Article
Chemistry, Multidisciplinary
Elisson da Silva Rocha, Patricia Takako Endo
Summary: This study compares four segmentation algorithms for dental segmentation in panoramic radiograph and evaluates their results. The DoubleU-Net model performs the best with 96.591% accuracy and 92.886% Dice using the dataset with data augmentation. The Nano-Net model also achieves results close to the literature without data augmentation.
APPLIED SCIENCES-BASEL
(2022)
Article
Dentistry, Oral Surgery & Medicine
Junhua Zhu, Zhi Chen, Jing Zhao, Yueyuan Yu, Xiaojuan Li, Kangjian Shi, Fan Zhang, Feifei Yu, Keying Shi, Zhe Sun, Nengjie Lin, Yuanna Zheng
Summary: This study developed an AI framework based on deep convolutional neural networks for efficient and accurate diagnosis of multiple dental diseases. The framework demonstrated high specificity and efficiency in diagnosing impacted teeth, full crowns, missing teeth, residual roots, and caries. Its performance was similar to or even better than dentists with 3-10 years of experience, indicating the preliminary clinical feasibility, although improvement is needed for caries diagnosis.
Article
Computer Science, Information Systems
Shih-Lun Chen, Tsung-Yi Chen, Yi-Cheng Mao, Szu-Yin Lin, Ya-Yun Huang, Chiung-An Chen, Yuan-Jin Lin, Mian-Heng Chuang, Patricia Angela R. Abu
Summary: This study introduces an advanced identification system using Faster R-CNN to detect seven dental conditions in dental panoramic radiograph (DPR) images. The study shows that including a Butterworth filter and employing enhancement technology tailored to different dental symptoms greatly improves the accuracy of diagnosis, achieving an impressive accuracy rate of 94.18%.
Article
Environmental Sciences
Joanna Janiszewska-Olszowska, Anna Jakubowska, Ewa Gieruszczak, Kacper Jakubowski, Piotr Wawrzyniak, Katarzyna Grocholewicz
Summary: This study evaluated the prevalence of carotid artery calcifications (CACs) on panoramic radiographs of Polish dental patients, finding a rate of 21.68% in patients aged 54 and older. The presence of CACs was more common in women. These results highlight CACs as an important clinical issue in elderly patients.
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
(2022)
Article
Chemistry, Multidisciplinary
Jumi Park, Junseok Lee, Seongyong Moon, Kyoobin Lee
Summary: This study proposes an automated method for detecting missing tooth regions in panoramic radiographic images, assisting clinicians in diagnosing missing teeth regions for implant placement.
APPLIED SCIENCES-BASEL
(2022)
Article
Medicine, General & Internal
Lukasz Zadrozny, Piotr Regulski, Katarzyna Brus-Sawczuk, Marta Czajkowska, Laszlo Parkanyi, Scott Ganz, Eitan Mijiritsky
Summary: The aim of this study was to assess the reliability of AI automatic evaluation of panoramic radiographs. The results showed that the AI protocol had high accuracy in most assessments, and there was high consistency among evaluators. However, the reliability in some aspects was not sufficient.
Article
Radiology, Nuclear Medicine & Medical Imaging
Chunan Zhang, Linfeng Fan, Shisheng Zhang, Jun Zhao, Yingxin Gu
Summary: Periapical and panoramic images can be used to predict the occurrence of implant failure effectively, facilitating early clinical intervention.
QUANTITATIVE IMAGING IN MEDICINE AND SURGERY
(2023)
Article
Biochemistry & Molecular Biology
Shintaro Sukegawa, Kazumasa Yoshii, Takeshi Hara, Tamamo Matsuyama, Katsusuke Yamashita, Keisuke Nakano, Kiyofumi Takabatake, Hotaka Kawai, Hitoshi Nagatsuka, Yoshihiko Furuki
Summary: This study used multi-task deep learning to classify dental implant brands and treatment stages, evaluating five deep convolutional neural network models and finding better performance with deeper networks and more parameters. Multi-task learning significantly improved brand classification and overall accuracy in treatment phase classification.
Article
Dentistry, Oral Surgery & Medicine
Noah H. Menaker, Juan F. Yepes, LaQuia A. Vinson, James E. Jones, Tim Downey, Qing Tang, Gerardo Maupome
Summary: The authors evaluated prescription patterns for bite-wing and panoramic radiographs for pediatric and adolescent dental patients. They found that pediatric dentists were more likely to comply with the guidelines, but there is room for improvement in radiograph prescriptions. Including patient caries risk in insurance claims data could lead to more appropriate administration of dental radiography.
JOURNAL OF THE AMERICAN DENTAL ASSOCIATION
(2022)
Article
Computer Science, Information Systems
Abhishek Gupta, Shailendra Singh Rana, Arshad Eranhikkal, Prashant Kumar
Summary: The objective of this study was to examine the repeatability and reproducibility of landmark localization on panoramic images for PA cephalometric analysis. The study found that the repeatability and reproducibility of panoramic images and PA cephalometric images were good, indicating that they can be used in further experiments. The findings support the use of panoramic radiographs for PA analysis, as the repeatability of landmark placement among appropriately educated observers is sufficient to provide reliable test findings.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Medicine, General & Internal
Jun-Young Cha, Hyung-In Yoon, In-Sung Yeo, Kyung-Hoe Huh, Jung-Suk Han
Summary: Panoramic radiographs, commonly used in dental clinics, present challenges for automated structure detection due to the variety of sizes and shapes. By applying the concept of panoptic segmentation and training a deep neural network model, accurate segmentation of structures like the maxillary sinus and mandibular canal on panoramic radiographs is possible, aiding in diagnosis and treatment planning in dentistry.
JOURNAL OF CLINICAL MEDICINE
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Annika Bertram, Alexander W. Eckert, Ruediger Emshoff
Summary: This study found site-specific underestimations of available horizontal bone dimensions for implants when assessed by PAN, indicating that canines, first, and second premolars may need to be excluded when evaluating root angulations via PAN.
BMC MEDICAL IMAGING
(2021)
Article
Multidisciplinary Sciences
Yifan Zhang, Fan Ye, Lingxiao Chen, Feng Xu, Xiaodiao Chen, Hongkun Wu, Mingguo Cao, Yunxiang Li, Yaqi Wang, Xingru Huang
Summary: This study presents the world's first dataset of children's dental panoramic radiographs for caries segmentation and dental disease detection. A total of 106 pediatric patients aged 2 to 13 years old were included, and efficient and intelligent interactive segmentation annotation software as well as image annotation software were used. Additionally, a segmentation dataset suitable for deep learning was created by combining 93 dental panoramic radiographs of pediatric patients and three internationally published adult dental datasets with a total of 2,692 images.
Article
Medicine, Legal
Eunice Kihara, Ivan Galic, Donna Nyamunga, Fuad Mehdi, Luz Andrea Velandia Palacio, Roberto Cameriere
Summary: This study aimed to validate the accuracy of five different formulas based on the Cameriere method for age estimation in Kenyan children. The findings suggest that the Italian formula provides the best accuracy in dental age estimation for Kenyan children.
INTERNATIONAL JOURNAL OF LEGAL MEDICINE
(2022)
Article
Dentistry, Oral Surgery & Medicine
Noura Alsufyani, Sarah Alnamlah, Sarah Mutaieb, Raseel Alageel, Mayson AlQarni, Areej Bukhari, Maram Alhajri, Abdulrahman AlSubaie, Meshari Alabdulkarim, Asma'a Faden
Summary: This study aimed to utilize virtual reality (VR) in dental radiographic anatomical interpretation in junior dental students and test if it can enhance student learning, engagement, and performance. A VR software for panoramic anatomy was developed and used to teach dental students. The results showed that lecture-based students generally performed better, but VR students showed higher scores in identifying certain anatomical landmarks.
JOURNAL OF DENTAL EDUCATION
(2023)