Swarm Intelligence Algorithms for Medical Image Registration: A Comparative Study

Sarvamangala, D. R.; Kulkarni, Raghavendra V.

doi:10.1007/978-981-10-6430-2_35

Cited by 7 publications

(6 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Still, one of the essential processes in 3-D image reconstruction is image registration. In the literature, there exist some 2-D medical image registration research works [8][9][10][11][12]. However, in our case, the 3-D registration is more suitable.…”

Section: Introductionmentioning

confidence: 88%

Three-Dimensional Tooth Model Reconstruction Using Statistical Randomization-Based Particle Swarm Optimization

et al. 2021

View full text Add to dashboard Cite

The registration between images is a crucial part of the 3-D tooth reconstruction model. In this paper, we introduce a registration method using our proposed statistical randomization-based particle swarm optimization (SR-PSO) algorithm with the iterative closet point (ICP) method to find the optimal affine transform between images. The hierarchical registration is also utilized in this paper since there are several consecutive images involving in the registration. We implemented this algorithm in the scanned commercial regular-tooth and orthodontic-tooth models. The results demonstrated that the final 3-D images provided good visualization to human eyes with the mean-squared error of 7.37 micrometer2 and 7.41 micrometer2 for both models, respectively. From the results compared with the particle swarm optimization (PSO) algorithm with the ICP method, it can be seen that the results from the proposed algorithm are much better than those from the PSO algorithm with the ICP method.

show abstract

Section: Introductionmentioning

confidence: 88%

Three-Dimensional Tooth Model Reconstruction Using Statistical Randomization-Based Particle Swarm Optimization

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Let S be the sensed image and we denote by T the target. The images have the same size, M × N. The accuracy of the registration method is measured through the success rate and using the similarity between T and the result of applying the alignment process on S, denoted by T. We evaluate the similarity between T and T using two metrics commonly used in image processing, signal-to-noise-ratio (SNR) and peak-signal-to-noise ratio (PSNR), and two entropic measures, Shannon normalized mutual information defined by ( 4) and Tsallis normalized mutual information given by (9). The values SNR T, T and PSNR T, T are given by SNR T, T = 10 * log 10…”

Section: Efficiency Measuresmentioning

confidence: 99%

“…All kinds of bio-inspired algorithms are used in reported works, from GA [8,9] and evolutionary algorithms (EA) [7] to newer approaches that employ hybridizations and metaheuristics.…”

Section: Introductionmentioning

confidence: 99%

“…The GA approach is compared to the artificial bee colony (ABC) approach in [9], highlighting the advantages of each algorithm: while GA is faster, ABC gives better quality of image registration. Another comparison between GA and swarm approach, using the correlation function of two images to estimate the quality of registration process, is reported in [12] with the conclusion that the PSO approach provides superior results.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cluster-Based Memetic Approach of Image Alignment

Cocianu

Uscatu

2021

Electronics

View full text Add to dashboard Cite

The paper presents a new memetic, cluster-based methodology for image registration in case of geometric perturbation model involving translation, rotation and scaling. The methodology consists of two stages. First, using the sets of the object pixels belonging to the target image and to the sensed image respectively, the boundaries of the search space are computed. Next, the registration mechanism residing in a hybridization between a version of firefly population-based search procedure and the two membered evolutionary strategy computed on clustered data is applied. In addition, a procedure designed to deal with the premature convergence problem is embedded. The fitness to be maximized by the memetic algorithm is defined by the Dice coefficient, a function implemented to evaluate the similarity between pairs of binary images. The proposed methodology is applied on both binary and monochrome images. In case of monochrome images, a preprocessing step aiming the binarization of the inputs is considered before the registration. The quality of the proposed approach is measured in terms of accuracy and efficiency. The success rate based on Dice coefficient, normalized mutual information measures, and signal-to-noise ratio are used to establish the accuracy of the obtained algorithm, while the efficiency is evaluated by the run time function.

show abstract

“…[154] Rigid PSO with use of initial orientation for avoiding convergence of the swarm [155] Nonrigid Quantum-behaved particle swarm optimization [154] Review [156] Rigid PSO is used for locating the area of the global optimum and, then, Powell's method of minimization is used for fine tuning. [157] Rigid+Scaling [158] Rigid+Scale Use of fixed inertia weight for the adjustment of the particle velocity. [159] Rigid inclusion of an unscented Kalman filter to guide particle motion, thus increasing the speed of convergence and reducing the likelihood of premature convergence…”

Section: Particle Swarm Optimizationmentioning

confidence: 99%

Novel and robust methods for the automatic registration of image data

Spanakis¹,

Σπανάκης²

View full text Add to dashboard Cite

Η Ταύτιση εικόνων είναι η διαδικασία του γεωμετρικού μετασχηματισμού δύο ή περισσότερων εικόνων με σκοπό τα κοινά τους σημεία να έχουν την ίδια θέση στο χώρο, κι έχει πολλές εφαρμογές όπως στην Ιατρική απεικόνιση, Remote Sensing και Συρραφή Εικόνων (Image Stitching). Παρά την επιστημονική πρόοδο που έχει επιτευχθεί τα τελευταία 40 χρόνια, εξακολουθούν να υπάρχουν άλυτα θέματα που σχετίζονται με Ακρίβεια, Υπολογιστικό Κόστος, Σύγκλιση σε τοπικά μέγιστα και διαδικασίες Αυτοματισμού των αριθμητικών μεθόδων ταύτισης εικόνων. Αυτά με την σειρά τους επηρεάζονται από το Μέτρο Ομοιότητας των εικόνων, τον Γεωμετρικό Μετασχηματισμό και την Μέθοδο βελτιστοποίησης που χρησιμοποιούνται. Οι μαθηματικές/στατιστικές μέθοδοι για την σύγκριση εικόνων έχουν αποδειχθεί πολύ αποτελεσματικότερες των μεθόδων που χρησιμοποιούν χαρακτηριστικά των εικόνων όπως τα σημεία τους. Επιπλέον, απαιτούν ελάχιστη (αν όχι καθόλου) προεπεξεργασία των εικόνων, πράγμα που τις καθιστά αυτόματες. Επειδή χρησιμοποιούν ένα σημαντικό τμήμα των εικόνων για την εκτίμηση της ομοιότητας, καθίστανται υπολογιστικά πολύ ακριβές ιδιαίτερα όταν χρειαστεί να γίνει εκτενής αναζήτηση του βέλτιστου μετασχηματισμού. Στα πλαίσια της διατριβής αυτής, έγινε εκτενής έρευνα σχετικά με τις Μεθόδους Βελτιστοποίησης και τα Μέτρα Σύγκρισης των εικόνων. Συγκεκριμένα, έγινε έρευνα σε Ελιτιστικούς Γενετικούς Αλγορίθμους (Elitist Genetic Algorithms) καθώς και σε νέες παραλλαγές μίας άλλης μεθόδου βελτιστοποίησης γνωστή ως Αρμονική Αναζήτηση (Harmony Search). Επίσης, κατασκευάστηκε και μία μέθοδος, με σκοπό την μείωση του υπολογιστικού κόστους, γνωστή ως Surrogate Model. Τέλος, στα πλαίσια εκτίμησης ομοιότητας των εικόνων, έγινε σύγκριση στατιστικών μέτρων βασισμένα στην στατιστική απόκλιση του Renyi (Renyi’s Divergence) με σκοπό την χρήση όσο είναι δυνατόν μικρότερου ποσοστού των εικόνων χωρίς την ταυτόχρονη μείωση της ποιότητας των αποτελεσμάτων.

show abstract

Swarm Intelligence Algorithms for Medical Image Registration: A Comparative Study

Cited by 7 publications

References 28 publications

Three-Dimensional Tooth Model Reconstruction Using Statistical Randomization-Based Particle Swarm Optimization

Three-Dimensional Tooth Model Reconstruction Using Statistical Randomization-Based Particle Swarm Optimization

Cluster-Based Memetic Approach of Image Alignment

Novel and robust methods for the automatic registration of image data

Contact Info

Product

Resources

About