26
Automated Cataract Detection and Classification Using Random Forest Classifier in Fundus Images
Authors: Esra’a Mahmoud Jamil Al Sariera, M. C. Padma, Thamer Mitib Al Sariera
![](/system_img/view.png)
Number of views: 6
One of the most common causes of blindness, particularly in the elderly, is cataracts. Nearly half of India's elderly population has cataracts by the age of 80 or has had surgery to treat them. According to surveys conducted by the WHO and NPCB, there are over 12 million blind persons in India, and 80.1% of them are blind due to cataracts. Early detection of cataract cases is necessary to prevent total blindness. The World Health Organization (WHO) states that cataracts are the most frequent cause of blindness and visual loss. The risk of blindness among cataract patients can be decreased with prompt detection and treatment. On the other hand, clinical cataract identification requires the expertise of ophthalmologists. Therefore, the broad adoption of cataract detection to avert blindness may be hampered by the prospective expenses. Researchers are becoming more and more interested in artificial intelligence assisted diagnosis based on medical imagery. This study suggests an automated cataract detection procedure built on image processing and machine learning methods. A set of fundus retinal images serves as the input for the suggested model. The image dataset includes two kinds of images: healthy and images with cataracts to train the algorithm. This research consists of three primary phases: pre-processing, feature extraction and classification. The initial step of the method involves pre-processing the images to make them easier to process by extract the gray scale from the input image, then contrast-limited adaptive histogram equalization (CLAHE) is applied to improve the image and minimize noise, Finally ROI has been extracted. The second phase is feature extraction; by extract four kinds of texture features: (I) grey-level co-occurrence matrix (GLCM) to extract 11 features: 1) difference variance, 2) inverse difference moment, 3,4) information1\2, 5) entropy, 6) difference entropy, 7) correlation, 8) sum entropy, 9) maximal correlation coefficient, 10) contrast, and 11) angular second moment. (II) First Order Statistics (FOS) to extract 5 features: 1) entropy, 2) maximal gray level, 3) kurtosis, 4) skewness, and 5) energy. (III) Statistical Feature Matrix (SFM) to extract 4 features: 1) coarseness, 2) periodicity, 3) contrast, and 4) roughness. And finally (IV) Neighborhood Gray Tone Difference Matrix (NGTDM) to extract 4 features: 1) complexity, 2) coarseness, 3) strength, and 4) contrast. In the last phases, the extracted 24 features are put as input to the classifier, the classification was done by using Random Forest, support vector machines (SVM), Logistic Regression, K Neighbors (KNN), Decision Tree, and Naive Base Classifier. Classifies the retinal fundus images into two classes Cataracts or normal image. When compared to other current approaches, the experimental results of the suggested method show that its accuracy is 95%.