfully detect periapical lesions on panoramic radiographs.

Detection of the separated endodontic instrument on periapical radiographs using a deep learning‐based convolutional neural network algorithm

“…Periapical radiographs are generally considered the gold standard imaging techniques for diagnosing apical lesions and provide a more detailed view of endodontic pathology than other extraoral radiographic imaging techniques [14]. The data set required for detecting fractured root canal instruments was collected from Karabük Oral and Dental Health Education and Research Hospital.…”

Evaluation of Performance of Artificial Neural Networks in Determination of Mandibular Condil Morphology in Panoramic Radiographies: Methodological Studies

“…4 YSA modelleri, kapsamlı miktarda veri içeren bir derin öğrenme süreci yoluyla, bir bilgisayarın kendi başına düşünmeyi öğrenme, karar verme ve sorunları çözme kapasitesiyle sunulmasını sağlayan bir tür YZ algoritmasıdır. 5 Görüntü segmentasyonu; düz radyografi, bilgisayarlı tomografi, manyetik rezonans ve ultrason görüntüleri dâhil olmak üzere çeşitli yöntemler kullanılarak elde edilen görüntülerdeki çeşitli anatomik yapıları veya lezyonları tanımlamak için kullanılmıştır. Diş hekimliğinde; diş segmentasyonu, yaş tahmini, üçüncü molar dişler ve mandibular alveolar sinir arasındaki ilişkinin tespiti, kistler ve maksiller sinüs gibi klinik durumlar için YZ algoritmalarının uygulandığı çeşitli çalışmalar bildirilmiştir.…”

Artificial Intelligence in Planning Oral Rehabilitations: Current Status

“…In general, digital workflow in dentistry enhances predictability and some of the clinical outcomes, such as dental prosthetic adaptation and trueness, with shorter total treatment times [1]. In this context, artificial intelligence (AI) algorithms have been used to further orient dentists regarding the diagnosis and prognosis of several types of clinical situations [4][5][6][7][8][9][10][11][12][13][14][15].…”

“…Among the main clinical diagnostic applications of AI described in dental research are the detection of anatomical structures [2], caries [4], periapical lesions [5], periodontal bone loss [6], root fractures [7], odontogenic tumors [8], and even malignant diseases [9]. Furthermore, AI has been used to predict periodontal prognosis [10], need of orthodontic treatment [11], and debonding of resin composite crowns [12].…”