Diagnosis is important and challenging in dentistry. Dental caries and diseases are the most prevalent chronic dental diseases worldwide [1]. Periapical tissue diseases are localized, diffuse, liquefaction lesions that occur as an inflammatory response to tooth infection and necrotic pulp or non-microbial causes. Pulpal and periodontal infections can affect the alveolar bone, and they can spread to distant structures from the oral cavity via bone marrow, cortical bone and periosteum [2]. Therefore, many techniques have been developed for the diagnosis of dental caries and infections. Visual and tactile examination and radiographs (panoramic, bitewing, periapical) are usually used to diagnose caries and infections [3]. In addition, transillumination is one of the oldest caries diagnosis methods. Based on this principle, various diagnostic technologies have been developed (Foti, Difoti, Nilt, Diagnodent, Diagnopen) [4].
As technology has advanced, artificial intelligence (AI) has taken on important roles in health, providing convenience and superior success in several areas, with evident potential in diagnosis. Artificial intelligence continues to be researched and developed to facilitate the diagnosis of dental caries and infections, which are frequently encountered [5].
The application of artificial intelligence is aimed towards obtaining the best results in dentistry, patient examination, and treatments. It has been used to make diagnosis more accurate and efficient. The diagnostic speed of artificial intelligence has a significant advantage when compared to dentists, reducing the time spent in the dental chair and the associated stress levels, of particular benefit to pediatric and adult patients with anxiety problems [6]. To offer the best diagnosis, the most appropriate treatment plan and to predict the prognosis, dentists must draw on all their academic knowledge; however, in some cases, their knowledge may be insufficient [7].
There is no general-purpose artificial intelligence, and no general solution method to serve as a comprehensive expert algorithm. Different solution methods are chosen for different tasks. Many tasks address mainly auditory and textual data that concern visual and natural language. Among the many AI technologies, classification is often handled by artificial neural networks (ANNs), and of the subtype called convolutional neural networks (CNNs).
ANNs start by assigning random weights to the connections between neurons, and, through the learning process, re-sets those weights so that the ANN mechanism works correctly. Each layer of an image recognition ANN conducts an abstraction process lines and corners are distinguished in the first layer, curvatures can be detected in later layers. Adding convolution to the network shifts the attention to low-level mechanisms such as curves and edges in an image5. As the network proceeds to learn, redundant data can be deleted, and, finally, the information is condensed into a one-dimensional vector by a fully interconnected layer. Once trained, the ANN is given an input image, and produces an output that indicates the presence of certain objects [8].
CNN has already been the subject of much dental research on orthodontics and dentofacial orthopaedics [9], endodontics [10], periodontology [8], oral and maxillofacial surgery [11], forensic odontology [12] and especially dento-maxillofacial radiology and diagnostic studies [13-15].
This new dental artificial intelligence programme is software that aims to interpret radiographs with high success by using successful deep neural network architectures such as Fast R-CNN, Faster R-CNN, SSD, and YoLo. For this purpose, a large training and test data set is created from the radiological images which made over 5100 adult and 4800 pedodontic panoramic x-ray images. All dental and gingival problems in these images have been labeled in detail by the five specialist dentists who are two endodontists, two pedodontists and one oral, dental and maxillofacial radiologist in the project team. Existing treated deep architectures are adapted to panoramic x-ray images using a transfer learning approach and subjected to an extensive training process. Python-based Keras, Tensorflow, and Caffe deep learning environments are used for algorithm development in this ai system. It can apply World Dental Federation (FDI) notation to teeth and detect diseases on adult and pediatric radiographs which exhibit periodontal hard tissue loss, detection of dental periapical infection, missing tooth, caries, impacted tooth (especially third molar), and can detect immature tooth, supernumerary tooth, erupting tooth, permanent tooth germ, etc. (Fig. 1).
Annotation of caries or periapical infections in the maxillo-mandibular area of panoramic radiographs were detected by specialist dentists. The LabelImg program was used to manually delineate and label the bounding boxes around locations of caries (Fig. 2A) and infections (Fig. 2B). These labelled radiographs were used to assess the success rate of the new AI application, by comparison with diagnoses from three junior dentists and two specialist dentists. True diagnosis, misdiagnosis, underdiagnosis and diagnostic duration were compared between all three groups.