Multiple Retinal Disease Detection Using Convolution Neural Network
S.RAMA DEVI (Assistant Professor),Project Guide, S.Dakshayani, G.Sarishma Naidu, P.Manju Satya Mahalakshmi, P.Pavitra, K.Roja,students.
Department of Electronics and Communication Engineering, Andhra University College of Engineering for Women, Visakhapatnam, Andhra Pradesh, India.
Abstract:
In todays generation, issues related to retinal diseases and eye diseases are increasing due to digitized world. The major resons of visual impairment around the world are Cataract, Glaucoma, Myopia and other retinal diseases among patients. The alarming instances of these illnesses name for a pressing intervention by early diagnosis. Artificial Intelligence has provided a platform through which the early detection of diseases is possible and on basis of that proper treatment can be made available.
One of the valuable sources available for opthalmologists in diagosing retinal issues is ‘Retinal Fundus’ images.Medical professionals utilise theses retinal fundus images to diagnose numerous retinal problems like diabetic retinopathy, hypertensive retinopathy, glaucoma etc. In recent times, machine learning research has focused on diagnosing diseases like diabetic retinopathy by extracting features and then classifying the image.
In this project, we use machine learning to develop a program which collects the related data from the provided dataset and detect the retinal diseases such as ‘Cataract’, ‘Glaucoma’, ‘Hypertension’, ‘Myopia’ and ‘Diabetic Retinopathy’(Diabetes). Software used in this project is ‘PyCharm’ software editor which uses ‘Python’ programming language. The algorithm used in this project is ‘Convolution Neural Network’ (CNN). We also made use of ‘TKinter’ which provides a Graphical User Interface (GUI) for the project and the dataset is collected from ‘Kaggle’ which is an internet network of data scientists and machine learning engineers and allows customers to locate datasets they want to use in building AI models.
Deep learning methods (mainly CNNs) which are introduced for the automated detection, diagnosis, and staging of retinal diseases are achieving improved performance. Hence this project facilitates the assistance to the clinicians in early detection of various retinal diseases and this can improve chances of cure and also prevent blindness.
Keywords: - Machine Learning, Retinal disease, Convolution Neural Network (CNN), PyCharm, TKinter (GUI), Kaggle.