Automated retinal health diagnosis using pyramid histogram of visual words and Fisher vector techniques. (1st January 2018)

• Record Type: Journal Article
• Authors: Koh, Joel E.W.; Ng, Eddie Y.K.; Bhandary, Sulatha V.; Hagiwara, Yuki; Laude, Augustinus; Acharya, U. Rajendra
• Is Part Of: Computers in biology and medicine. Volume 92(2018)
• Page Start: 204
• Page End: 209
• Publication Date: 2018-01-01
• Subjects: Age-related macular degeneration -- Bag-of-visual-words -- Computer-aided diagnosis system -- Diabetic retinopathy -- Eye diseases -- Fisher vector encoder -- Fundus images -- Glaucoma -- Machine learning; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2017.11.019
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Untreated age-related macular degeneration (AMD), diabetic retinopathy (DR), and glaucoma may lead to irreversible vision loss. Hence, it is essential to have regular eye screening to detect these eye diseases at an early stage and to offer treatment where appropriate. One of the simplest, non-invasive and cost-effective techniques to screen the eyes is by using fundus photo imaging. But, the manual evaluation of fundus images is tedious and challenging. Further, the diagnosis made by ophthalmologists may be subjective. Therefore, an objective and novel algorithm using the pyramid histogram of visual words (PHOW) and Fisher vectors is proposed for the classification of fundus images into their respective eye conditions (normal, AMD, DR, and glaucoma). The proposed algorithm extracts features which are represented as words. These features are built and encoded into a Fisher vector for classification using random forest classifier. This proposed algorithm is validated with both blindfold and ten-fold cross-validation techniques. An accuracy of 90.06% is achieved with the blindfold method, and highest accuracy of 96.79% is obtained with ten-fold cross-validation. The highest classification performance of our system shows the potential of deploying it in polyclinics to assist healthcare professionals in their initial diagnosis of the eye. Our developed system can reduce the workload of ophthalmologists significantly. Graphical abstract: The proposed method for the development of a CAD eye screening system. Image 1 Highlights: Classification of the various eye conditions using fundus images. It is a four class eye problem. Pyramid histogram of visual words and fisher vector are employed. Accuracy of 90.06% obtained with blindfold technique. Accuracy of 96.79% obtained with ten-fold technique.