Text
KOMBINASI ARSITEKTUR U-NET DAN FCN (FCNU-NET) DALAM SEGMENTASI OPTIC DISC DAN OPTIC CUP PADA CITRA RETINA
Semantic image segmentation has an important role in the medical field to assist in diagnosing glaucoma. Detection of this disease can be done through segmentation of the optic disc and optic cup on the retina. The architecture that is widely used in semantic image segmentation is U-Net. Convolutional Neural Network (CNN) has good performance in semantic image segmentation. This architecture has good accuracy in medical image analysis and disease diagnosis. In this study, propose the application of a combination of U-Net architecture and Fully Convolutional Network (FCN) for optical disc and optical cup segmentation on the retina using the Messidor-2 dataset with performance evaluation measures such as accuracy, specificity, sensitivity, F1 Score and IoU. The research stages include data collection, pre-processing, modification of U-Net and FCN architecture, training, testing, evaluation, analysis and interpretation of results, and conclusions. The results of the study using the Messidor-2 dataset obtained values 99.79% of accuracy, 96.44% of specificity, 78.89% of sensitivity, 81.86% of F1 Score, and 71.87%, of IoU. Based on these results, it shows that the proposed architecture is capable of segmenting the optical disc and retinal optic cup from the given dataset.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2207005450 | T70755 | T707552022 | Central Library (Referens) | Available but not for loan - Not for Loan |
No other version available