scholarly journals Weakly Supervised Sensitive Heatmap framework to classify and localize diabetic retinopathy lesions

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Mohammed Al-Mukhtar ◽  
Ameer Hussein Morad ◽  
Mustafa Albadri ◽  
MD Samiul Islam
Keyword(s):  
Diabetic Retinopathy ◽  
Supervised Learning ◽  
Automatic Detection ◽  
Training Data ◽  
Optic Disk ◽  
Test Accuracy ◽  
Fundus Images ◽  
Data Set ◽  
Weakly Supervised ◽  
The Impact

AbstractVision loss happens due to diabetic retinopathy (DR) in severe stages. Thus, an automatic detection method applied to diagnose DR in an earlier phase may help medical doctors to make better decisions. DR is considered one of the main risks, leading to blindness. Computer-Aided Diagnosis systems play an essential role in detecting features in fundus images. Fundus images may include blood vessels, exudates, micro-aneurysm, hemorrhages, and neovascularization. In this paper, our model combines automatic detection for the diabetic retinopathy classification with localization methods depending on weakly-supervised learning. The model has four stages; in stage one, various preprocessing techniques are applied to smooth the data set. In stage two, the network had gotten deeply to the optic disk segment for eliminating any exudate's false prediction because the exudates had the same color pixel as the optic disk. In stage three, the network is fed through training data to classify each label. Finally, the layers of the convolution neural network are re-edited, and used to localize the impact of DR on the patient's eye. The framework tackles the matching technique between two essential concepts where the classification problem depends on the supervised learning method. While the localization problem was obtained by the weakly supervised method. An additional layer known as weakly supervised sensitive heat map (WSSH) was added to detect the ROI of the lesion at a test accuracy of 98.65%, while comparing with Class Activation Map that involved weakly supervised technology achieved 0.954. The main purpose is to learn a representation that collect the central localization of discriminative features in a retina image. CNN-WSSH model is able to highlight decisive features in a single forward pass for getting the best detection of lesions.

scholarly journals WSSH_DR: Weakly Supervised Sensitive Heatmap Framework to Classify and Localize Diabetic Retinopathy Lesions

2021 ◽  
Author(s):  
Mohammed Almukhtar ◽  
Ameer Morad ◽  
Mustafa Albadri ◽  
MD Islam
Keyword(s):  
Diabetic Retinopathy ◽  
Supervised Learning ◽  
Automatic Detection ◽  
Training Data ◽  
Optic Disk ◽  
Test Accuracy ◽  
Fundus Images ◽  
Data Set ◽  
Weakly Supervised ◽  
The Impact

Abstract Vision loss happens due to diabetic retinopathy (DR) in severe stages. Thus, an automatic detection method applied to diagnose DR in an earlier phase may help medical doctors to make better decisions. DR is considered one of the main risks, leading to blindness. Computer-Aided Diagnosis (CAD) systems play an essential role in detecting features in fundus images. Fundus images may include blood vessel area, exudates, micro-aneurysm, hemorrhages, and neovascularization. In this paper, our model combines automatic detection for the diabetic retinopathy classification with localization methods depending on weakly-supervised learning. The model has four stages; in stage one, various preprocessing techniques are applied for smoothing the data set. In stage two, the network had gotten deeply to the optic disk segment for eliminating any exudate's false prediction because the exudates had the same color pixel as the optic disk. Stage three, the network is fed through training data to classify each class label. Finally, the layers of the convolution neural network are re-edited, and the layers are used to localize the impact of DR on the eye's patient. The framework tackled the matching technique between two essential concepts where the classification problem depends on the supervised learning method. In comparison, the localization problem was obtained by the weakly supervised method. An additional layer known as weakly supervised sensitive heat map (WSSH) was added to detect the ROI of the lesion at a test accuracy of 98.65%.

scholarly journals The SUSTech-SYSU dataset for automated exudate detection and diabetic retinopathy grading

2020 ◽  
Vol 7 (1) ◽  
Author(s):  
Li Lin ◽  
Meng Li ◽  
Yijin Huang ◽  
Pujin Cheng ◽  
Honghui Xia ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Supervised Learning ◽  
Automated Detection ◽  
Training Data ◽  
Classification Algorithms ◽  
Fundus Images ◽  
Severity Scale ◽  
Great Opportunity ◽  
Detection Algorithms

AbstractAutomated detection of exudates from fundus images plays an important role in diabetic retinopathy (DR) screening and evaluation, for which supervised or semi-supervised learning methods are typically preferred. However, a potential limitation of supervised and semi-supervised learning based detection algorithms is that they depend substantially on the sample size of training data and the quality of annotations, which is the fundamental motivation of this work. In this study, we construct a dataset containing 1219 fundus images (from DR patients and healthy controls) with annotations of exudate lesions. In addition to exudate annotations, we also provide four additional labels for each image: left-versus-right eye label, DR grade (severity scale) from three different grading protocols, the bounding box of the optic disc (OD), and fovea location. This dataset provides a great opportunity to analyze the accuracy and reliability of different exudate detection, OD detection, fovea localization, and DR classification algorithms. Moreover, it will facilitate the development of such algorithms in the realm of supervised and semi-supervised learning.

Underwater Acoustic Target Recognition Based on Generative Adversarial Network Data Augmentation

2021 ◽  
Vol 263 (2) ◽  
pp. 4558-4564
Author(s):  
Minghong Zhang ◽  
Xinwei Luo
Keyword(s):  
Data Augmentation ◽  
Target Recognition ◽  
Training Data ◽  
Small Samples ◽  
Generative Adversarial Network ◽  
Data Set ◽  
Underwater Acoustic ◽  
Adversarial Network ◽  
Acoustic Target ◽  
The Impact

Underwater acoustic target recognition is an important aspect of underwater acoustic research. In recent years, machine learning has been developed continuously, which is widely and effectively applied in underwater acoustic target recognition. In order to acquire good recognition results and reduce the problem of overfitting, Adequate data sets are essential. However, underwater acoustic samples are relatively rare, which has a certain impact on recognition accuracy. In this paper, in addition of the traditional audio data augmentation method, a new method of data augmentation using generative adversarial network is proposed, which uses generator and discriminator to learn the characteristics of underwater acoustic samples, so as to generate reliable underwater acoustic signals to expand the training data set. The expanded data set is input into the deep neural network, and the transfer learning method is applied to further reduce the impact caused by small samples by fixing part of the pre-trained parameters. The experimental results show that the recognition result of this method is better than the general underwater acoustic recognition method, and the effectiveness of this method is verified.

scholarly journals Automatic detection of diabetic retinopathy and its progression in sequential fundus images of patients with diabetes

2018 ◽  
Vol 97 (4) ◽  
pp. e667-e669
Author(s):  
Alexander Dietzel ◽  
Carolin Schanner ◽  
Aura Falck ◽  
Nina Hautala
Keyword(s):  
Diabetic Retinopathy ◽  
Automatic Detection ◽  
Fundus Images ◽  
Patients With Diabetes

scholarly journals United Kingdom Diabetic Retinopathy Electronic Medical Record (UK DR EMR) Users Group: report 4, real-world data on the impact of deprivation on the presentation of diabetic eye disease at hospital services

2018 ◽  
Vol 103 (6) ◽  
pp. 837-843 ◽  
Author(s):  
Alastair K Denniston ◽  
Aaron Y Lee ◽  
Cecilia S Lee ◽  
David P Crabb ◽  
Clare Bailey ◽  
...  
Keyword(s):  
Visual Acuity ◽  
Diabetic Retinopathy ◽  
Medical Record ◽  
Electronic Medical Record ◽  
Real World ◽  
Eye Disease ◽  
Inclusion Criteria ◽  
Data Set ◽  
Diabetic Eye Disease ◽  
The Impact

AimTo assess the impact of deprivation on diabetic retinopathy presentation and related treatment interventions, as observed within the UK hospital eye service.MethodsThis is a multicentre, national diabetic retinopathy database study with anonymised data extraction across 22 centres from an electronic medical record system. The following were the inclusion criteria: all patients with diabetes and a recorded, structured diabetic retinopathy grade. The minimum data set included, for baseline, age and Index of Multiple Deprivation, based on residential postcode; and for all time points, visual acuity, ETDRS grading of retinopathy and maculopathy, and interventions (laser, intravitreal therapies and surgery). The main  outcome measures were (1) visual acuity and binocular visual state, and (2) presence of sight-threatening complications and need for early treatment.Results79 775 patients met the inclusion criteria. Deprivation was associated with later presentation in patients with diabetic eye disease: the OR of being sight-impaired at entry into the hospital eye service (defined as 6/18 to better than 3/60 in the better seeing eye) was 1.29 (95% CI 1.20 to 1.39) for the most deprived decile vs 0.77 (95% CI 0.70 to 0.86) for the least deprived decile; the OR for being severely sight-impaired (3/60 or worse in the better seeing eye) was 1.17 (95% CI 0.90 to 1.55) for the most deprived decile vs 0.88 (95% CI 0.61 to 1.27) for the least deprived decile (reference=fifth decile in all cases). There is also variation in sight-threatening complications at presentation and treatment undertaken: the least deprived deciles had lower chance of having a tractional retinal detachment (OR=0.48 and 0.58 for deciles 9 and 10, 95% CI 0.24 to 0.90 and 0.29 to 1.09, respectively); in terms of accessing treatment, the rate of having a vitrectomy was lowest in the most deprived cohort (OR=0.34, 95% CI 0.19 to 0.58).ConclusionsThis large real-world study suggests that first presentation at a hospital eye clinic with visual loss or sight-threatening diabetic eye disease is associated with deprivation. These initial hospital visits represent the first opportunities to receive treatment and to formally engage with support services. Such patients are more likely to be sight-impaired or severely sight-impaired at presentation, and may need additional resources to engage with the hospital eye services over complex treatment schedules.

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.

An Approach for Automatic Detection and Grading of Macular Edema

2017 ◽  
pp. 1677-1702
Author(s):  
Jyoti Prakash Medhi
Keyword(s):  
Image Processing ◽  
Decision Making ◽  
Diabetic Retinopathy ◽  
Blood Vessel ◽  
Macular Edema ◽  
Automatic Detection ◽  
Automatic Analysis ◽  
Fundus Images

Prolonged Diabetes causes massive destruction to the retina, known as Diabetic Retinopathy (DR) leading to blindness. The blindness due to DR may consequence from several factors such as Blood vessel (BV) leakage, new BV formation on retina. The effects become more threatening when abnormalities involves the macular region. Here automatic analysis of fundus images becomes important. This system checks for any abnormality and help ophthalmologists in decision making and to analyze more number of cases. The main objective of this chapter is to explore image processing tools for automatic detection and grading macular edema in fundus images.

scholarly journals Time-Series Laplacian Semi-Supervised Learning for Indoor Localization †

Sensors ◽  
2019 ◽  
Vol 19 (18) ◽  
pp. 3867 ◽  
Author(s):  
Jaehyun Yoo
Keyword(s):  
Time Series ◽  
Supervised Learning ◽  
Indoor Localization ◽  
Learning Algorithm ◽  
Unlabeled Data ◽  
Training Data ◽  
Practical Implementation ◽  
Additional Information ◽  
Localization Scheme ◽  
The Impact

Machine learning-based indoor localization used to suffer from the collection, construction, and maintenance of labeled training databases for practical implementation. Semi-supervised learning methods have been developed as efficient indoor localization methods to reduce use of labeled training data. To boost the efficiency and the accuracy of indoor localization, this paper proposes a new time-series semi-supervised learning algorithm. The key aspect of the developed method, which distinguishes it from conventional semi-supervised algorithms, is the use of unlabeled data. The learning algorithm finds spatio-temporal relationships in the unlabeled data, and pseudolabels are generated to compensate for the lack of labeled training data. In the next step, another balancing-optimization learning algorithm learns a positioning model. The proposed method is evaluated for estimating the location of a smartphone user by using a Wi-Fi received signal strength indicator (RSSI) measurement. The experimental results show that the developed learning algorithm outperforms some existing semi-supervised algorithms according to the variation of the number of training data and access points. Also, the proposed method is discussed in terms of why it gives better performance, by the analysis of the impact of the learning parameters. Moreover, the extended localization scheme in conjunction with a particle filter is executed to include additional information, such as a floor plan.

Sign in / Sign up

Export Citation Format

Share Document