Medical Image Segmentation through Bat-Active Contour Algorithm

Abstract

Abstract-In this research work, an improved active contour method called Bat-Active Contour Method (BA-ACM) using bat algorithm has been developed. The bat algorith m is incorporated in order to escape local min ima entrapped into by the classical active contour method, stabilize contour (snake) movement and accurately, reach boundary concavity. Then, the developed Bat-Active Contour Method was applied to a dataset of med ical images of the human heart, bone of knee and vertebra which were obtained from Auckland MRI Research Group (Card iac Atlas Website), University of Auckland. Set of similarity metrics, including Jaccard index and Dice similarity measures were adopted to evaluate the performance of the developed algorithm. Jaccard index values of 0.9310, 0.9234 and 0.8947 and Dice similarity values of 0.8341, 0.8616 and 0.9138 were obtained fro m the human heart, vertebra and bone of knee images respectively. The results obtained show high similarity measures between BA-A CM algorithm and expert segmented images. Moreso, traditional ACM produced Jaccard index values 0.5873, 0.5601, 0.6009 and Dice similarity values of 0.5974, 0.6079, 0.6102 in the hu man heart, vertebra and bone of knee images respectively. The results obtained for traditional ACM show low similarity measures between it and expertly segmented images. It is evident from the results obtained that the developed algorith m performed better co mpared to the traditional ACM.

Polycystic Ovary Cyst Segmentation Using Adaptive K-means with Reptile Search Algorith

“…Isah et al, [10] developed an efficient hybrid approach using Particle Swarm Optimization (PSO) with ANN for the detection of follicles. Using the Lee filter, the input ultrasound images are preprocessed.…”

“…Hunting stage: this is considered as an exploitation attitude of crocodiles which is used to find the optimal solution based on two strategies such as hunting coordination and hunting cooperation as denoted in Equation (10).…”

“…where 𝛼𝛼𝛼𝛼 is also used to control the exploration ability and set as 0.2, 𝜀𝜀𝜀𝜀 is the random number (10) (ii) Initialization of population: initially, the set of populations is generated randomly using Equation ( 6) ( , ) . (…”

Adaptive Learning Model Based on Ant Colony Algorithm

“…Over time, more and more user data will be stored on the system, and can be processed by more intelligent data analysis technology or artificial intelligence technology, such as genetic algorithm, SVM, Tensor Flow and other algorithms and technologies. These new technologies will gradually improve their precise push [14][15][16][17]. These measures will help understand the diverse behaviors of learners, providing important assistance for learners' behaviors and preferences, and motivating them to offer more useful information.…”

Application of Bat Algorithm for Texture Image Classification

“…The final results testify BA does not need selection, crossover and mutation operations like GA. What's more, it could converge to the optimal solution more stably. Currently, BA has been widely applied in various fields, such as Bora et al employed BA to work out the brushless DC wheel motor problems [14], Yang extend this algorithm to solve multi-objective optimization problems [15], Taha A M applied bat algorithm for feature selection [16], Adarsh B R handled with the economic dispatch problem with bat algorithm [17], Rabiu O. Isah used a bat-active contour algorithm to generate medical image segmentation and so on [25]. As a result, in the paper, BA is employed to learn the tuned mask and used for remote sensing image classification.…”