A novel deep learning model for diabetic retinopathy detection in retinal fundus images using pre-trained CNN and HWBLSTM.

Diabetic retinopathy (DR) is a global visual indicator of diabetes that leads to blindness and loss of vision. Manual testing presents a more difficult task when attempting to detect DR due to the complexity and variances of DR. Early detection and treatment prevent the diabetic patients from visual loss. Also classifying the intensity and levels of DR is crucial to provide necessary treatment. This study develops a novel deep learning (DL) approach called He Weighted Bi-directional Long Short-term Memory (HWBLSTM) with an effective transfer learning technique for detecting DR from the RFI. The collected fundus images initially undergo preprocessing to improve their quality, which includes noise removal and contrast enhancement using a Hybrid Gaussian Filter and probability density Function-based Gamma Correction (HGFPDFGC) technique. The segmentation procedure divides the image into subgroups and is crucial for accurate detection and classification. The segmentation of the study initially removes the optical disk (OD) and blood vessels (BVs) from the preprocessed images using mathematical morphological operations. Next, it segments the retinal lesions from the OD and BV removed images using the Enhanced Grasshopper Optimization-based Region Growing Algorithm (EGORGA). Then, the features from the segmented retinal lesions are learned using a Squeeze Net (SQN), and the dimensionality reduction of the extracted features is done using the Modified Singular Value Decomposition (MSVD) approach. Finally, the classification is performed by employing the HWBLSTM approach, which classifies the DR abnormalities in datasets as non-DR (NDR), non-proliferative DR (NPDR), moderate NPDR (MDNPDR), and severe DR, also known as proliferative DR (PDR). The proposed approach is implemented on APTOS as well as MESSIDOR datasets. The outcomes proved that the proposed technique accurately identifies the DR with minimal computation overhead compared to the existing approaches.Communicated by Ramaswamy H. Sarma.

Convolutional neural network-based sea lion optimization algorithm for the detection and classification of diabetic retinopathy.

AIMS: Diabetic retinopathy (DR) becomes a complicated type of diabetic that causes damage to the blood vessels of the retina's light-sensitive tissue. DR may initially cause mild symptoms or no symptoms. But prolonged DR results in permanent vision loss, and hence, it is necessary to detect the DR at an early stage. METHODS: Manual diagnosing of DR retina fundus image is a time-consuming process and sometimes leads to misdiagnosis. The existing DR detection model faces few shortcomings in case of improper detection accuracy, higher loss or error values, high feature dimensionality, not suitable for large datasets, high computational complexity, poor performances, unbalanced and limited number of data points, and so on. As a result, the DR is diagnosed in this paper through four critical phases to tackle the shortcomings. The retinal images are cropped during preprocessing to reduce unwanted noises and redundant data. The images are then segmented using a modified level set algorithm based on pixel characteristics. RESULTS: Here, an Aquila optimizer is employed in extracting the segmented image. Finally, for optimal classification of DR images, the study proposes a convolutional neural network-oriented sea lion optimization (CNN-SLO) algorithm. Here, the CNN-SLO algorithm classifies the retinal images into five classes (healthy, moderate, mild, proliferative and severe). CONCLUSION: The experimental investigation is performed for Kaggle datasets with respect to diverse evaluation measures to deliberate the performances of the proposed system.

Hybrid adaptive deep learning classifier for early detection of diabetic retinopathy using optimal feature extraction and classification.

Objectives: Diabetic retinopathy (DR) is one of the leading causes of blindness. It is important to use a comprehensive learning method to identify the DR. However, comprehensive learning methods often rely heavily on encrypted data, which can be costly and time consuming. Also, the DR function is not displayed and is scattered in the high-definition image below. Methods: Therefore, learning how to distribute such DR functions is a big challenge. In this work, we proposed a hybrid adaptive deep learning classifier for early detection of diabetic retinopathy (HADL-DR). First, we provide an improved multichannel-based generative adversarial network (MGAN) with semi-maintenance to detect blood vessels segmentation. Results: By reducing the reliance on the encoded data, the following high-resolution images can be used to detect the indivisible features of some semi-observed MGAN references. Scale invariant feature transform (SIFT) function is then extracted and the best function is selected using the improved sequential approximation optimization (SAO) algorithm. After that, a hybrid recurrent neural network with long short-term memory (RNN-LSTM) is utilized for DR classification. The proposed RNN-LSTM classifier evaluated through standard benchmark Kaggle and Messidor datasets. Conclusion: Finally, the simulation results are compared with the existing state-of-art classifiers in terms of accuracy, precision, recall, f-measure and area under cover (AUC), it is seen that more successful results are obtained.