MR Image-Based Attenuation Correction of Brain PET Imaging: Review of Literature on Machine Learning Approaches for Segm
- PDF / 1,472,329 Bytes
- 18 Pages / 595.224 x 790.955 pts Page_size
- 103 Downloads / 158 Views
REVIEW
MR Image-Based Attenuation Correction of Brain PET Imaging: Review of Literature on Machine Learning Approaches for Segmentation Imene Mecheter1,2
· Lejla Alic3 · Maysam Abbod1 · Abbes Amira4 · Jim Ji2,5
© The Author(s) 2020
Abstract Recent emerging hybrid technology of positron emission tomography/magnetic resonance (PET/MR) imaging has generated a great need for an accurate MR image-based PET attenuation correction. MR image segmentation, as a robust and simple method for PET attenuation correction, has been clinically adopted in commercial PET/MR scanners. The general approach in this method is to segment the MR image into different tissue types, each assigned an attenuation constant as in an X-ray CT image. Machine learning techniques such as clustering, classification and deep networks are extensively used for brain MR image segmentation. However, only limited work has been reported on using deep learning in brain PET attenuation correction. In addition, there is a lack of clinical evaluation of machine learning methods in this application. The aim of this review is to study the use of machine learning methods for MR image segmentation and its application in attenuation correction for PET brain imaging. Furthermore, challenges and future opportunities in MR image-based PET attenuation correction are discussed. Keywords MR image-based attenuation correction · Image segmentation · Machine learning · Deep learning · PET/MR
Introduction Positron emission tomography (PET) is an imaging modality that provides direct imaging of physiological biomarkers using radiolabeled gamma-ray emitting molecules. The knowledge of the tissue-dependent attenuation map, needed for attenuation correction, is a critical step to achieve an accurate PET image reconstruction. Figure 1 shows the effect of attenuation correction on reconstructed PET Imene Mecheter
[email protected] 1
Department of Electronic and Computer Engineering, Brunel University London, Uxbridge, UK
2
Department of Electrical and Computer Engineering, Texas A & M University at Qatar, Doha, Qatar
3
Magnetic Detection and Imaging Group, Faculty of Science and Technology, University of Twente, Enschede, Netherlands
4
Institute of Artificial Intelligence, De Montfort University, Leicester, UK
5
Department of Electrical and Computer Engineering, Texas A & M University, College Station, TX, USA
images. The attenuation map is usually obtained by performing an additional scan using X-ray computed tomography (CT) [1]. CT image intensity measured in the Hounsfield unit is a map of the normalized X-ray attenuation coefficients, which reflects the anatomical, physiological and pathological states of the underlying tissues. Therefore, the CT image can be mathematically converted to the equivalent linear X-ray attenuation coefficients [2, 3]. Since X-rays and gamma-rays have similar attenuations in biological tissues, X-ray CT is the most straightforward way for PET attenuation correction. However, it introduces additional ionizing radiations to
Data Loading...
