An Efficient and Light Weight Deep Learning Model for Accurate Retinal Vessels Segmentation

Aurangzeb, Khursheed; Alharthi, Rasha; Haider, Syed Irtaza; Alhussein, Musaed

doi:10.1109/access.2022.3217782

Cited by 13 publications

(10 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It seems that the RV-SegNet has been able to achieve a significant improvement in performance while still maintaining a lower level of computational complexity compared to other existing technologies. According to the proposed work, there has been a reduction in the number of parameters used from 5.00M to 982,177, compared with our recent work [32].…”

Section: Results Analysismentioning

confidence: 77%

“…Additionally, these previous works attribute higher computational complexity to the DL model. Recently, we applied the ColonSegNet [32] model for retinal vessel segmentation, which is lightweight and also achieved All these challenges, specifically the damage caused by different lesions hinders accurate vessel segmentation. For accurate and reliable vessel segmentation, it is recommended to select suitable pre and post-processing operations, which are faster and assist the developed learning model in achieving better evaluation metrics.…”

Section: The Framework For Dr and Glaucoma Detectionmentioning

confidence: 99%

“…We recently [32] developed an accurate and lightweight model for retinal vessel segmentation based on ColonSegNet [33]. ColonSegNet [33] is a real-time polyp segmentation Encoder-Decoder architecture.…”

Section: A Details Of the Basic Model Architecturementioning

confidence: 99%

See 2 more Smart Citations

Systematic Development of AI-Enabled Diagnostic Systems for Glaucoma and Diabetic Retinopathy

Aurangzeb,

Alharthi,

Haider

et al. 2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

With the rapid advancements in artificial intelligence, particularly in machine learning and deep learning, automated disease diagnosis is becoming increasingly feasible. Generating larger databases is crucial for training and validating the performance of models for chronic diseases such as glaucoma and diabetic retinopathy, which progress slowly and unnoticed. Automated procedures for retinal vessel segmentation and optic cup/disk localization are preferred for largescale screening of the public, contributing to the early detection and treatment of eye diseases, preventing blindness, and improving public health. This paper focuses on the challenges involved in segmenting the retinal vessels from fundus images and presents a modified ColonSegNet model for retinal vessel segmentation that includes efficient methods for locating the true vessels and applies data augmentation to overcome the issue of fewer graded images. The paper uses the optimal values for the contrast enhancement of retinal fundus images using intelligent evolution algorithms. The central vessel reflex, bifurcation, crossover, thin vessels, and lesion presence are highlighted as significant challenges in retinal vessel segmentation. The proposed method achieves high sensitivity, specificity, and accuracy, {0.839, 0.979, 0.966}, {0.865, 0.979, 0.971}, and {0.867, 0.981, 0.972}, segmenting retinal vessels on DRIVE, CHASE_DB , and STARE. The work is crucial in developing automated systems for the early detection and treatment of eye diseases, thereby improving public health.INDEX TERMS Deep Learning, disease diagnosis; diabetic retinopathy; glaucoma; image classification; retinal vessels; cup to disc ratio.

show abstract

Section: Results Analysismentioning

confidence: 77%

Section: The Framework For Dr and Glaucoma Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Systematic Development of AI-Enabled Diagnostic Systems for Glaucoma and Diabetic Retinopathy

Aurangzeb,

Alharthi,

Haider

et al. 2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…In [38], the researchers sought to lower the computational complexity of AI-enabled diagnostic systems by creating a lightweight deep learning model for retinal vascular segmentation. They achieved good sensitivity, specificity, and accuracy with a small number of trainable parameters by evaluating the ColonSegNet architecture on many fundus imaging datasets.…”

Section: International Journal On Recent and Innovation Trends In Com...mentioning

confidence: 99%

An In-Depth Statistical Review of Retinal Image Processing Models from a Clinical Perspective

Jagadale Sachin Mohan

2023

IJRITCC

View full text Add to dashboard Cite

The burgeoning field of retinal image processing is critical in facilitating early diagnosis and treatment of retinal diseases, which are amongst the leading causes of vision impairment globally. Despite rapid advancements, existing machine learning models for retinal image processing are characterized by significant limitations, including disparities in pre-processing, segmentation, and classification methodologies, as well as inconsistencies in post-processing operations. These limitations hinder the realization of accurate, reliable, and clinically relevant outcomes. This paper provides an in-depth statistical review of extant machine learning models used in retinal image processing, meticulously comparing them based on their internal operating characteristics and performance levels. By adopting a robust analytical approach, our review delineates the strengths and weaknesses of current models, offering comprehensive insights that are instrumental in guiding future research and development in this domain. Furthermore, this review underscores the potential clinical impacts of these models, highlighting their pivotal role in enhancing diagnostic accuracy, prognostic assessments, and therapeutic interventions for retinal disorders. In conclusion, our work not only bridges the existing knowledge gap in the literature but also paves the way for the evolution of more sophisticated and clinically-aligned retinal image processing models, ultimately contributing to improved patient outcomes and advancements in ophthalmic care.

show abstract

“…However, these methods lack generalization on data outside of the training set and encounter problems with mode collapse with the GAN-based unsupervised method, including difficulties in optimizing the parameters. Additionally, deep learning methods via a new frontier of machine learning require more training [32], which takes more computational time [33,34], and have poor real-world clinical generalizability, limiting their practicality in medical imaging [35,36]. Moreover, deep learning models are often considered black boxes, lacking the interpretability crucial for clinical acceptance [37,38].…”

Section: Introductionmentioning

confidence: 99%

Robust PCA with Lw,∗ and L2,1 Norms: A Novel Method for Low-Quality Retinal Image Enhancement

Likassa,

Chen,

Chen

et al. 2024

J. Imaging

View full text Add to dashboard Cite

Nonmydriatic retinal fundus images often suffer from quality issues and artifacts due to ocular or systemic comorbidities, leading to potential inaccuracies in clinical diagnoses. In recent times, deep learning methods have been widely employed to improve retinal image quality. However, these methods often require large datasets and lack robustness in clinical settings. Conversely, the inherent stability and adaptability of traditional unsupervised learning methods, coupled with their reduced reliance on extensive data, render them more suitable for real-world clinical applications, particularly in the limited data context of high noise levels or a significant presence of artifacts. However, existing unsupervised learning methods encounter challenges such as sensitivity to noise and outliers, reliance on assumptions like cluster shapes, and difficulties with scalability and interpretability, particularly when utilized for retinal image enhancement. To tackle these challenges, we propose a novel robust PCA (RPCA) method with low-rank sparse decomposition that also integrates affine transformations τi, weighted nuclear norm, and the L2,1 norms, aiming to overcome existing method limitations and to achieve image quality improvement unseen by these methods. We employ the weighted nuclear norm (Lw,*) to assign weights to singular values to each retinal images and utilize the L2,1 norm to eliminate correlated samples and outliers in the retinal images. Moreover, τi is employed to enhance retinal image alignment, making the new method more robust to variations, outliers, noise, and image blurring. The Alternating Direction Method of Multipliers (ADMM) method is used to optimally determine parameters, including τi, by solving an optimization problem. Each parameter is addressed separately, harnessing the benefits of ADMM. Our method introduces a novel parameter update approach and significantly improves retinal image quality, detecting cataracts, and diabetic retinopathy. Simulation results confirm our method’s superiority over existing state-of-the-art methods across various datasets.

show abstract

An Efficient and Light Weight Deep Learning Model for Accurate Retinal Vessels Segmentation

Cited by 13 publications

References 49 publications

Systematic Development of AI-Enabled Diagnostic Systems for Glaucoma and Diabetic Retinopathy

Systematic Development of AI-Enabled Diagnostic Systems for Glaucoma and Diabetic Retinopathy

An In-Depth Statistical Review of Retinal Image Processing Models from a Clinical Perspective

Robust PCA with Lw,∗ and L2,1 Norms: A Novel Method for Low-Quality Retinal Image Enhancement

Contact Info

Product

Resources

About