Abstract
This paper aimed to explore segmentation effects of the magnetic resonance imaging (MRI) images of the inner auditory canal of patients with Meniere's disease under the intelligent segmentation method of the inner ear based on three-dimensional (3D) level set (IS3DLS). The statistical shape model and the level set segmentation algorithm were combined to propose the IS3DLS. First, the shape training samples of the inner ear model were determined, and the results were manually segmented to further obtain region of interest (ROI) of the inner ear. The IS3DLS was employed to accurately segment MRI images of the inner auditory canal of patients with Meniere's disease. The segmentation performance of IS3DLS was compared with the expert manual segmentation method and the region growth level set-based segmentation algorithm. Results showed that Matthews correlation coefficient (MCC), Dice similarity coefficient (DSC), false positive rate (FPR), and false negative rate (FNR) of this algorithm were 0.9599, 0.9594, 0.0325, and 0.03655, respectively. Therefore, the IS3DLS could achieve good segmentation effect in MRI images of the inner auditory canal of patients with Meniere's disease, which was helpful for diagnosis and subsequent treatment of Meniere's disease.
Highlights
Meniere’s disease is an idiopathic inner ear disease, and the inner ear mainly includes bony and membranous labyrinths, which locates between the thigh chamber and the bottom of the inner ear canal. e main pathological change of this disease is membrane labyrinth hydrops, which is clinically manifested as recurrent rotating vertigo, fluctuating hearing loss, tinnitus, and ear fullness
One of the images was arbitrarily selected as a reference, the other images were extracted through registration technology to take the inner ear region of interest (ROI) out, and the inner ear ROI was segmented through level set evolution to obtain the image (Figure 5). e inner ear was drawn through the segmentation algorithm proposed in this study to obtain Figure 6. rough comparison, it was found that the algorithm proposed in this study showed clear display of the vestibule, cochlea, and semicircular canal, and the segmentation was accurate. us, the results were basically consistent with the actual structure of the inner ear
E comparison results of the three segmentation methods are shown in Table 1. e measurement indicators in Table 1 were evaluated from the accuracy and error of the segmentation results. e results revealed that the segmentation algorithm in this study had a good segmentation effect, and the accuracy and error rates were close to 1 and 0 in turn
Summary
Meniere’s disease is an idiopathic inner ear disease, and the inner ear mainly includes bony and membranous labyrinths, which locates between the thigh chamber and the bottom of the inner ear canal. e main pathological change of this disease is membrane labyrinth hydrops, which is clinically manifested as recurrent rotating vertigo, fluctuating hearing loss, tinnitus, and ear fullness. E main pathological change of this disease is membrane labyrinth hydrops, which is clinically manifested as recurrent rotating vertigo, fluctuating hearing loss, tinnitus, and ear fullness. It mostly occurs in young and middle-aged people aged 30–50 years, and the incidence is about 0.2–0.5% [1]. MRI is a type of tomography that adopts the magnetic resonance phenomena to obtain electromagnetic signals from the human body, so as to reconstruct the information of human body It can display the distribution of a certain physical quantity in panic and weight loss and can obtain tomographic images and three-dimensional images in any direction. It is featured with the absence of ionizing radiation, clear soft tissue structure, and multisequence imaging. e shortcoming is that the spatial resolution is not high [3]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
