Optic disc pallor diagnosis using ROMF based optic disc segmentation in fundus images

Disc pallor is a pale yellow discoloration of the optic disc (OD) that causes irreversible damage to the fiber of the retina's anterior visual pathway. Automatic disc pallor diagnosis has obstacles such as increased time consumption and reduced accuracy due to less powerful OD segmentation algorithms. Hence, a new development for pallor diagnosis through the enhanced version of OD segmentation, namely, 'Optic Disc Pallor Diagnosis using ROMF-based OD segmentation in fundus images (ODPD_ROMF)', is proposed. Herein, the essential contribution is a new OD segmentation method, namely 'Optic disc segmentation using Retinex and ONH structure-specific Membership based FCM method (ROMF)’. The ROMF method is constituted based on a new variant of Fuzzy C Means (FCM), namely 'Optic Nerve Head (ONH) structure-influenced Fuzzy C Means (FCM)', where the membership function and the objective function are redefined to calibrate according to the refined or updated ONH structure, which results in fast and accurate OD segmentation. The second-best approach has an average classification accuracy of 93.00, while the proposed ODPD_ROMF method has an average accuracy of 96.17. The suggested ROMF method's average segmentation accuracy in OD segmentation is 97.52, while the second-best method's average segmentation accuracy is 96.66. Because of its great competence, the proposed ODPD_ROMF method can be utilized to identify disc pallor more effectively.