Novel artificial intelligence algorithms for diabetic retinopathy and diabetic macular edema

Eye and Vision, Journal Year: 2024, Volume and Issue: 11(1)

Published: June 17, 2024

Abstract Background Diabetic retinopathy (DR) and diabetic macular edema (DME) are major causes of visual impairment that challenge global vision health. New strategies needed to tackle these growing health problems, the integration artificial intelligence (AI) into ophthalmology has potential revolutionize DR DME management meet challenges. Main text This review discusses latest AI-driven methodologies in context terms disease identification, patient-specific profiling, short-term long-term management. includes current screening diagnostic systems their real-world implementation, lesion detection analysis, progression prediction, treatment response models. It also highlights technical advancements have been made areas. Despite advancements, there obstacles widespread adoption technologies clinical settings, including regulatory privacy concerns, need for extensive validation, with existing healthcare systems. We explore disparity between AI models actual effectiveness applications. Conclusion DME, offering more efficient precise tools professionals. However, overcoming challenges deployment, compliance, patient is essential realize full potential. Future research should aim bridge gap technological innovation application, ensuring integrate seamlessly workflows enhance outcomes.

Language: Английский

---

Analysis of preprocessing for generative adversarial networks: A case study on color fundoscopy to fluorescein angiography image-to-image translation

Computer Methods and Programs in Biomedicine Update, Journal Year: 2025, Volume and Issue: unknown, P. 100179 - 100179

Published: Jan. 1, 2025

Language: Английский

---

Artificially Intelligent detection of retinal pigment sign using P3S-Net for retinitis pigmentosa analysis

Results in Engineering, Journal Year: 2025, Volume and Issue: 25, P. 104263 - 104263

Published: Feb. 4, 2025

Language: Английский

---

Dual-Branch U-Net Architecture for Retinal Lesions Segmentation on Fundus Image

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 130451 - 130465

Published: Jan. 1, 2023

Deep learning has found widespread application in diabetic retinopathy (DR) screening, primarily for lesion detection. However, this approach encounters challenges such as information loss due to convolutional operations, shape uncertainty, and the high similarity between different types. These factors collectively hinder accurate segmentation of lesions. In research paper, we introduce a novel dual-branch U-Net architecture, referred Dual-Branch (DB)-U-Net, tailored address intricacies small-scale segmentation. Our involves two branches: one employs capture shared characteristics lesions, while other utilizes modified U-Net, known U2Net, equipped with decoders that share common encoder. U2Net is responsible generating probability maps well corresponding boundary DB combines outputs dual branch, concatenating their produce final result. To mitigate challenge imbalanced data, employ Dice function. We evaluate effectiveness our on publicly available datasets, including DDR, IDRiD, E-Ophtha. results demonstrate achieves AUPR values 0.5254 0.7297 Microaneurysms soft exudates segmentation, respectively, IDRiD dataset. outperform models, highlighting potential clinical utility method identifying retinal lesions from fundus images.

Language: Английский

---

Bi-attention DoubleUNet: A deep learning approach for carotid artery segmentation in transverse view images for non-invasive stenosis diagnosis

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 94, P. 106350 - 106350

Published: April 13, 2024

The carotid artery is a vital blood vessel that supplies oxygenated to the brain. Blockages in this can lead life-threatening illnesses, making accurate diagnosis essential. While ultrasound (US) imaging primary diagnostic tool, evaluations by trained operators be subjective and imprecise. An automated approach provide more reliable evaluation of artery's condition. To achieve this, must first identified isolated from US images. This paper proposes an segmentation method for transverse B-mode images, using Bi-attention DoubleUnet architecture which incorporates spatial attention channel wise Bottleneck module. evaluated on dataset images acquired two devices. obtained results exhibit higher performance than existing methods with dice index 95.96%, IoU 97.92%, Precision 98.35% recall 97.57% combined dataset. Another variant doubleUnet SE layer without ASPP (Artous Spatial Pyramidal Pooling) presented where modified realized average 92.805%, Dice 96.215%, precision 98.82%, 93.84% representing across datasets. These approaches significantly improve efficiency accuracy disease treatment, ultimately improving patient outcomes.

Language: Английский

---

A Context for Effective Prediction and Classification of Diabetic Retinopathy Disease using Deep Ensemble AlexNet & LeNet Classifier

2022 9th International Conference on Computing for Sustainable Global Development (INDIACom), Journal Year: 2024, Volume and Issue: unknown, P. 414 - 421

Published: Feb. 28, 2024

Typically, Diabetes is regarded as a metabolic disorder which aids in retinal complications termed Diabetic Retinopathy (DR) major reason for blindness over globe. Usually, there exists no clear symptoms DR before its onset, hence making disease identification an interesting job. Nowadays, industry of healthcare facing negative significances once gap the not made with effectual automation. Hence, objective this work to implement cost-effective and automated model prediction classification samples. This research presents DL-based segmentation fundus images depending on severity level. The proposed technique includes preprocessing, segmentation, feature extraction, optimal selection, classification. input image dataset considered subjected preprocessing by filtering, restoration, augmentation, enhancement process remove noise enhance quality. Then, carried use Deep DenseNet-169 approach. features from segmented are extracted means Enriched Haralick SURF based point extraction technique. range selected Meta-heuristic tuna swarm optimization algorithm. At last, using Ensemble AlexNet LeNet classifier predicts classifies per severity. was classified Non-proliferative (NPDR), mild, severe case. performance assessment & outcomes then related traditional models show enhancement.

Language: Английский

---

Revolutionizing diabetic retinopathy diagnosis through advanced deep learning techniques: Harnessing the power of GAN model with transfer learning and the DiaGAN-CNN model

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 99, P. 106790 - 106790

Published: Sept. 12, 2024

Language: Английский

---

Diabetic retinopathy detection using EADBSC and improved dilated ensemble CNN-based classification

Multimedia Tools and Applications, Journal Year: 2023, Volume and Issue: 83(11), P. 33573 - 33595

Published: Sept. 21, 2023

Language: Английский

---

GAN-Based Approach for Diabetic Retinopathy Retinal Vasculature Segmentation

Bioengineering, Journal Year: 2023, Volume and Issue: 11(1), P. 4 - 4

Published: Dec. 21, 2023

Most diabetes patients develop a condition known as diabetic retinopathy after having for prolonged period. Due to this ailment, damaged blood vessels may occur behind the retina, which can even progress stage of losing vision. Hence, doctors advise screen their retinas regularly. Examining fundus requires long time and there are few ophthalmologists available check ever-increasing number patients. To address issue, several computer-aided automated systems being developed with help many techniques like deep learning. Extracting retinal vasculature is significant step that aids in developing such systems. This paper presents GAN-based model perform segmentation. The achieves good results on ARIA, DRIVE, HRF datasets.

Language: Английский

---

Advances in retinal microaneurysms detection, segmentation and datasets for the diagnosis of diabetic retinopathy: a systematic literature review

Multimedia Tools and Applications, Journal Year: 2024, Volume and Issue: 83(30), P. 74897 - 74935

Published: Feb. 13, 2024

Language: Английский

---