Artificial Intelligence for Classifying and Archiving Orthodontic Images

Abstract

One of the main requirements for orthodontic treatment is continuous image acquisition. However, the conventional system of orthodontic image acquisition, which includes manual classification, archiving, and monitoring, is time-consuming and prone to errors caused by fatigue. This study is aimed at developing an effective artificial intelligence tool for the automated classification and monitoring of orthodontic images. We comprehensively evaluated the ability of a deep learning model based on Deep hidden IDentity (DeepID) features to classify and archive photographs and radiographs. This evaluation was performed using a dataset of >14,000 images encompassing all 14 categories of orthodontic images. Our model automatically classified orthodontic images in an external dataset with an accuracy of 0.994 and macro area under the curve of 1.00 in 0.08 min. This was 236 times faster than a human expert (18.93 min). Furthermore, human experts with deep learning assistance required an average of 8.10 min to classify images in the external dataset, much shorter than 18.93 min. We conclude that deep learning can improve the accuracy, speed, and efficiency of classification, archiving, and monitoring of orthodontic images.

Application of deep learning artificial intelligence technique to the classification of clinical orthodontic photos

“…There have been attempts to use machine learning methodology to help solve orthodontic problems like automated cephalometric landmarking and surgery versus non-surgery determination [8]. However, there had been a single study [9], to the best of our knowledge, to recognize and classify orthodontic clinical photos. In this study, we used a data augmentation technique with a lesser number of original photos compared to the previous study while maintaining a lightweight model structure.…”

“…Most studies on artificial intelligence related to orthodontics have focused on two [3][4][5] or three dimensional [6] digital radiograph films or numerical analyses with numbers which were already generated by humans [7,8]. However, to the best of our knowledge, only few studies [9] to date have focused on digital orthodontic photographs. Thus, this study might be in the first group regarding artificial intelligence to classify orthodontic digital clinical photos.…”

Application of Artificial Intelligence in Orthodontics: Current State and Future Perspectives

“…During the orthodontic treatment, orthodontists often come across various challenges, including clinical expertise in orthodontics and patient communication and management. The application of AI can help facilitate efficient and effective orthodontic treatment regarding practice guidance, remote care and clinical documentation [152][153][154][155][156][157][158][159][160].…”

Inteligencia artificial en diagnóstico, pronóstico y planificación del tratamiento de alteraciones de la región cráneo-cérvico maxilofacial en ortodoncia. Revisión de la literatura

“…Las imágenes ya editadas ortodónticas las clasifica con una exactitud de 0.994 en un tiempo de 0.08 minutos siendo este 236 veces más rápido que un humano experto requiriendo para su clasificación de aproximadamente 18.09 minutos, sin embargo, hay que tener en cuenta que para el procesado del sistema de IA se necesita un PC con tarjeta gráfica al menos una "NVIDIA RTX 2080Ti". Por lo tanto, se puede decir que el DL mejora la precisión velocidad y eficacia en la clasificación, registro y monitoreo de imágenes ortodónticas (25). Evaluación del estadio de maduración de las vértebras cervicales para determinar la etapa de crecimiento y desarrollo:…”