Abstract

Diffusion Tensor Imaging (DTI) is a process to determine the diffusion of water molecules in the body, especially in the brain. This process can be used to extract the neural fibers in the brain. In this study, we proposed an approach for constructing three-dimensional (3D) DTI using Digital Imaging and Communications in Medicine (DICOM) files directly and linear interpolation to improve the quality of neural fibers extraction results. Based on the experimental results, the average amounts of neural fibers generated using our approach are 155534 fibers. Meanwhile, the use of Neuroimaging Informatics Technology Initiative (NIfTI) data that was widely used in recent studies resulted in an average of 117028 fibers. So that there was an increase of 38606 fibers or about 32.9%. In addition, the metadata of the DICOM file is still stored properly and can be used for further 3D image processing. The greater amounts of fibers indicate that the more complete the fibers produced and can be more helpful for doctors to check for abnormalities that may exist.

Original languageEnglish
Title of host publication2021 International Seminar on Machine Learning, Optimization, and Data Science, ISMODE 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages80-85
Number of pages6
ISBN (Electronic)9781665405447
DOIs
Publication statusPublished - 2022
Event2021 International Seminar on Machine Learning, Optimization, and Data Science, ISMODE 2021 - Jakarta, Indonesia
Duration: 29 Jan 2022 → …

Publication series

Name2021 International Seminar on Machine Learning, Optimization, and Data Science, ISMODE 2021

Conference

Conference2021 International Seminar on Machine Learning, Optimization, and Data Science, ISMODE 2021
Country/TerritoryIndonesia
CityJakarta
Period29/01/22 → …

Keywords

  • DICOM
  • Diffusion Tensor Imaging
  • Fiber Tracking
  • Linear Interpolation
  • NIfTI

Fingerprint

Dive into the research topics of 'Constructing 3D Diffusion Tensor Imaging using DICOM Files Directly and Linear Interpolation'. Together they form a unique fingerprint.

Cite this