Search

Eye globe volume estimation has gained attention in both medical and biomedical engineering field. However, most of the methods used manual analysis which is tedious and prone to errors due to various inter- or intraoperator variability studies. In the present study, we estimated the volume of eye globe, in MRI images of normal eye globe condition using the circular Hough transform (CHT) algorithm. To test the performance of the proposed method, 24 magnetic resonance images which constitute 14 males and ten females (normal eye globe condition) with T1-weighted MRI images are randomly selected from the database. The mean (±SD) of the eye globe volume for male was 6.75 (±0.82) cm3and 6.17 (±0.74) cm3on the right and left side respectively. For female, the mean (±SD) of the eye globe volume was 6.24 (±0.70) cm3on the right side and 6.22 (±0.72) cm3on the left side. The proposed method have provided the new insight in estimating eye globe volume with a new and unique, automated approach.

Retinal tissue plays a crucial part in human vision. Infections of retinal tissue and delayed treatment or untreated infection could lead to loss of vision. Additionally, the diagnosis is prone to errors when huge dataset is involved. Therefore, a fully automated model of identification of retinal disease is proposed to reduce human interaction while retaining its high accuracy classification results. This paper introduces an enhanced design of a fully automatic multi-class retina diseases prediction system to assist ophthalmologists in making speedy and accurate investigation. Retinal fundus images, which have been used in this study, were downloaded from the stare website (157 images from five classes: BDR, CRVO, CNV, PDR, and Normal). The five files were categorized according to their annotations conducted by the experienced specialists. The categorized images were first processed with the proposed upgraded contrast-limited adaptive histogram filter for image brightness enhancement, noise reduction, and intensity spectrum normalization. The proposed model was designed with transfer learning method and the fine-tuned pre-trained RESNET50. Eventually, the proposed framework was examined with performance evaluation parameters, recorded a classification rate with 100% sensitivity, 100% specificity, and 100% accuracy. The performance of the proposed model showed a magnificent superiority as compared to the state-of-the-art studies.