Risk Factor Based Stage Advancement Prediction of Cataract Using Deep Learning Techniques

Title

Risk Factor Based Stage Advancement Prediction of Cataract Using Deep Learning Techniques

Creator

Saju, Binju

Contributor

R, Rajesh

Description

In modern world, Cataract is the predominant causative of blindness. Treatment and detection at the early stage can reduce the number of cataract sufferers and prevent surgery. Two types of images are generally used for cataract related studies- Retinal Images an Slit lamp Images. The quality of Retinal images is selected by utilizing the hybrid naturalness image quality evaluator (hybrid NIQE-PIQE) approach. Here, the raw input image quality score is and Deep newlinelearning convolutional neural network (DCNN) categorizes the images based on quality newlinescore. Then the selected quality images are again pre-processed to remove the noise present in the images. The individual green channel (G-channel) is extracted for noise filtering. Moreover, hybrid modified histogram equalization and homomorphic filtering (Hybrid GMHE-HF) is utilized for enhanced noise filtering. The Slit lamp image quality selection is done using Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) model. Further a new algorithm Normalization based Contrast limited adaptive histogram equalization (NCLAHE) is used for image enhancement. Images are pre-processed utilizing the wiener filtering (WF) with Convolutional neural network (CNN) with adaptive atom search optimization (CNN-AASO) for removing the noise. Further, the denoised image is enhanced by Gaussian mixture based contrast enhancement (GMCE) for contrast enhancement. The cataract detection and classification is performed using two phases. In phase I, the cataract is detected using Deep Optimized Convolutional Recurrent Network_Improved Aquila Optimization (Deep OCRN_IAO) model. Phase II uses slit lamp images and detects the type and grade of cataracts through proposed Batch Equivalence ResNet-101 (BE_ResNet101) model.This work also proposes the risk factors for cataracts and classify the cataracts risk using deep learning models. The dataset is pre-processed by missing values and the string values are converted into numeric values.

Source

Author's Submission

Date

2024-01-01

Publisher

Christ(Deemed to be University)

Subject

Computer Science

Rights

Open Access

Relation

61000291

Format

PDF

Language

English

Type

PhD

Identifier

http://hdl.handle.net/10603/547683