Dental imaging is one of the most difficult and recent areas of medical imaging. The maxillofacial area is densely populated by overlapping complex structures, often very small. In addition to this, the teeth vary significantly in shape and position, creating additional obstacles for image segmentation. As a result, dental image analysis it requires advanced feature extraction and segmentation techniques and, in many cases, 3D reconstruction.
Computer vision applications in dentistry
Medical imaging analysis deals primarily with diagnostic issues, supporting diagnoses in their decisions; however, dentistry provides at least one more application for some image analysis techniques, which is computer aided design and computer aided manufacturing systems (CAD / CAM).
Of course, CAD / CAM systems use only some of the image analysis techniques, such as image preprocessing and semi-automated image segmentation, but these systems are one of the most important trends in dentistry. modern, and this apparently makes them one of the best dental. image analysis applications.
However, computer-assisted diagnosis is the second major use of dental imaging analysis. Computer vision can be used to identify caries lesions and signs of periodontitis, as well as maxillary sinusitis, osteoporosis, and other pathologies.
Computer vision also applies to cephalometric analysis and the classification of teeth for both theoretical and practical purposes.
CAD / CAM systems
Introduced in the 1980s as an uncomfortable novelty, CAD / CAM systems have since become an avant-garde orthodontic and dental surgery technique that provides a fast and reliable method for dental restoration.
CAD / CAM systems use intraoral or CBCT cameras to reconstruct a 3D image of the dental arch and provide the information needed to design and create dental prostheses and orthodontic appliances. He CAM part means that the system creates the necessary prostheses at the time, allowing the manipulation to be performed in a single day.
According to the latest Technavio’s market research, the global dental CAD / CAM market is constantly growing at an estimated CAGR of more than 8% in 2021, and a key trend to drive its growth is the shift towards open architecture software that allows for more flexibility.
As the most common tool based on medical image analysis, computer-aided diagnosis (CAD) The systems support radiologists and dentists in their work, often significantly improving the accuracy and speed of diagnosis.
From the reference match, CAD systems are already used for caries diagnosis. Some researchers have reported that the rate of true positive results almost doubles (from 39% to 69%) in caries detection when it is compatible with a CAD system. Another investigation has shown less optimistic results due to tooth segmentation problems.
However, identifying caries lesions is one of the most common tasks in conservative dentistry, and partial automation of this process would be of great benefit to physicians, so this problem definitely requires more attention.
2) Endodontic diagnosis
The presence or absence of inflammatory changes in the dental pulp is crucial to the tooth treatment plan. To decide on dental depulpation, dentists can also seek advice on the CAD system.
Several recent research papers propose multi-faceted approaches to the problem of pulp and root canal segmentation, such as linear prediction model for the extraction of the root canal edge i fuzzy c-means grouping for root canal segmentation into high-resolution micro-CT registers.
Periodontitis, an inflammatory disease of the soft tissues surrounding the teeth, can be even harder to detect on simple dental x-rays. To be successful, highly sensitive edge detection and segmentation techniques must be applied.
To address the problem of automated detection of periodontitis, Chinese researchers suggested a combination of semi-supervised fuzzy clustering algorithms for dental X-ray image segmentation. The proposed system worked much better than conventional segmentation techniques, although the authors admit that there is still room for improvement.
4) Maxillary sinusitis
Dental infections often cause inflammation of the maxillary sinuses due to the anatomical peculiarities of this area, and it is important that even inexperienced dentists can detect this complication on simple panoramic x-rays. It is not easy, as panoramic dental images are not intended to diagnose sinus pathology, and overlapping structures often make it difficult to recognize sinusitis.
An investigation conducted in Japan in 2016 showed that CAD systems make the difference in this case, increasing the diagnostic accuracy of neophyte dentists to that of their experienced colleagues. After filtering and segmenting the initial image, the system performs the recording of the reflected sinus regions to detect the difference in opacity. Although this technique can only be applied to the diagnosis of unilateral sinusitis, it remains a promising direction.
Although the gold standard for the detection of osteoporosis is dual energy X-ray (DXA) absorption, bone mineral density can also be measured in the area of the mandibular condyle (a part of the lower jaw). Because panoramic dental x-ray is much easier to access than DXA, many doctors see it as a promising method for detecting osteoporosis.
A recent investigation has shown that by using imaging techniques to determine ROIs, extract features, and classify data obtained from panoramic radiographs, it is possible to achieve at least 88% accuracy in the detection of osteoporosis.
Although calcification of the carotid artery is not immediately related to dentistry, it can be detected on dental panoramic radiographs. By defining two more ROIs (for both sides) on a panoramic x-ray, an image analysis system can easily detect calcification with image filtering and grayscale threshold.
This “incidental discovery” is of vital importance, as it indicates that the patient has a high risk of stroke, so adding this feature to a CAD system for panoramic X-ray analysis would provide an immense benefit.
Dentists, orthodontists, and oral-maxillofacial surgeons analyze the anatomical milestones of the head when planning treatment. There is an even broader interest in this area, as cephalometry can also be used for various purposes, for example, to plan childbirth and childbirth in obstetrics.
However, manual cephalometric analysis requires significant time, making it a good candidate for automation. Medical imaging systems can dramatically increase the speed and efficiency of detecting anatomical milestones.
In accordance with a recent survey performed by an international collaboration, automated detection of caries lesions in bite X-ray images remains a major challenge. The key problem is the segmentation of dental structures, because the variation in the data is high and the teeth are sometimes mislabeled as background.
Another important challenge outlined in the same article takes into account cephalometric analysis. Although the accuracy of automated detection of anatomical milestones has increased in the last 7 years, it is still below 90%.
With the development of image processing and machine learning algorithms, the success rate of both caries detection and cephalometric analysis will increase.
Trends and growth options
As CAD / CAM systems are among the key trends in dentistry worldwide, the demand for image preprocessing techniques and segmentation algorithms will grow. And the shift to open architecture indicates that it will be easier for CAD / CAM manufacturers to order software tailored to their specific needs.
Speaking of imaging techniques, the palm of victory belongs to computed tomography of the cone beam, which is another key trend in dentistry. In the near future, CBCT with CAD imaging systems can become the most efficient diagnostic tool in dentistry.
In addition to this, the global trend of artificial neural networks, fuzzy logic systems, random forests, and other intelligent algorithms that can be used to group and classify images creates new opportunities for dental image analysis. An additional improvement in their performance will improve the accuracy of CAD systems and allow the automation of the most difficult cases.
1.Tracy KD, Dykstra BA, Gakenheimer DC, Scheetz JP, Lacina S, Scarfe WC, et al. Usefulness and effectiveness of computer-assisted diagnosis of dental caries. General Dentistry (2011).
2.C.-W. Wang et al. A benchmark for comparing dental radiography analysis algorithms. Medical Image Analysis 31 (2016) 63’76.
3. T. Sawagashira, T. Hayashi, T. Hara, A. Katsumata, C. Muramatsu, X. Zhou, et al. A method of automatic detection of carotid artery calcifications by cup hat filter on dental panoramic radiographs. IEICE Trans Inform Syst, E96-D (8) (2013), p. 1878’1881