Segmentation of Cochlear Nerve Based on Particle Swarm Optimization Method
Sensorineural hearing loss is a hearing impairment happens when there is damage to the inner ear or to the nerve pathways from the internal ear to the brain. Cochlear implants have been developed to help the patients with congenital or acquired hearing loss. The size of the cochlear nerve is a prerequisite for the successful outcome of cochlear implant surgery. Hence, an accurate segmentation of cochlear nerve is a critical assignment in computer-aided diagnosis and surgery planning of cochlear implants. This paper aims at developing a cochlear nerve segmentation approach based on modified particle swarm optimization (PSO). In the proposed approach, a constant adaptive inertia weight based on the kernel density estimation of the image histogram is estimated for fine-tuning the current search space to segment the cochlear nerve. The segmentation results are analyzed both qualitatively and quantitatively based on the performance measures, namely Jaccard index, Dice coefficient, sensitivity, specificity, and accuracy as well. These results indicate that the proposed algorithm performs better compared to standard PSO algorithm in preserving edge details and boundary shape. The proposed method is tested on different slices of eight patients undergone for magnetic resonance imaging in the assessment of giddiness/vertigo or fitness for the cochlear implant. The significance of this work is to segment the cochlear nerve from magnetic resonance (MR) images to assist the radiologists in their diagnosis and for successful cochlear implantation with the scope of developing speech and language, especially in children.
KeywordsCochlear nerve Cochlear implant Improved PSO segmentation Magnetic resonance (MR) image
We express our gratitude to Dr. R. Rajeshwaran for his helpful data on demonstrative detail of internal ear MR images. Likewise, authors might want to thank the Sri Ramachandra Medical Center, Porur, Chennai, India, for giving the MR images.
- 6.Kennedy J, Eberhart R (1995) Particle swarm optimization. In: Proceedings of the IEEE international conference on neural networks, Perth, Australia, vol 4, no 2, pp 1942–1948Google Scholar
- 9.Jeevakala S, Brintha Therese A (2016) Non local means filter based Rician noise removal of MR images. Int J Pure Appl Math 109(5):133–139Google Scholar