Enhanced mutual information based medical image registration

Pradhan, Swastik; Patra, Dipti

doi:10.1049/iet-ipr.2015.0346

Cited by 22 publications

(12 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance measure indices that proves of robustness and efficacy are Root Mean square (RMS), Mean Square Error (MSE), and Normalized Absolute Error (NAE). All the performance measures are described in [13].…”

Section: Simulation and Resultsmentioning

confidence: 99%

Non-rigid medical image registration using adaptive knot selection in P-spline

Pradhan¹,

Patra²

2016

2016 IEEE Students’ Technology Symposium (TechSym)

Self Cite

View full text Add to dashboard Cite

In medical imaging application, nonrigid registration is an important step which requires transformation to align the deformed floating image grid points spatially with reference image grids. The transformation includes interpolation which estimates the intensity values of floating image other than the grid points. For nonrigid registration, generally the transformation is modeled using B-spline basis function. As the acquired images are deformed and contains bias field, it is very time consuming to reform the grid at each level. Considering the registration process as an optimization problem, the grid points are adaptively chosen and updated iteratively with a new transformation in each step. In this paper, an adaptive knot placement algorithm is presented for P-spline interpolation method to achieve accurate alignment of local deformation with less computation time. The proposed algorithm is validated with 3 sets of simulated brain images with a known distortion and 2 real brain MR image data sets. Different performance measures such as MSE, RMS, NAE are used to evaluate the qualitative measure of the proposed scheme. Estimated transformation grid and evaluated performance measures show the improvement in the proposed algorithm as compared to the other existing state-of-arts.

show abstract

Section: Simulation and Resultsmentioning

confidence: 99%

Non-rigid medical image registration using adaptive knot selection in P-spline

Pradhan¹,

Patra²

2016

2016 IEEE Students’ Technology Symposium (TechSym)

Self Cite

View full text Add to dashboard Cite

show abstract

“…It compares success rate versus registration error threshold of each method according to statistical results of their 25 runs. Registration error [1] is measured according to difference of mean pixel distance of registered image with respect to reference image b Visualised result. For fair comparison, we take result that corresponds to 80% success rate out of 25 runs for each method…”

Section: Methodsmentioning

confidence: 99%

“…In this Letter, we propose an IR method based on the EMI. The main contribution is that a hybrid optimisation technique is developed to improve the optimisation performance of the method in [1]. The hybrid technique combines the local search capacity of Powell's method and the global search advantage of a popular metaheuristic algorithm called cuckoo search (CS) [8].…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, it is generally regarded as an optimisation problem. Recently, Smita et al proposed a medical IR method [1]. A similarity measure called enhanced mutual information (EMI) is developed in the method, which shows remarkable performance under the optimisation of Powell's method [2].…”

Section: Introductionmentioning

confidence: 99%

“…where p(r) and p(f ) are the marginal probability distributions of the intensity values of R and F, respectively. p(r, f ) and w(r, f ) [1] are the joint probability distributions and joint weighted informations of R and F.…”

mentioning

confidence: 99%

See 2 more Smart Citations