Dr. Ahmed Abdelkarim , Dr. Ali Syed , Dr. Sonali Rathore
{"title":"Deep learning image quality improvement in cone beam computed tomography using the super-resolution technique","authors":"Dr. Ahmed Abdelkarim , Dr. Ali Syed , Dr. Sonali Rathore","doi":"10.1016/j.oooo.2024.11.059","DOIUrl":null,"url":null,"abstract":"<div><h3>Objective</h3><div>This poster presents the ability of a convolutional neural network to generate image quality−enhanced images of the microstructure trabecular pattern of the temporomandibular region. The rationale of this aim is to validate the network capability to train the software to improve the low-resolution images.</div></div><div><h3>Study Design</h3><div>Five cone beam computed tomography (CBCT) scans will be obtained for the mandible phantom using 2 CBCT scanners. The scanning protocols employed in the project consisted of 4 of the existing protocols suggested by the manufacturer. In this project, the 3-dimensional U-Net architecture will be used for super-resolution processing.</div></div><div><h3>Results</h3><div>The high-resolution CBCT images will successfully enhance the image quality characteristics of the low-resolution input data using the 3-dimensional U-Net architecture.</div></div><div><h3>Conclusion</h3><div>With the successful implementation of this validation study, this method will be used as an index for diseases with trabecular bone changes, such as medication-related osteonecrosis of the jaw and identification of pathologies.</div></div>","PeriodicalId":49010,"journal":{"name":"Oral Surgery Oral Medicine Oral Pathology Oral Radiology","volume":"139 3","pages":"Page e90"},"PeriodicalIF":2.0000,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Oral Surgery Oral Medicine Oral Pathology Oral Radiology","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2212440324008526","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"DENTISTRY, ORAL SURGERY & MEDICINE","Score":null,"Total":0}
引用次数: 0
Abstract
Objective
This poster presents the ability of a convolutional neural network to generate image quality−enhanced images of the microstructure trabecular pattern of the temporomandibular region. The rationale of this aim is to validate the network capability to train the software to improve the low-resolution images.
Study Design
Five cone beam computed tomography (CBCT) scans will be obtained for the mandible phantom using 2 CBCT scanners. The scanning protocols employed in the project consisted of 4 of the existing protocols suggested by the manufacturer. In this project, the 3-dimensional U-Net architecture will be used for super-resolution processing.
Results
The high-resolution CBCT images will successfully enhance the image quality characteristics of the low-resolution input data using the 3-dimensional U-Net architecture.
Conclusion
With the successful implementation of this validation study, this method will be used as an index for diseases with trabecular bone changes, such as medication-related osteonecrosis of the jaw and identification of pathologies.
期刊介绍:
Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology is required reading for anyone in the fields of oral surgery, oral medicine, oral pathology, oral radiology or advanced general practice dentistry. It is the only major dental journal that provides a practical and complete overview of the medical and surgical techniques of dental practice in four areas. Topics covered include such current issues as dental implants, treatment of HIV-infected patients, and evaluation and treatment of TMJ disorders. The official publication for nine societies, the Journal is recommended for initial purchase in the Brandon Hill study, Selected List of Books and Journals for the Small Medical Library.