Journal of Dental Pathology and Medicine
Open Access

Dental radiography; Radiographic imaging; Imaging techniques; Intraoral radiography; Extraoral radiography

Introduction

Dental radiographs are used in pediatric dentistry for diagnosis during oral examination of children, as well as as auxiliary diagnostic methods in the detection of caries, dental injuries, tooth development disorders, and examination of pathological conditions.1 Dental radiographs provide critical information on developmental and eruption problems, detection of interface caries, and pulpal and periapical pathologies in clinical examination. The AAPD states that the timing of the first radiographic examination should not be determined by the patient's age but rather by the child's specific circumstances, and that a radiographic examination should not be used to diagnose a disease without a clinical examination.3 Bitewing radiographs from dental radiographs have a dose of MSv, while panoramic radiographs from extraoral radiographs have a dose of 14–24 mSv.4 Despite the low radiation dose, dental radiographs are There are radiographic guidelines that can be used to avoid using dental radiographs in the wrong way and to determine who would benefit from a radiographic examination. In order to reduce the cumulative effect of radiation, the ADA provides some recommendations during radiographic applications. Utilizing the fastest image receptor (F-speed film or digital [photostimulable phosphor PSP plate, charge-coupled device CCD]), collimating the beam to the size of the receptor whenever possible, employing appropriate film exposure and processing techniques, utilizing protective aprons and thyroid collars, and limiting the number of images to the bare minimum required to gather vital diagnostic data are all examples of these [1].

COVID-19 clinical and radiographic manifestations

Mucormycosis is a quickly advancing, entrepreneurial, angioobtrusive contagious contamination that is most normal in safe compromised people.3 It has six kinds of introductions which include: rhino-cerebral, aspiratory, cutaneous, gastrointestinal,scattered, and miscellaneous.4 Rhino-orbito-cerebral structure is much of the time related with uncontrolled diabetes and diabetic ketoacidosis, pneumonic contribution is habitually found in patients with neutropenia, bone marrow and organ transplantation, diabetes, Coronavirus and hematological malignancies, and GIT association is more normal in malnourished individuals. Facial pain and swelling, proptosis, and blurry vision are the initial signs of the rhino-cerebral variant. In later stages, palatal mucosal necrosis and loss of vision may lead to cavernous sinus thrombosis and death. Other symptoms include toothache, maxillary tooth mobility, abscess formation, and jaw movement restriction, which were uncommon before COVID-19 [2].

Dental radiographs

Using dental radiographs, deep learning (DL) teaches a computer how to act like a human. A computer model can learn from unlabeled or unstructured data thanks to this. CNN is a popular deep learning algorithm that can take images as input, give different objects in the image weights and biases, and then tell them apart. The CNN model has been used in the majority of studies. The ability of three distinct CNN architectures to categorize the presence of impacted supernumerary teeth (ISTs) in the maxilla. 550 panoramic radiographs were taken from patients with fully erupted incisors-275 with ISTs and 275 without ISTs-for their study. For the purpose of classification, they applied two models-AlexNet and VGG-16-to their dataset [3]. These two models should arrange the physically trimmed pictures into two classes, with IST or without IST. They manually fed the Region of Interest (ROI) into the model when putting AlexNet and VGG-16 into action. On the other hand, object detection and classification were the primary goals of the third model, known as DetectNet. The model should distinguish the incisor locale, which is the return for capital invested, then, at that point, characterize it either regardless of IST. Their findings revealed that the model with the highest accuracy-96%-that performed the best was DetectNet [4].

Materials and Methods

Participants/Patients: Describe the characteristics of the participants or patients involved in the study, including the sample size, age range, gender distribution, and any specific inclusion or exclusion criteria.

Ethical Considerations: Mention any ethical approvals obtained from relevant institutional review boards or ethics committees. If applicable, state that informed consent was obtained from the participants.

Imaging Equipment: Provide details about the radiographic equipment used, including the make, model, and specifications of the X-ray machines, intraoral or extraoral imaging systems, and any additional devices or accessories used for image acquisition [5].

Imaging Techniques: Describe the specific imaging techniques employed, such as periapical radiography, bitewing radiography, panoramic radiography, or CBCT. Include information about the positioning of the patient, the type and size of film or digital sensors used, and the exposure settings (e.g., kilovoltage, milliamperage, exposure time).

Image Acquisition: Outline the procedures followed for capturing the radiographic images, including the standard anatomical landmarks used for alignment, the number and orientation of the radiographs taken, and any additional instructions given to participants or patients [6].

Image Processing and Analysis: Explain the methods used for processing and analyzing the radiographic images. This may involve techniques such as image enhancement, measurement of relevant parameters, or subjective evaluation by experienced observers or software algorithms.

Statistical Analysis: If applicable, describe the statistical tests or methods used to analyze the data collected from the radiographic images. Provide details about the software or statistical packages used for data analysis. Discuss any limitations or potential sources of bias in the study, such as sample size limitations, technical challenges, or limitations in the imaging technique or analysis methods. If relevant, mention the level of significance used for statistical tests and any adjustments made for multiple comparisons.

Result and Discussion

Results presentation: Present the results in a clear and organized manner, using tables, figures, or graphs as appropriate. Provide a concise summary of the key findings, highlighting the most significant or relevant outcomes of the study [7].

Accuracy and reliability: Discuss the accuracy and reliability of the imaging techniques used. Evaluate the quality of the radiographic images obtained, including factors such as image clarity, resolution, and diagnostic yield. Consider any challenges or limitations encountered during the imaging process and how they may have affected the results.

Diagnostic validity: Evaluate the diagnostic validity of the imaging techniques by comparing the radiographic findings with the reference standard or gold standard for the dental condition or pathology being investigated. Calculate and report relevant diagnostic accuracy measures, such as sensitivity, specificity, positive predictive value, or negative predictive value [8].

Comparison with existing literature: Compare the study findings with previously published literature in the field of dental radiography. Discuss any similarities or differences between the current study and existing research, highlighting the novel aspects or unique contributions of the current study.

Clinical Relevance and Implications: Discuss the clinical relevance and implications of the study findings. Explain how the results contribute to the understanding of dental conditions or pathologies, their diagnosis, and treatment planning. Discuss the potential impact of the findings on patient care, dental practice, or future research directions. Acknowledge and discuss the limitations and challenges encountered during the study. Address any potential sources of bias, confounding factors, or limitations in the study design, imaging techniques, or data analysis methods. Consider the generalizability of the findings and any implications for future research.

Recommendations and Future Directions: Provide recommendations for improving the imaging techniques, protocols, or analysis methods based on the study findings. Suggest potential areas for further research or investigations to address any unresolved questions or limitations identified in the current study [9].

Conclusion

Dental radiography image analysis systems frequently make use of custom feature-based software solutions. Due to the lack of a comprehensive training data set, deep learning could not provide an acceptable solution. Software solutions based on features that have been handcrafted call for a significant amount of computation effort. Calculation ought to be confined inside forefront areas to make those frameworks quicker and to work on the presentation of the customary methodology. As a result, segmenting the dental region from the entire dental radiographic image is crucial. The proposed strategy fragments the teeth areas. Subsequent to sectioning the district of interest, a particular dental sickness recognition calculation can be utilized for additional investigation. The dental radiographic images aren't always clear, so the proposed method sometimes misses some areas of the teeth that are hard to segment [10]. By testing the property of random samples taken from the background regions, the issue can be resolved. The foreground region should not be too close to these background samples. If some samples of the background region contain a significant amount of the properties of the foreground region, those selected regions are reexamined locally for further fine-tuning. To significantly shorten the amount of time spent on computation, random sample methods would be used. The proposed method's dependence on image resolution is one of its major flaws. It can't work the same way on images of different resolutions. For a particular image resolution, the system's parameters must be adjusted. This issue is brought on by the system's use of LBP and other features that are affected by the resolution of the input image. The following automatic abnormalities detection from dental radiographic images is planned for the authors' next phase of work:

• Diagnosing conditions like cancer, tumors, and cysts, among others.

• Development of biometric dental systems.

• Obtaining information about broken or missing teeth, for example.

• Removing features one tooth at a time.

Acknowledgement

None

1. Kleber M, Ihorst G, Gross B, Koch B, Reinhardt H, et al. (2013) Validation of the Freiburg comorbidity index in 466 multiple myeloma patients and combination with the international staging system are highly predictive for outcome. Clin Lymphoma Myeloma Leuk 5:541-551.

Indexed at, Google Scholar, Crossref

2. Carrozzo M, Francia Di Celle P, Gandolfo S, et al. (2001)Increased frequency of HLA-DR6 allele in Italian patients with hepatitis C virus-associated oral lichen planus. Br J Dermatol 144(4):803-8.

Indexed at, Google Scholar, Crossref

3. Canto AM, Müller H, Freitas RR, Santos PS (2010) Oral lichen planus (OLP): clinical and complementary diagnosis. An Bras Dermatol 85:669-75.

Indexed at, Google Scholar, Crossref

4. Eisen D (1999) The evaluation of cutaneous, genital, scalp, nail, esophageal, and ocular involvement in patients with oral lichen planus. Oral Surg Oral Med Oral Pathol Oral Radiol Endod 88:431-6.

Indexed at, Google Schpolar, Crossref

5. Panchbhai AS (2012) Oral health care needs in the dependant elderly in India. Indian J Palliat Care 18:19.

Indexed at, Google Scholar, Crossref

6. Soini H, Routasalo P, Lauri S, Ainamo A (2003) Oral and nutritional status in frail elderly. Spec Care Dentist 23:209-15.

Indexed at, Google Scholar, Crossref

7. Vissink A, Spijkervet FK, Amerongen VA (1996) Aging and saliva: Areview of the literature. Spec Care Dentist 16:95103.

Indexed at, Google Scholar, Crossref

8. Bron D, Ades L, Fulop T, Goede V, Stauder R (2015) Aging and blood disorders: new perspectives, new challenges. Haematologica 4:415-417.

Indexed at, Google Scholar, Crossref

9. Thornhill MH, Sankar V, Xu XJ, Barrett AW, High AS, et al. (2006) The role of histopathological characteristics in distinguishing amalgam-associated oral lichenoid reactions and oral lichen planus. J Oral Pathol Med 35:233-40.

Indexed at, Google Scholar, Crossref

10. Hiremath SK, Kale AD, Charantimath S (2011) Oral lichenoid lesions: clinico-pathological mimicry and its diagnostic implications. Indian J Dent Res 22:827-34.

Indexed at, Google Scholar, Crossref