Affine based image registration applied to MRI brain

Lakshmanan, Annamalai; Ayyachamy, Swarnambiga; Vasuki, S.; Raja, A.

doi:10.1109/icices.2013.6508186

Cited by 3 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MR Scans were first registered to MNI template space using FSL package [6].This was mandatory since all the images are of different sizes and registering them to a common space is required (to maintain homogeneity). All the images can be registered to a common image but we chose MNI since it is a standard template in the literature as mentioned in [9]. The registered scans were then skull-stripped using ROBEX [4] which were further normalized to [0 − 1] intensity values (to avoid the problem of gradients exploding and convergence).…”

Section: Preprocessingmentioning

confidence: 99%

MRI to FDG-PET: Cross-Modal Synthesis Using 3D U-Net for Multi-modal Alzheimer’s Classification

Sikka

Peri

Bathula

2018

Simulation and Synthesis in Medical Imaging

View full text Add to dashboard Cite

Recent studies suggest that combined analysis of Magnetic resonance imaging (MRI) that measures brain atrophy and positron emission tomography (PET) that quantifies hypo-metabolism provides improved accuracy in diagnosing Alzheimer's disease. However, such techniques are limited by the availability of corresponding scans of each modality. Current work focuses on a cross-modal approach to estimate FDG-PET scans for the given MR scans using a 3D U-Net architecture. The use of the complete MR image instead of a local patch based approach helps in capturing non-local and non-linear correlations between MRI and PET modalities. The quality of the estimated PET scans is measured using quantitative metrics such as MAE, PSNR and SSIM. The efficacy of the proposed method is evaluated in the context of Alzheimer's disease classification. The accuracy using only MRI is 70.18% while joint classification using synthesized PET and MRI is 74.43% with a p-value of 0.06. The significant improvement in diagnosis demonstrates the utility of the synthesized PET scans for multi-modal analysis.

show abstract

Section: Preprocessingmentioning

confidence: 99%

MRI to FDG-PET: Cross-Modal Synthesis Using 3D U-Net for Multi-modal Alzheimer’s Classification

Sikka

Peri

Bathula

2018

Simulation and Synthesis in Medical Imaging

View full text Add to dashboard Cite

show abstract

A novel semi-automatic method for accurate registration of FDG_CT and FLT_CT image modalities

Wang

et al. 2015

2015 IEEE Signal Processing in Medicine and Biology Symposium (SPMB)

View full text Add to dashboard Cite

Image Registration Techniques and Frameworks

Chakraborty¹,

Patra²,

Maji³

et al. 2017

Applied Video Processing in Surveillance and Monitoring Systems

View full text Add to dashboard Cite

Image registration allude to transforming one image with reference to another (geometrically alignment of reference and sensed images) i.e. the process of overlaying images of the same scene, seized by assorted sensors, from different viewpoints at variant time. Virtually all large image evaluating or mining systems require image registration, as an intermediate step. Over the years, a broad range of techniques has been flourished for various types of data and problems. These approaches are classified according to their nature mainly as area-based and feature-based and on four basic tread of image registration procedure namely feature detection, feature matching, mapping function design, and image transformation and resampling. The current chapter highlights the cogitation effect of four different registration techniques, namely Affine transformation based registration, Rigid transformation based registration, B-splines registration, and Demons registration. It provides a comparative study among all of these registration techniques as well as different frameworks involved in registration process.

show abstract

Affine based image registration applied to MRI brain

Cited by 3 publications

References 19 publications

MRI to FDG-PET: Cross-Modal Synthesis Using 3D U-Net for Multi-modal Alzheimer’s Classification

MRI to FDG-PET: Cross-Modal Synthesis Using 3D U-Net for Multi-modal Alzheimer’s Classification

A novel semi-automatic method for accurate registration of FDG_CT and FLT_CT image modalities

Image Registration Techniques and Frameworks

Contact Info

Product

Resources

About