RETRACTED ARTICLE: A method of progression detection for glaucoma using K-means and the GLCM algorithm toward smart medical prediction

• Published in: The Journal of supercomputing Vol. 77; no. 10; pp. 11894 - 11910
• Main Authors: Vimal, S., Robinson, Y. Harold, Kaliappan, M., Vijayalakshmi, K., Seo, Sanghyun
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.10.2021; Springer Nature B.V
• Subjects: Artificial Intelligence for Smart Cities; Compilers; Computer Science; Interpreters; Processor Architectures; Programming Languages; Glaucoma screening; CDR; K-means; Feature extraction; Fundus eye image; GLCM
• ISSN: 0920-8542; 1573-0484
• DOI: 10.1007/s11227-021-03757-w

Diabetes mellitus is one of the leading medical issues, causing national financial weight and low personal satisfaction. People with diabetes have an extended possibility of glaucoma. The pain caused by glaucoma is irreversible. This can occur when abnormal vein growth from diabetic retinopathy (DR), a significant consequence of diabetic illness, hinders the characteristic use of the eye—impacting the retina of diabetic individuals. A period of DR can prompt permanent vision impairment. The early discovery and observation of DR are critical to forestalling it or for effective treatment, yet the issue related to early identification of DR is minor changes on the retinal fundus picture: it incorporates hemorrhages, exudates, red sores, cotton fleece spots, and drusen. Early location or screening of changes on the retinal picture is exceptionally testing and tedious for ophthalmologists because the size and shading changes are at first coordinated with neighborhood veins in the retinal picture. Therefore, glaucoma is one of the most unsafe visual maladies, continuing to influence and burden a considerable portion of our populace. Accordingly, it is essential to distinguish glaucoma early. The proposed frameworks have focused on the cup-to-disc ratio for the identification of glaucoma, which might be the best methodology for building a proficient, vigorous, and precise computerized framework for glaucoma diagnosis. This strategy advocates the use of a half-and-half methodology of manual elements with profound learning. It can improve the precision of glaucoma conclusion using robotized systems.