Diabetic Retinopathy Detection Using Deep Learning

Gothane, Suwarna; Raju, K. Srujan; Bhaskar, Nuthanakanti; Divya, G.

doi:10.1007/978-981-19-1559-8_39

Cited by 7 publications

(5 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…al. in [2] have used the dataset available in Kaggle consists of fundus images. The image of fundus was taken from the back side of the retina and the pupil is dilated.…”

Section: Datasetmentioning

confidence: 99%

“…Machine learning (ML) and deep-learning (DL) methodologies find application based on factors-such as the desired level of interpretability or the scale of the available dataset. [2,8] On the other hand, segmentation-oriented strategies aim to partition objects within an image. These approaches focus on dissecting morphological-features or extracting significant patterns from snapshots, such as delineating borders in 2D-or 3D imaging.…”

Section: Introductionmentioning

confidence: 99%

“…Typically situated in the peripheral areas of the eye, they exhibit clear demarcations. [2,8] Soft Exudates: -White lesions on-the eye, originating from nerve-fiber swelling, are denoted as soft exudates or cotton wool spots. These lesions assume ovular or-circular configurations.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Systematic Literature Review on Diabetic Retinopathy Stage Diagnosis Using Deep Learning Approach

D C

2024

IJSREM

View full text Add to dashboard Cite

Diabetic retinopathy is a medical condition that occurs due to diabetic mellitus causing blindness in the later stages. As the name says it is caused for people with the diabetes of type 1 and type 2 for a period of 20 years or more. However, early diagnosis and proper treatment at the initial stages could reduce aggressive forms of threatening retinopathy by up to 90%. According to the 2019 census from the ninth edition of the IDF Diabetes Atlas, India is put in the second slot right up to 2045 with people who are aged between 20-79 years. In 2019, India had 77 diabetic patients. In the recent survey of 2022 by the Union Health Ministry of India, almost 17% of the Indian population has diabetic retinopathy of which 3.6% is sight threatening. Specific to the rural population, 10.4% had diabetes of which 10.3% were diabetic retinopathy affected. From the WHO survey, it is estimated that by 2030, diabetics with retinopathy will increase by 50%. Without proper treatment, the individual is more likely to lose his vision. So, to prevent it, early detection of diabetic retinopathy and its stage is necessary. Key Words: Diabetic retinopathy, fundus, proliferative and non-proliferative, deep learning.

show abstract

“…al. in [2] have used the dataset available in Kaggle consists of fundus images. The image of fundus was taken from the back side of the retina and the pupil is dilated.…”

Section: Datasetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Systematic Literature Review on Diabetic Retinopathy Stage Diagnosis Using Deep Learning Approach

D C

2024

IJSREM

View full text Add to dashboard Cite

show abstract

“…Physicians can detect blindness early on thanks to Artificial Intelligence and Deep Learning. Using a supervised learning technique, fundus images can be classified [11]. To improve numerous significant features, such as microaneurysms, hemorrhages, exudates, and swollen blood vessels features of the fundus image that suggest a specific person has diabetic retinopathy many image processing techniques and filters were employed for this task.…”

Section: Literature Reviewmentioning

confidence: 99%

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

Minakshee Chandankhede

2024

jes

View full text Add to dashboard Cite

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

show abstract

“…Bhaskar et al [3] applied U-net and convolutional neural network (CNN) models on lung computed tomography (CT) images to classify lung cancer and achieved 96% accuracy. Using the ResNet architecture, Gothane et al [4] classified the fundus images with an accuracy of 82%. Tiwari et al [5] investigated the reliability of a deep learning system for diagnosing lung disease based on clinical image analysis challenges.…”

Section: Introductionmentioning

confidence: 99%

An approach for liver cancer detection from histopathology images using hybrid pre-trained models

Bhaskar,

Kiran,

Satyanarayan

et al. 2024

TELKOMNIKA

View full text Add to dashboard Cite

Histopathological image analysis (HIA) plays an essential role in detecting cancer cell development, but it is time-consuming, prone to inaccuracy, and dependent on pathologist competence. This paper proposes an automated HIA that uses deep learning to improve accuracy and efficiency in liver cancer cell growth. The model uses whole slide image (WSI) input, open computer vision (OpenCV) libraries for image preprocessing, ResNet50 for patch-level feature extraction, and multiple instances learning for imagelevel classification. The suggested approach accurately distinguishes liver histopathological pictures as cancerous or non-cancerous. Assisting in the early detection of liver cancer cell development with potential invasion or spread.

show abstract

Diabetic Retinopathy Detection Using Deep Learning

Cited by 7 publications

References 6 publications

A Systematic Literature Review on Diabetic Retinopathy Stage Diagnosis Using Deep Learning Approach

A Systematic Literature Review on Diabetic Retinopathy Stage Diagnosis Using Deep Learning Approach

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

An approach for liver cancer detection from histopathology images using hybrid pre-trained models

Contact Info

Product

Resources

About