Non-rigid medical image registration using image field in Demons algorithm

Lan, Sheng; Guo, Zhenhua; You, Jane

doi:10.1016/j.patrec.2019.04.006

Cited by 15 publications

(23 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To obtain the deformation fields of medical images, the velocity field of demons was evaluated. In 2016, Lan et al [ 43 ] proposed a comparative analysis of all demons registration, which proved that Wang’s demons [ 43 ] was superior in terms of performance than Thirion’s and Tang’s demons.…”

Section: Literature Surveymentioning

confidence: 99%

“…The Gaussian smoothening kernel σ is applied in demons, which is a variable parameter. To calculate the value of

, the following formula is applied [ 30 , 43 ]:

where

is the gradient information of the reference image. The gradient information are calculated using

The default values of the registration parameters as defined by Thirion are listed in Table 1 .…”

Section: Non-rigid Image Registration Using Demons Algorithmmentioning

confidence: 99%

“…Since the analysis of the general range of parameters was still missing in demons registration, Tang et al [ 4 ] introduced a balance coefficient k in Tang’s demons to solve this problem. The adaptation of the balance coefficient is managed to adjust the demons force and its strength, where the Tang’s demons force is represented by [ 28 , 43 ]:

where

and

are the gradient field information unit vectors of the reference image ( R ), and fixed image ( F ), respectively. The Tang’s demons force is given by:

…”

Section: Non-rigid Image Registration Using Demons Algorithmmentioning

confidence: 99%

“…Thus, despite the balance coefficient k, Wang’s demons proved its efficiency compared to the Tang’s demons [ 43 ]. The unit vectors of the gradient field are managed to simplify the Thirion’s demons leading to producing worse results than Wang’s demons.…”

Section: Non-rigid Image Registration Using Demons Algorithmmentioning

confidence: 99%

“…The current work focuses on reducing the registration error as well as the time complexity in order to get rid of the problem raised by processing on large chunk of images in retinal image database, that takes a large amount of time. A comparative study is conducted with the cuckoo search- [ 10 ], firefly algorithm [ 43 ], and particle swarm optimization- [ 9 ] based demons registration [ 44 , 45 , 46 ] framework.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Grey-Wolf-Based Wang’s Demons for Retinal Image Registration

Chakraborty

Pradhan

Ashour

et al. 2020

Entropy

View full text Add to dashboard Cite

Image registration has an imperative role in medical imaging. In this work, a grey-wolf optimizer (GWO)-based non-rigid demons registration is proposed to support the retinal image registration process. A comparative study of the proposed GWO-based demons registration framework with cuckoo search, firefly algorithm, and particle swarm optimization-based demons registration is conducted. In addition, a comparative analysis of different demons registration methods, such as Wang’s demons, Tang’s demons, and Thirion’s demons which are optimized using the proposed GWO is carried out. The results established the superiority of the GWO-based framework which achieved 0.9977 correlation, and fast processing compared to the use of the other optimization algorithms. Moreover, GWO-based Wang’s demons performed better accuracy compared to the Tang’s demons and Thirion’s demons framework. It also achieved the best less registration error of 8.36 × 10−5.

show abstract

Section: Literature Surveymentioning

confidence: 99%

“…The Gaussian smoothening kernel σ is applied in demons, which is a variable parameter. To calculate the value of

, the following formula is applied [ 30 , 43 ]:

where

is the gradient information of the reference image. The gradient information are calculated using

The default values of the registration parameters as defined by Thirion are listed in Table 1 .…”

Section: Non-rigid Image Registration Using Demons Algorithmmentioning

confidence: 99%

where

and

are the gradient field information unit vectors of the reference image ( R ), and fixed image ( F ), respectively. The Tang’s demons force is given by:

…”

Section: Non-rigid Image Registration Using Demons Algorithmmentioning

confidence: 99%

Section: Non-rigid Image Registration Using Demons Algorithmmentioning

confidence: 99%