Machine Learning-Based Noise Reduction for Craniofacial Bone Segmentation in CT Images

Journal Title: Journal of Dental Health and Oral Research - Year 2023, Vol 4, Issue 1

Abstract

Objective: When high X-ray absorption rate materials such as metal prosthetics are in the field of CT scan, noise called metal artifacts might appear. In reconstructing a three-dimensional bone model from X-ray CT images, the metal artifacts remain. Often, the image of the scanning bed also remains. A machine learning-based system to reduce noises in the craniofacial CT images was constructed. Methods: DICOM images of CT archives of patients with head and neck tumors were used. The metal artifacts and beds were removed from the threshold segmented images to obtain the target bony images. U-nets, respectively with the function loss of mean squared error, Dice and Jaccard, were trained by the datasets consisting of 5671 DICOM images and corresponding target images. DICOM images of 2000 validation datasets were given to the trained models and predicted images were obtained. Results: The use of mean squared errors presented superiority to Dice or Jaccard loss. The mean prediction error pixels were 14.43, 778.57, and 757.60 respectively per 512 x 512 pixeled image. Conclusion: Automatic CT image noise reduction system was constructed. Dedicated to the delineation of craniofacial bones, the presented study showed high prediction accuracy. The “correctness” of the predictions made by this system may not be guaranteed, but the results were generally satisfactory.

Authors and Affiliations

Soh Nishimoto, Takuya Saito, Hisako Ishise, Toshihiro Fujiwara, Kenichiro Kawai, Maso Kakibuchi

Keywords

Related Articles

Mandibular Brown Tumor Linked to Tertiary Hyperparathyroidism: A Case Report

Introduction: Brown Tumors (BT) are rare, non-neoplastic, osteolytic lesions associated with Hyperparathyroidism (HPT). BTs are rare in the craniofacial region and diagnosis is uncommon in children. Case report: A nin...

Failure Rates of Tooth-Supported Crown Restorations in an Academic Dental Center

Background: Accurate documentation of tooth-supported crown restoration failures is crucial for assessing dental care quality. At the University of Michigan School of Dentistry, failure rates from Electronic Health Recor...

Effect of Smoking and Periodontal Diseases on Salivary Glycoconjugates and Oxidative Stress Markers-A Comparative Study

Background and Objectives: The most important feature in periodontal disease is degradation of extracellular matrix, resulting in elevated levels of various salivary biomarkers in periodontal diseases. Smoking results...

Correlation of Prevalence and Symptom Severity of Temporomandibular Disorders Among Healthy Individuals and Patients with Newly Diagnosed Rheumatic Diseases

Objective: The objective of this study was to assess the prevalence and severity of temporomandibular disorders in patients with rheumatic diseases at the initial stage of diagnosis, prior to any medication and to compar...

Applicability of Infrared Thermography in Dentistry: Mini Review

Infrared thermography is a precise, non-invasive and safe method for measuring superficial temperature, with increasing application in different areas of dentistry, such as endodontics, implantology, restorative dentistr...

Download PDF file
  • EP ID EP714378
  • DOI https://doi.org/10.46889/JDHOR.2023.4106
  • Views 54
  • Downloads 0

How To Cite

Soh Nishimoto, Takuya Saito, Hisako Ishise, Toshihiro Fujiwara, Kenichiro Kawai, Maso Kakibuchi (2023). Machine Learning-Based Noise Reduction for Craniofacial Bone Segmentation in CT Images. Journal of Dental Health and Oral Research, 4(1), -. https://europub.co.uk/articles/-A-714378