An Enhanced Segmentation and Deep Learning Architecture for Early Diabetic Retinopathy Detection

Maaliw, Renato R.; Mabunga, Zoren P.; Veluz, Maria Rossana D. de; Alon, Alvin Sarraga; Lagman, Ace C.; Garcia, Manuel B.; Lacatan, Luisito Lolong; Dellosa, Rhowel M.

doi:10.1109/ccwc57344.2023.10099069

Cited by 22 publications

(2 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the conditions of DR, IoT is utilized to link different elements, such as healthcare providers, fundus cameras, and image analysis algorithms [3]. If DR is in an advanced or final stage, it can result in loss of vision [4]. The probability of DR is increased for diabetes cases affected by the disease for a prolonged period.…”

Section: Introductionmentioning

confidence: 99%

An Effective Heuristic Optimizer with Deep Learning-assisted Diabetic Retinopathy Diagnosis on Retinal Fundus Images

Nithyeswari,

Karthikeyan

2024

Eng. Technol. Appl. Sci. Res.

View full text Add to dashboard Cite

Diabetic Retinopathy (DR), a common diabetes complication affecting retinal blood vessels, may result in vision damage if not addressed promptly. Early and accurate detection is crucial for effective management, and Deep Learning (DL) techniques offer promising tools for the automated screening of Retinal Fundus Images (RFIs). This approach enhances objectivity, reduces inter-observer variability, and has the potential to extend the DR diagnoses to regions with limited access to specialized medical professionals. This manuscript presents the design of the Beluga Whale Optimizer (BWO) with Deep Learning (DL)-assisted DR Diagnosis on RFIs (BWODL-DRDRFI) technique in the Internet of Things (IoT) platform. The proposed technique automatically examines the RFIs for identifying and classifying DR. During the IoT-based data-gathering procedure the patient utilizes a head-mounted camera for capturing the RFI and sends it to a cloud server. Median Filtering (MF)-based image preprocessing is performed to eradicate noise. Next, the BWODL-DRDRFI technique exploits the ShuffleNet-v2 approach to derive feature vectors. For DR recognition, the BWODL-DRDRFI technique applies a deep Stacked AutoEncoder (SAE) model. Finally, the BWO model optimally adjusts the hyperparameter values of the DSAE model for greater classification performance. The simulation output of the BWODL-DRDRFI approach can be examined on a standard image dataset and the outputs are computed on discrete measures. The simulation result highlighted the enhanced performance of the BWODL-DRDRFI approach in the DR diagnosis process.

show abstract

Section: Introductionmentioning

confidence: 99%

An Effective Heuristic Optimizer with Deep Learning-assisted Diabetic Retinopathy Diagnosis on Retinal Fundus Images

Nithyeswari,

Karthikeyan

2024

Eng. Technol. Appl. Sci. Res.

View full text Add to dashboard Cite

show abstract

“…Diabetic microvascular disease leads to DR which is classified into three classes such as blood vessel rupture, hemorrhage, and obstruction of blood vessels. Moreover, DR is categorized into five stages such as normal, mild, moderate, severe, and proliferative ( Hasan et al, 2021 ; Xu et al, 2021 ; Pundikal and Holi, 2022 ; Maaliw et al, 2023 ) based on the severity of disease. Regular screening is required to aid in early DR identification, and early DR discovery will allow for thorough monitoring of the DR progression rate, which can be remarkably quick from early to high risk.…”

Section: Introductionmentioning

confidence: 99%

Level-set based adaptive-active contour segmentation technique with long short-term memory for diabetic retinopathy classification

Bhansali,

Patra,

Abouhawwash

et al. 2023

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

Diabetic Retinopathy (DR) is a major type of eye defect that is caused by abnormalities in the blood vessels within the retinal tissue. Early detection by automatic approach using modern methodologies helps prevent consequences like vision loss. So, this research has developed an effective segmentation approach known as Level-set Based Adaptive-active Contour Segmentation (LBACS) to segment the images by improving the boundary conditions and detecting the edges using Level Set Method with Improved Boundary Indicator Function (LSMIBIF) and Adaptive-Active Counter Model (AACM). For evaluating the DR system, the information is collected from the publically available datasets named as Indian Diabetic Retinopathy Image Dataset (IDRiD) and Diabetic Retinopathy Database 1 (DIARETDB 1). Then the collected images are pre-processed using a Gaussian filter, edge detection sharpening, Contrast enhancement, and Luminosity enhancement to eliminate the noises/interferences, and data imbalance that exists in the available dataset. After that, the noise-free data are processed for segmentation by using the Level set-based active contour segmentation technique. Then, the segmented images are given to the feature extraction stage where Gray Level Co-occurrence Matrix (GLCM), Local ternary, and binary patterns are employed to extract the features from the segmented image. Finally, extracted features are given as input to the classification stage where Long Short-Term Memory (LSTM) is utilized to categorize various classes of DR. The result analysis evidently shows that the proposed LBACS-LSTM achieved better results in overall metrics. The accuracy of the proposed LBACS-LSTM for IDRiD and DIARETDB 1 datasets is 99.43% and 97.39%, respectively which is comparably higher than the existing approaches such as Three-dimensional semantic model, Delimiting Segmentation Approach Using Knowledge Learning (DSA-KL), K-Nearest Neighbor (KNN), Computer aided method and Chronological Tunicate Swarm Algorithm with Stacked Auto Encoder (CTSA-SAE).

show abstract

A Novel Classification Approach for Retinal Disease Using Improved Gannet Optimization‐Based Capsule DenseNet

Venkatesan,

Kempanna,

Nagaraja

et al. 2024

Int J Imaging Syst Tech

View full text Add to dashboard Cite

An unusual condition of the eye called diabetic retinopathy affects the human retina and is brought on by the blood's constant rise in insulin levels. Loss of vision is the result. Diabetic retinopathy can be improved by receiving an early diagnosis to prevent further damage. A cost‐effective method of accumulating medical treatments is through appropriate DR screening. In this work, deep learning framework is introduced for the accurate classification of retinal diseases. The proposed method processes retinal fundus images obtained from databases, addressing noise and artifacts through an improved median filter (ImMF). It leverages the UNet++ model for precise segmentation of the disease‐affected regions. UNet++ enhances feature extraction through cross‐stage connections, improving segmentation results. The segmented images are then fed as input to the improved gannet optimization‐based capsule DenseNet (IG‐CDNet) for retinal disease classification. The hybrid capsule DenseNet (CDNet) classifies disease and is optimized using the improved gannet optimization algorithm to boost classification accuracy. Finally, the accuracy and dice score values achieved are 0.9917 and 0.9652 on the APTOS‐2019 dataset.

show abstract

An Enhanced Segmentation and Deep Learning Architecture for Early Diabetic Retinopathy Detection

Cited by 22 publications

References 43 publications

An Effective Heuristic Optimizer with Deep Learning-assisted Diabetic Retinopathy Diagnosis on Retinal Fundus Images

An Effective Heuristic Optimizer with Deep Learning-assisted Diabetic Retinopathy Diagnosis on Retinal Fundus Images

Level-set based adaptive-active contour segmentation technique with long short-term memory for diabetic retinopathy classification

A Novel Classification Approach for Retinal Disease Using Improved Gannet Optimization‐Based Capsule DenseNet

Contact Info

Product

Resources

About