Automated diabetic retinopathy screening in resource-limited areas with attention-enhanced deep learning on fundus images DOI

Sornil A. Binusha,

Herobin Rani C. Sheeja,

Sheeba I. Rexiline

и другие.

i-manager’s Journal on Image Processing, Год журнала: 2024, Номер 11(4), С. 10 - 10

Опубликована: Янв. 1, 2024

Diabetic retinopathy (DR) is a leading contributor to vision impairment, particularly in areas with limited resources where access specialized care scarce. This study introduces an automated screening system for DR using attention- enhanced deep learning on retinal fundus images, specifically designed these regions. The leverages convolutional neural network (CNN) technology integrated attention mechanisms focus critical features indicative of DR, such as microaneurysms and hemorrhages, improving detection accuracy reliability. Varied images were used training validation, data augmentation applied enhance model robustness. was optimized deployment low-cost hardware, ensuring feasibility resource-limited settings. Performance evaluation demonstrated high sensitivity specificity, maps provided interpretability healthcare providers. has the potential early diabetic underserved areas, facilitating timely intervention reducing risk blindness. By making advanced diagnostic tools accessible, this approach promotes equitable helps prevent loss globally.

Язык: Английский

ResDenseNet:Hybrid Convolutional Neural Network Model for Advanced Classification of Diabetic Retinopathy(DR) in Retinal Image Analysis DOI Open Access

Sashi Kanth Betha

International Journal of Computational and Experimental Science and Engineering, Год журнала: 2024, Номер 10(4)

Опубликована: Дек. 22, 2024

Preventing vision loss in diabetic retinopathy (DR) requires early and precise detection. Although strong feature extraction is required there class imbalance the current methods, deep learning (DL) techniques have showed promise DR classification. With components from both ResNeXt DenseNet designs, a unique DL architecture for classification proposed this work. A that integrates work.To address issues classification, method channel-wise masking with an attention mechanism. The network able to learn less frequent stages because reduces influence of majority concentrates on important features. To improve interpretability confidence model's predictions, incorporation Explainable AI (XAI) approaches also covered.Our findings show suggested approach outperforms architectures, achieving better sensitivity differentiating phases at 0.82 accuracy 0.87. This shows new has improving categorization, which could result earlier diagnoses patient outcomes.

Язык: Английский

Процитировано

6
Classification of Diabetic Retinopathy Using Optimization Driven Automated Self-Feature Selected Light Gradient Boosting Mechanism DOI

Shobhana,

Lakshmi Patil

Sensing and Imaging, Год журнала: 2025, Номер 26(1)

Опубликована: Март 12, 2025

Язык: Английский

Процитировано

0
Generative AI-Enabled IoT Applications for Smart Cities DOI
Anupriya Sharma Ghai, Kapil Ghai,

Gulsun Kurubacak Cakir

и другие.

Advances in computational intelligence and robotics book series, Год журнала: 2024, Номер unknown, С. 222 - 238

Опубликована: Апрель 1, 2024

In the dynamic evolution of smart cities, collaboration between generative artificial intelligence (AI) and internet things (IoT) technologies is reshaping urban experiences fostering sustainable development. This collaborative explores intricate balance resource allocation optimization facilitated by AI algorithms within intelligent city IoT networks. It unfolds transformative potential design for infrastructure, offering insights into energy efficiency advanced processes. The chapter underscores pivotal role predictive analytics, behavior prediction, cybersecurity measures in steering decision-making optimal functioning. Real-world case studies illuminate successful AI-IoT integrations, providing tangible lessons stakeholders, conclude urging ongoing research to address evolving challenges chart future directions a more interconnected resilient future. serves as valuable contribution, comprehensive exploration this paradigm.

Язык: Английский

Процитировано

2
The Role of Fundus Imaging and GAN in Diabetic Retinopathy Classification using VGG19 DOI

C Kabilan,

Shalini Kumar,

G Latha Selvi

и другие.

2022 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI), Год журнала: 2024, Номер unknown, С. 1 - 5

Опубликована: Май 9, 2024

Язык: Английский

Процитировано

1
Optimized YOLOV8: An efficient underwater litter detection using deep learning DOI Creative Commons

Faiza Rehman,

Mariam Rehman,

Maria Anjum

и другие.

Ain Shams Engineering Journal, Год журнала: 2024, Номер 16(1), С. 103227 - 103227

Опубликована: Дек. 26, 2024

Язык: Английский

Процитировано

1
Enhanced Diabetic Retinopathy Diagnosis: A Comparative Analysis of models with an Ensemble classifier and Deep Q Learning DOI Creative Commons

Minakshee Chandankhede

Deleted Journal, Год журнала: 2024, Номер 20(6s), С. 2613 - 2624

Опубликована: Май 2, 2024

- A novel method that combines the strengths of different classifiers such as Naive Bayes, Multi-Layer Perceptron (MLP), and Support Vector Machine (SVM) is introduced in this paper. This tackles urgent need for cutting-edge diagnostic methods field ophthalmology, mainly identification diabetic retinopathy (DR). The approach ensemble-based. Classical retinal analysis images often fail they are static unable to adjust unique details each distinct image presents. constraint results less accurate precise results, highlighting more adaptable dynamic methods. suggested model differs significantly from previous Through use an ensemble approach, it capitalizes on advantages classifier: MLP process's sophisticated feature extraction skill, Bayes' probabilistic analysis, SVM's non-linear pattern recognition capacity. By combining these techniques, inherent drawbacks utilizing a single strategy addressed, guaranteeing thorough examination samples images. core idea system using Deep Q Learning (DQL) adaptive classifier selection. Using learned Values various contexts, reinforcement learning technique selects best adaptively image, hence optimizing ensemble. not only advances diagnosis accuracy precision but also guarantees ongoing adaptation keep up with changing data patterns imaging technology. Extensive experiments IDRiD & EyePACS Dataset show effectiveness 5.5% increase overall other performance metrics, significant improvement over current method. They represent advancement timely retinopathy, which will ultimately benefit patients lessen strain healthcare systems. Thus, work represents major step forward patient care well technological advance, opening door efficient supervision treatment illnesses.

Язык: Английский

Процитировано

0
Predicting Diabetic Retinopathy Severity with Deep Learning: A Survey of Fundus Image Analysis Technique DOI

A Binusha Sornil,

C. Sheeja Herobin Rani,

I.Rexilin Sheeba

и другие.

Опубликована: Апрель 12, 2024

Diabetic retinopathy (DR) is a significant complication of diabetes mellitus, impacting vision due to retinal abnormalities. Early detection and precise severity assessment are crucial for effective management. Leveraging deep learning techniques image preprocessing methods, this paper proposes comprehensive approach DR classification. Utilizing publicly available datasets like EyePACS, Messidor-2, APTOS, DDR, steps including Gaussian blurring data augmentation employed enhance quality address class imbalance. Wavelet decomposition used feature extraction capture multi-resolution information from fundus images. Transfer with ResNet variants, coupled regularization techniques, aids in model generalization. A modified ResNet50 architecture introduced, featuring custom fully connected layers additional convolutional improved extraction. The aims classify diseases into four levels: normal, mild, moderate, severe proliferative. survey aspect delves methods' effectiveness improving CNN performance medical analysis, specifically detection. applicability transfer imaging tasks, particularly DR, also explored. This study contributes advancing analysis diagnosis classification, addressing the critical need efficient management debilitating condition.

Язык: Английский

Процитировано

0
ERBVS: Enhanced Retinal Blood Vessel Segmentation using Multiple Modalities and Attention Mechanisms with Adversarial Training and Ensemble Deep Learning Operations DOI Creative Commons

Komal Umare Thool

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Июль 26, 2024

Abstract It would, therefore, require highly advanced prediction tools to enhance early diagnosis and preemptive mechanisms for all these burgeoning diseases. Fast correct disease pre-emption have huge potential changing clinical outcome ensuring timely effective interventions that reduce morbidity mortality. Current predictive models, instrumental as they are, been found faltering in precision, recall, accuracy, timeliness. Such delays inaccuracies often miss the therapeutic window or lead misguided decisions. In this work, we present a novel model aims quite dramatically improve process of segmentation classification. Our approach embeds Attention Mechanisms with Adversarial Training Ensemble Deep Learning Operations, together multimodal approach, which places it substantially higher across several metrics. This improves AUC by 8.5%, 8.3%, 4.9%, 3.9%, respectively, classification, while reducing classification delay 5.9% different situations. Not only does our handle intrinsic limitations current methods, but also shows flexibility wide range applications. The compelling improvements preemption metrics strengthen its make sea change framework establishing optimum patient outcomes efficient scenarios healthcare delivery.

Язык: Английский

Процитировано

0
Detection Of Diabetic Retinopathy Using Deep Learning Algorithms DOI
Uddipan Das,

Jahnavi Haloi,

Pallabi Hassam

и другие.

2022 4th International Conference on Energy, Power and Environment (ICEPE), Год журнала: 2024, Номер unknown, С. 1 - 5

Опубликована: Июнь 20, 2024

Язык: Английский

Процитировано

0
Diabetic Retinal Images Severity Prediction Using Feature Extraction Mechanism with Deep Learning Method DOI

M. Murugesan,

S. Sharmila

2022 8th International Conference on Advanced Computing and Communication Systems (ICACCS), Год журнала: 2024, Номер unknown, С. 777 - 783

Опубликована: Март 14, 2024

Язык: Английский

Процитировано

0