scholarly journals An interpretable multiple-instance approach for the detection of referable diabetic retinopathy in fundus images

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Alexandros Papadopoulos ◽  
Fotis Topouzis ◽  
Anastasios Delopoulos
Keyword(s):  
Machine Learning ◽  
Diabetic Retinopathy ◽  
Vision Loss ◽  
Classification Performance ◽  
Multiple Instance Learning ◽  
Attention Mechanism ◽  
Learning System ◽  
Successful Outcome ◽  
Fundus Images ◽  
Image Patches

AbstractDiabetic retinopathy (DR) is one of the leading causes of vision loss across the world. Yet despite its wide prevalence, the majority of affected people lack access to the specialized ophthalmologists and equipment required for monitoring their condition. This can lead to delays in the start of treatment, thereby lowering their chances for a successful outcome. Machine learning systems that automatically detect the disease in eye fundus images have been proposed as a means of facilitating access to retinopathy severity estimates for patients in remote regions or even for complementing the human expert’s diagnosis. Here we propose a machine learning system for the detection of referable diabetic retinopathy in fundus images, which is based on the paradigm of multiple-instance learning. Our method extracts local information independently from multiple rectangular image patches and combines it efficiently through an attention mechanism that focuses on the abnormal regions of the eye (i.e. those that contain DR-induced lesions), thus resulting in a final image representation that is suitable for classification. Furthermore, by leveraging the attention mechanism our algorithm can seamlessly produce informative heatmaps that highlight the regions where the lesions are located. We evaluate our approach on the publicly available Kaggle, Messidor-2 and IDRiD retinal image datasets, in which it exhibits near state-of-the-art classification performance (AUC of 0.961 in Kaggle and 0.976 in Messidor-2), while also producing valid lesion heatmaps (AUPRC of 0.869 in the 81 images of IDRiD that contain pixel-level lesion annotations). Our results suggest that the proposed approach provides an efficient and interpretable solution against the problem of automated diabetic retinopathy grading.

scholarly journals Classification among Microaneurysms, Exudates, and Lesion free Retinal Regions in the Eye Images using Transfer Learned CNNs

2019 ◽  
Vol 9 (2) ◽  
pp. 5508-5512
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Diabetic Retinopathy ◽  
Glucose Level ◽  
Vision Loss ◽  
Early Stage ◽  
Training Data ◽  
Fundus Images ◽  
Diabetic Mellitus ◽  
Start Process

When pancreas fails to secrete sufficient insulin in the human body, the glucose level in blood either becomes too high or too low. This fluctuation in glucose level affects different body organs such as kidney, brain, and eye. When the complications start appearing in the eyes due to Diabetic Mellitus (DM), it is called Diabetic Retinopathy (DR). DR can be categorized in several classes based on the severity, it can be Microaneurysms (ME), Haemorrhages (HE), Hard and Soft Exudates (EX and SE). DR is a slow start process that starts with very mild symptoms, becomes moderate with the time and results in complete vision loss, if not detected on time. Early-stage detection may greatly bolster in vision loss. However, it is impassable to detect the symptoms of DR with naked eyes. Ophthalmologist harbor to the several approaches and algorithm which makes use of different Machine Learning (ML) methods and classifiers to overcome this disease. The burgeoning insistence of Convolutional Neural Network (CNN) and their advancement in extracting features from different fundus images captivate several researchers to strive on it. Transfer Learning (TL) techniques help to use pre-trained CNN on a dataset that has finite training data, especially that in under developing countries. In this work, we propose several CNN architecture along with distinct classifiers which segregate the different lesions (ME and EX) in DR images with very eye-catching accuracies.

scholarly journals A Machine Learning based Approach for Segmenting Retinal Nerve Images using Artificial Neural Networks

2020 ◽  
Vol 10 (4) ◽  
pp. 5986-5991
Author(s):  
A. N. Saeed
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Diabetic Retinopathy ◽  
Blood Vessels ◽  
Back Propagation ◽  
Texture Feature ◽  
Texture Features ◽  
Classification Performance ◽  
Fundus Images ◽  
Retinal Blood Vessels

Artificial Intelligence (AI) based Machine Learning (ML) is gaining more attention from researchers. In ophthalmology, ML has been applied to fundus photographs, achieving robust classification performance in the detection of diseases such as diabetic retinopathy, retinopathy of prematurity, etc. The detection and extraction of blood vessels in the retina is an essential part of various diagnosing problems associated with eyes, such as diabetic retinopathy. This paper proposes a novel machine learning approach to segment the retinal blood vessels from eye fundus images using a combination of color features, texture features, and Back Propagation Neural Networks (BPNN). The proposed method comprises of two steps, namely the color texture feature extraction and training the BPNN to get the segmented retinal nerves. Magenta color and correlation-texture features are given as input to the BPNN. The system was trained and tested in retinal fundus images taken from two distinct databases. The average sensitivity, specificity, and accuracy obtained for the segmentation of retinal blood vessels were 0.470%, 0.914%, and 0.903% respectively. Results obtained reveal that the proposed methodology is excellent in automated segmentation retinal nerves. The proposed segmentation methodology was able to obtain comparable accuracy with other methods.

An Explainable Deep Learning Ensemble Model for Robust Diagnosis of Diabetic Retinopathy Grading

2021 ◽  
Vol 17 (3s) ◽  
pp. 1-24
Author(s):  
Mohammad Shorfuzzaman ◽  
M. Shamim Hossain ◽  
Abdulmotaleb El Saddik
Keyword(s):  
Diabetic Retinopathy ◽  
Deep Learning ◽  
Vision Loss ◽  
Final Diagnosis ◽  
Learning Rate ◽  
Ensemble Model ◽  
Fundus Images ◽  
Robust Detection ◽  
Retinal Fundus Images ◽  
Retinal Fundus

Diabetic retinopathy (DR) is one of the most common causes of vision loss in people who have diabetes for a prolonged period. Convolutional neural networks (CNNs) have become increasingly popular for computer-aided DR diagnosis using retinal fundus images. While these CNNs are highly reliable, their lack of sufficient explainability prevents them from being widely used in medical practice. In this article, we propose a novel explainable deep learning ensemble model where weights from different models are fused into a single model to extract salient features from various retinal lesions found on fundus images. The extracted features are then fed to a custom classifier for the final diagnosis of DR severity level. The model is trained on an APTOS dataset containing retinal fundus images of various DR grades using a cyclical learning rates strategy with an automatic learning rate finder for decaying the learning rate to improve model accuracy. We develop an explainability approach by leveraging gradient-weighted class activation mapping and shapely adaptive explanations to highlight the areas of fundus images that are most indicative of different DR stages. This allows ophthalmologists to view our model's decision in a way that they can understand. Evaluation results using three different datasets (APTOS, MESSIDOR, IDRiD) show the effectiveness of our model, achieving superior classification rates with a high degree of precision (0.970), sensitivity (0.980), and AUC (0.978). We believe that the proposed model, which jointly offers state-of-the-art diagnosis performance and explainability, will address the black-box nature of deep CNN models in robust detection of DR grading.

Construction of benchmark retinal image database for diabetic retinopathy analysis

2020 ◽  
Vol 234 (9) ◽  
pp. 1036-1048
Author(s):  
Jaskirat Kaur ◽  
Deepti Mittal
Keyword(s):  
Diabetic Retinopathy ◽  
Vision Loss ◽  
Medical Condition ◽  
Diagnostic Technique ◽  
Performance Comparison ◽  
Fundus Images ◽  
Benchmark Database ◽  
Computer Aided ◽  
Retinal Fundus Images ◽  
Retinal Fundus

Diabetic retinopathy, a symptomless medical condition of diabetes, is one of the significant reasons of vision impairment all over the world. The prior detection and diagnosis can decrease the occurrence of acute vision loss and enhance efficiency of treatment. Fundus imaging, a non-invasive diagnostic technique, is the most frequently used mode for analyzing retinal abnormalities related to diabetic retinopathy. Computer-aided methods based on retinal fundus images support quick diagnosis, impart an additional perspective during decision-making, and behave as an efficient means to assess response of treatment on retinal abnormalities. However, in order to evaluate computer-aided systems, a benchmark database of clinical retinal fundus images is required. Therefore, a representative database comprising of 2942 clinical retinal fundus images is developed and presented in this work. This clinical database, having varying attributes such as position, dimensions, shapes, and color, is formed to evaluate the generalization capability of computer-aided systems for diabetic retinopathy diagnosis. A framework for the development of benchmark retinal fundus images database is also proposed. The developed database comprises of medical image annotations for each image from expert ophthalmologists corresponding to anatomical structures, retinal lesions and stage of diabetic retinopathy. In addition, the substantial performance comparison capability of the proposed database aids in analyzing candidature of different methods, and subsequently its usage in medical practice for real-time applications.

scholarly journals Loss-Based Attention for Deep Multiple Instance Learning

2020 ◽  
Vol 34 (04) ◽  
pp. 5742-5749
Author(s):  
Xiaoshuang Shi ◽  
Fuyong Xing ◽  
Yuanpu Xie ◽  
Zizhao Zhang ◽  
Lei Cui ◽  
...  
Keyword(s):  
State Of The Art ◽  
Classification Performance ◽  
Multiple Instance Learning ◽  
Attention Mechanism ◽  
Cross Entropy ◽  
General Category ◽  
Source Codes ◽  
Model Generalization ◽  
Fully Connected ◽  
Entropy Functions

Although attention mechanisms have been widely used in deep learning for many tasks, they are rarely utilized to solve multiple instance learning (MIL) problems, where only a general category label is given for multiple instances contained in one bag. Additionally, previous deep MIL methods firstly utilize the attention mechanism to learn instance weights and then employ a fully connected layer to predict the bag label, so that the bag prediction is largely determined by the effectiveness of learned instance weights. To alleviate this issue, in this paper, we propose a novel loss based attention mechanism, which simultaneously learns instance weights and predictions, and bag predictions for deep multiple instance learning. Specifically, it calculates instance weights based on the loss function, e.g. softmax+cross-entropy, and shares the parameters with the fully connected layer, which is to predict instance and bag predictions. Additionally, a regularization term consisting of learned weights and cross-entropy functions is utilized to boost the recall of instances, and a consistency cost is used to smooth the training process of neural networks for boosting the model generalization performance. Extensive experiments on multiple types of benchmark databases demonstrate that the proposed attention mechanism is a general, effective and efficient framework, which can achieve superior bag and image classification performance over other state-of-the-art MIL methods, with obtaining higher instance precision and recall than previous attention mechanisms. Source codes are available on https://github.com/xsshi2015/Loss-Attention.

scholarly journals Early Detection of Diabetic Retinopathy Using PCA-Firefly Based Deep Learning Model

Electronics ◽  
2020 ◽  
Vol 9 (2) ◽  
pp. 274 ◽  
Author(s):  
Thippa Reddy Gadekallu ◽  
Neelu Khare ◽  
Sweta Bhattacharya ◽  
Saurabh Singh ◽  
Praveen Kumar Reddy Maddikunta ◽  
...  
Keyword(s):  
Machine Learning ◽  
Diabetic Retinopathy ◽  
Deep Learning ◽  
Early Detection ◽  
Dimensionality Reduction ◽  
Vision Loss ◽  
Principal Component ◽  
Screening Methods ◽  
Learning Approaches ◽  
Time Period

Diabetic Retinopathy is a major cause of vision loss and blindness affecting millions of people across the globe. Although there are established screening methods - fluorescein angiography and optical coherence tomography for detection of the disease but in majority of the cases, the patients remain ignorant and fail to undertake such tests at an appropriate time. The early detection of the disease plays an extremely important role in preventing vision loss which is the consequence of diabetes mellitus remaining untreated among patients for a prolonged time period. Various machine learning and deep learning approaches have been implemented on diabetic retinopathy dataset for classification and prediction of the disease but majority of them have neglected the aspect of data pre-processing and dimensionality reduction, leading to biased results. The dataset used in the present study is a diabetes retinopathy dataset collected from the UCI machine learning repository. At its inceptions, the raw dataset is normalized using the Standardscalar technique and then Principal Component Analysis (PCA) is used to extract the most significant features in the dataset. Further, Firefly algorithm is implemented for dimensionality reduction. This reduced dataset is fed into a Deep Neural Network Model for classification. The results generated from the model is evaluated against the prevalent machine learning models and the results justify the superiority of the proposed model in terms of Accuracy, Precision, Recall, Sensitivity and Specificity.

CURVELET FUSION ENHACEMENT BASED EVALUATION OF DIABETIC RETINOPATHY BY THE IDENTIFICATION OF EXUDATES IN OPTIC COLOR FUNDUS IMAGES

2016 ◽  
Vol 28 (06) ◽  
pp. 1650046
Author(s):  
V. Ratna Bhargavi ◽  
Ranjan K. Senapati
Keyword(s):  
Diabetic Retinopathy ◽  
Vision Loss ◽  
Detection System ◽  
Clinical Signs ◽  
Posterior Part ◽  
Curvelet Transform ◽  
Optic Disk ◽  
Support Vector ◽  
Fundus Images ◽  
Statistical Measures

Rapid growth of Diabetes mellitus in people causes damage to posterior part of eye vessel structures. Diabetic retinopathy (DR) is an important hurdle in diabetic people and it causes lesion formation in retina due to retinal vessel structures damage. Bright lesions (BLs) or exudates are initial clinical signs of DR. Early BLs detection can help avoiding vision loss. The severity can be recognized based on number of BLs formed in the color fundus image. Manually diagnosing a large amount of images is time consuming. So a computerized DR grading and BLs detection system is proposed. In this paper for BLs detection, curvelet fusion enhancement is done initially because bright objects maps to largest coefficients in an image by utilizing the curvelet transform, so that BLs can be recognized in the retina easily. Then optic disk (OD) appearance is similar to BLs and vessel structures are barriers for lesion exact detection and moreover OD falsely classified as BLs and that increases false positives in classification. So these structures are segmented and eliminated by thresholding techniques. Various features were obtained from detected BLs. Publicly available databases are used for DR severity testing. 260 fundus images were used for the performance evaluation of proposed work. The support vector machine classifier (SVM) used to separate fundus images in various levels of DR based on feature set extracted. The proposed system that obtained the statistical measures were sensitivity 100%, specificity 95.4% and accuracy 97.74%. Compared to existing state-of-art techniques, the proposed work obtained better results in terms of sensitivity, specificity and accuracy.

scholarly journals In Search for the Optimal Preprocessing Technique for Deep Learning Based Diabetic Retinopathy Stage Classification from Fundus Images

2021 ◽  
Author(s):  
Nilarun Mukherjee ◽  
Souvik Sengupta
Keyword(s):  
Diabetic Retinopathy ◽  
Deep Learning ◽  
Vision Loss ◽  
Fundus Images ◽  
New Combinations ◽  
Z Score ◽  
Kappa Score ◽  
Stage Classification ◽  
Classification Tasks ◽  
Intensity Normalization

Abstract Background: Diabetic retinopathy (DR) is a complication of diabetes mellitus, which if left untreated may lead to complete vision loss. Early diagnosis and treatment is the key to prevent further complications of DR. Computer-aided diagnosis is a very effective method to support ophthalmologists, as manual inspection of pathological changes in retina images are time consuming and expensive. In recent times, Machine Learning and Deep Learning techniques have subsided conventional rule based approaches for detection, segmentation and classification of DR stages and lesions in fundus images. Method: In this paper, we present a comparative study of the different state-of-the-art preprocessing methods that have been used in deep learning based DR classification tasks in recent times and also propose a new unsupervised learning based retinal region extraction technique and new combinations of preprocessing pipelines designed on top of it. Efficacy of different existing and new combinations of the preprocessing methods are analyzed using two publicly available retinal datasets (EyePACS and APTOS) for different DR stage classification tasks, such as referable DR, DR screening, and five-class DR grading, using a benchmark deep learning model (ResNet-50). Results: It has been observed that the proposed preprocessing strategy composed of region of interest extraction through K-means clustering followed by contrast and edge enhancement using Graham’s method and z-score intensity normalization achieved the highest accuracy of 98.5%, 96.51% and 90.59% in DR-screening, referable-DR, and DR gradation tasks respectively and also achieved the best quadratic weighted kappa score of 0.945 in DR grading task. It achieved best AUC-ROC of 0.98 and 0.9981 in DR grading and DR screening tasks respectively. Conclusion: It is evident from the results that the proposed preprocessing pipeline composed of the proposed ROI extraction through K-means clustering, followed by edge and contrast enhancement using Graham’s method and then z-score intensity normalization outperforms all other existing preprocessing pipelines and has proven to be the most effective preprocessing strategy in helping the baseline CNN model to extract meaningful deep features.

scholarly journals Developments for Diabetic Retinopathy Detection and Classification: A Review

2018 ◽  
Vol 7 (4.5) ◽  
pp. 134
Author(s):  
Pooja M. Pawar ◽  
Avinash J. Agrawal
Keyword(s):  
Diabetic Retinopathy ◽  
Vision Loss ◽  
Eye Disease ◽  
Retinal Images ◽  
Screening Methods ◽  
Fundus Images ◽  
Insulin Deficiency ◽  
Vascular Disorder ◽  
Impaired Metabolism ◽  
Color Fundus Images

Diabetes is characterized by impaired metabolism of glucose caused by insulin deficiency. Diabetic retinopathy is the eye disease, is caused by retinal damage which is generally formed as a result of diabetes mellitus. It is a serious vascular disorder for which early detection and the treatment are required to inhibit the intense vision loss. Also, the diagnosis entails skilled professionals for detection because non-automatic screening methods are very time consuming and are not that efficient for a large number of retinal images. This paper provides a broad review of various techniques and methodologies used by the authors for diabetic retinopathy detection and classification. Furthermore, most recent work and developments are studied in this paper. We are proposing an advanced deep learning CNN approach for automatic diagnosis of DR from color fundus images.  

Sign in / Sign up

Export Citation Format

Share Document