Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Dec 19:11:1286966.
doi: 10.3389/fbioe.2023.1286966. eCollection 2023.

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

Ashok Bhansali  1 , Rajkumar Patra  2 , Mohamed Abouhawwash  3   4 , S S Askar  5 , Mohan Awasthy  6 , K B V Brahma Rao  7
Affiliations

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

Ashok Bhansali et al. Front Bioeng Biotechnol. .

Abstract

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).

Keywords: adaptive-active counter model; diabetic retinopathy; gray level co-occurrence matrix; level set method with improved boundary indicator function; long short term memory.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. The author(s) declared that they were an editorial board member of Frontiers, at the time of submission. This had no impact on the peer review process and the final decision.

Figures

FIGURE 1
FIGURE 1
The overall process involved in the classification of diabetic retinopathy using LBACS-LSTM.
FIGURE 2
FIGURE 2
Sample images of IDRiD dataset.
FIGURE 3
FIGURE 3
Sample images obtained from DIARETDB 1.
FIGURE 4
FIGURE 4
Sample image obtained after enhancing the color and luminosity.
FIGURE 5
FIGURE 5
The process involved in segmentation using AACM.
FIGURE 6
FIGURE 6
Architectural diagram of LSTM.
FIGURE 7
FIGURE 7
Graphical representation for the performance of the classifier for IDRiD dataset.
FIGURE 8
FIGURE 8
Graphical representation for the performance of the classifier for the DIARETDB 1 dataset.
FIGURE 9
FIGURE 9
Confusion matrix of (A) IDRiD dataset (B) DIARETDB 1.
FIGURE 10
FIGURE 10
ROC of (A) DIARETDB 1 and (B) IDRiD 1.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Alajlan A. M., Razaque. A. (2023). ESOA-HGRU: egret swarm optimization algorithm-based hybrid gated recurrent unit for classification of diabetic retinopathy. Artif. Intell. Rev., 1–30. 10.1007/s10462-023-10532-1 - DOI
    1. Alam M., Zhao E. J., Lam C. K., Rubin D. L. (2023). Segmentation-assisted fully convolutional neural network enhances deep learning performance to identify proliferative diabetic retinopathy. J. Clin. Med. Res. 12 (1), 385. 10.3390/jcm12010385 - DOI - PMC - PubMed
    1. Ali G., Dastgir A., Iqbal M. W., Anwar M., Faheem M. (2023). A hybrid convolutional neural network model for automatic diabetic retinopathy classification from fundus images. IEEE J. Transl. Eng. Health Med. 11, 341–350. 10.1109/JTEHM.2023.3282104 - DOI
    1. Atli I., Gedik O. S. (2021). Sine-Net: a fully convolutional deep learning architecture for retinal blood vessel segmentation. Eng. Sci. Technol. Int. J. 24 (2), 271–283. 10.1016/j.jestch.2020.07.008 - DOI
    1. Atwany M. Z., Sahyoun A. H., Yaqub M. (2022). Deep learning techniques for diabetic retinopathy classification: a survey. IEEE Access 10, 28642–28655. 10.1109/ACCESS.2022.3157632 - DOI