An automatic MRI/SPECT registration algorithm using image intensity and anatomical feature as matching characters: application on the evaluation of Parkinson's disease

Lee, Jiann-Der; Huang, Chung-Hsien; Weng, Yi-Hsin; Lin, Kun-Ju; Chen, Chin-Tu

doi:10.1016/j.nucmedbio.2007.02.008

Cited by 13 publications

(13 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This work was a first study to check the feasibility of this data adapted strategy and in order to improve the results, additional approaches such as the ones used by SPM or FLIRT (FSL) will be further integrated in this environment. Some additional approaches such as hybrid methods [11,12] coupling MI to feature information could be tested too.…”

Section: Study Limitationmentioning

confidence: 99%

A new strategy to improve coregistration of spect and MR images in patients with high grade glioma

Tacchella¹,

Roullot

Lefort³

et al. 2013

2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

View full text Add to dashboard Cite

This paper proposes a new strategy to optimize the coregistration of Technetium-99m Sestamibi SPECT and MRI data in case of patients with high grade glioma. It consists in a personalized approach which selects, for each data set, the best registration method among several ones. To achieve this selection, a quantitative dedicated evaluation criterion based on the average intensities within specific anatomical structures corresponding to physiological areas of uptake of Sestamibi was defined. The strategy was applied to sixty-two data sets using nine registration methods based on mutual information and chamfer distance registration approaches, with different settings. It was implemented within the Anatomist/Brainvisa environment, using its basic registration functions. The visual evaluation by experts indicated that this strategy provides 60% good quality registrations, and 26% intermediate quality ones. Compared to the single use of the best global registration method, the number of registrations of good quality was multiplied by 1.4 when using the data specific strategy.

show abstract

Section: Study Limitationmentioning

confidence: 99%

A new strategy to improve coregistration of spect and MR images in patients with high grade glioma

Tacchella¹,

Roullot

Lefort³

et al. 2013

2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

View full text Add to dashboard Cite

show abstract

“…The major symptoms of Parkinson's disease involve the motor nervous system, including tremor, rigidity, bradykinesia, shuffling gait, and postural instability. It can also lead to a higher risk of falling, which can cause serious injuries [1][2][3].…”

Section: Introductionmentioning

confidence: 99%

A Preliminary Study of Using Kinect-based Physical Rehabilitation System to Perform Tai Chi Exercises with FLS Evaluation

Lee¹,

Hsieh²,

Lin³

2018

Neuropsychiatry

View full text Add to dashboard Cite

In this study, a physical rehabilitation system based on Kinect sensor is proposed to assist patients with movement disorders to perform the "Tai Chi" exercises at home. With the aid of skeletal tracking of Kinect sensor, each movement of the patient while performing Tai Chi exercises is well recognized and validated. More specifically, patient's movements are compared with the prerecorded movements form a coach, and further evaluated by using fuzzy logic system (FLS). The experiment was carried out according to an ABAB sequence, i.e., A represents the baseline and B represents intervention phases. Experimental results also show that the participants significantly increased their motivation for physical rehabilitation, thus improving exercise performance during the intervention phases.

show abstract

“…In [25, 26], a novel extension of MI was proposed considering the regions of corresponding pixels to provide faster and significant reduction in errors. A new similarity metric combining the anatomical features along with intensity distribution is presented for automated MRI/single‐photon emission computed tomography (SPECT) image registration in [27]. To incorporate the spatial and structural image properties, feature‐based MI plays a significant role [28, 29].…”

Section: Introductionmentioning

confidence: 99%

Enhanced mutual information based medical image registration

Pradhan

Patra

2016

IET Image Processing

View full text Add to dashboard Cite

An automatic MRI/SPECT registration algorithm using image intensity and anatomical feature as matching characters: application on the evaluation of Parkinson's disease

Cited by 13 publications

References 19 publications

A new strategy to improve coregistration of spect and MR images in patients with high grade glioma

A new strategy to improve coregistration of spect and MR images in patients with high grade glioma

A Preliminary Study of Using Kinect-based Physical Rehabilitation System to Perform Tai Chi Exercises with FLS Evaluation

Enhanced mutual information based medical image registration

Contact Info

Product

Resources

About