Locating Cephalometric Landmarks with Multi-Phase Deep Learning
Journal Title: Journal of Dental Health and Oral Research - Year 2023, Vol 4, Issue 1
Abstract
Cephalometric analysis has long been one of the most helpful approaches in evaluating cranio-maxillo-facial skeletal profile. To perform this, locating anatomical landmarks on an X-ray image is a crucial step, demanding time and expertise. An automated cephalogram analyzer, if developed, will be a great help for practitioners. Artificial intelligence, including machine learning is emerging these days. Deep learning is one of the most developing techniques in data science field. The authors attempted to enhance the accuracy of an automated landmark predicting system utilizing multi-phase deep learning and voting. To guarantee objectivity, an open-to-the-public dataset, cephalometric images accompanied with coordinate values of 19 landmarks, were used. A regressional system was developed, consisted with convolutional neural networks of three phases. First phase network was to determine approximate position of each landmark, inputting whole area of compressed original images. Five secondary networks were to narrow down the area, based on the first phase prediction. Third phase networks were trained by small areas around respective landmarks, with original resolution. Third phase prediction with voting was done inputting 81 shifted areas. Successful detection rates improved as the phase advances. Voting in third phase improved successful detection rate. In comparison with previously reported benchmarks, using the same dataset, proposed system marked better results. Within the physical limitation of memory and computation, multi-phase deep learning may be a solution to deal with large images.
Authors and Affiliations
Soh Nishimoto1*, Kenichiro Kawai1 , Toshihiro Fujiwara1 , Hisako Ishise1 , Masao Kakibuchi1
Keywords
Related Articles
- EP ID EP713268
- DOI https://doi.org/10.46889/JDHOR.2023.4103
- Views 60
- Downloads 0
Revisiting the Concept of Diagonal Pre-cure Splitting of Horizontal Increments in Direct Composite Restorations
The unavoidable, inherent property of polymerization shrinkage in composite resins generates stresses in direct composite restorations which are detrimental to composite material, prepared tooth structure and interfaci...
The Relationship between Self-Rated Proficiency in Orthodontics and Tested Orthodontic Knowledge of Dentists Using Facebook in the United Kingdom
Introduction: There has been a rise in orthodontic treatments being undertaken by dentists in the United Kingdom (UK). Levels of orthodontic education vary, and this may impact upon self-rated proficiency and tested kn...
Lavender Aromatherapy in the Management of Dental Anxiety
Overview: Anxiety in the dental office is a common challenge for the clinicians. Dentophobia is a common cause for reduced motivation and infrequent dental visits for patients with oral diseases. Several techniques to...
Perspectives of Parents regarding the Appropriateness of Physical Restraint Alone or in Conjunction with Sedative Techniques for Managing Challenging Pediatric Dental Behaviour
Purpose: A retrospective look at parents’ responses to having witnessed their children of varying levels of apprehension undergo sedative treatment visits across a 35 year period. Sedation visits with outcomes ranging fr...
Basis for Modern and Standardized Endodontic Therapy
The purpose of this educative work was to evaluate the goal of endodontics, indications and contra-indications of endodontic treatment, criteria of success, causes of failure, as well as one appointment vs. multi...