Three-dimensional reconstruction and fusion for multi-modality spinal images

Yuan Tsung Chen, Ming Shi Wang

Research output: Contribution to journalArticlepeer-review

21 Citations (Scopus)

Abstract

Medical diagnosis can benefit from the complementary information in different modality images. Multi-modal image registration and fusion is an essential task in numerous three-dimensional (3D) medical image-processing applications. Registered images are not only providing more correlative information to aid in diagnosis, but also assisting with the planning and monitoring of both surgery and radiotherapy. This research is directed at registering different images captured from Computed Tomography (CT) and Magnetic Resonance (MR) imaging devices, respectively, to acquire more thorough information for disease diagnosis. Because MR bone model segmentation is difficult, this research used a 3D model obtained from CT images. This model accomplishes image registration by optimizing the gradient information accumulated around the bony boundary areas with respect to the 3D model. This system involves pre-processing, 2D segmentation, 3D registration, fusion and sub-system rendering. This method provides desired image operation, robustness verification, and multi-modality spinal image registration accuracy. The proposed system is useful in observing the foramen and nerve root. Because the registration can be performed without external markers, a better choice for clinical usage is provided for lumbar spine diagnosis.

Original languageEnglish
Pages (from-to)21-31
Number of pages11
JournalComputerized Medical Imaging and Graphics
Volume28
Issue number1-2
DOIs
Publication statusPublished - 2004

All Science Journal Classification (ASJC) codes

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Vision and Pattern Recognition
  • Health Informatics
  • Computer Graphics and Computer-Aided Design

Fingerprint Dive into the research topics of 'Three-dimensional reconstruction and fusion for multi-modality spinal images'. Together they form a unique fingerprint.

Cite this