Diabetic Retinopathy (DR) is an ophthalmic disease that damages retinal blood vessels. DR causes impaired vision and may even lead to blindness if it is not diagnosed in early stages. DR has five stages or classes, namely normal, mild, moderate, severe and PDR (Proliferative Diabetic Retinopathy). Normally, highly trained experts examine the colored fundus images to diagnose this fatal disease. This manual diagnosis of this condition (by clinicians) is tedious and error-prone. Therefore, various computer vision-based techniques have been proposed to automatically detect DR and its different stages from retina images. However, these methods are unable to encode the underlying complicated features and can only classify DR's different stages with very low accuracy particularly, for the early stages. In this research, we used the publicly available Kaggle dataset of retina images to train an ensemble of five deep Convolution Neural Network (CNN) models (Resnet50, Inceptionv3, Xception, Dense121, Dense169) to encode the rich features and improve the classification for different stages of DR. The experimental results show that the proposed model detects all the stages of DR unlike the current methods and performs better compared to state-of-the-art methods on the same Kaggle dataset.

/pdf/a-deep-learning-ensemble-approach-for-diabetic-retinopathy-44hmr2lw63.pdf

A Deep Learning Ensemble Approach for Diabetic Retinopathy Detection

Diabetic retinopathy detection through deep learning techniques: A review

Deep learning (DL) systems are widely used in domains including aircraft collision avoidance systems, Alzheimer's disease diagnosis, and autonomous driving cars. Despite the requirement for high reliability, DL systems are difficult to test. Existing DL testing work focuses on testing the DL models, not the implementations (e.g., DL software libraries) of the models. One key challenge of testing DL libraries is the difficulty of knowing the expected output of DL libraries given an input instance. Fortunately, there are multiple implementations of the same DL algorithms in different DL libraries. Thus, we propose CRADLE, a new approach that focuses on finding and localizing bugs in DL software libraries. CRADLE (1) performs cross-implementation inconsistency checking to detect bugs in DL libraries, and (2) leverages anomaly propagation tracking and analysis to localize faulty functions in DL libraries that cause the bugs. We evaluate CRADLE on three libraries (TensorFlow, CNTK, and Theano), 11 datasets (including ImageNet, MNIST, and KGS Go game), and 30 pre-trained models. CRADLE detects 12 bugs and 104 unique inconsistencies, and highlights functions relevant to the causes of inconsistencies for all 104 unique inconsistencies.

CRADLE: Cr oss-backend v a lidation to D etect and L ocalize bugs in D e ep learning libraries

Remarkable advances in biomedical research have led to the generation of large amounts of data. Using artificial intelligence, it has become possible to extract meaningful information from large volumes of data, in a shorter frame of time, with very less human interference. In effect, convolutional neural networks (a deep learning method) have been taught to recognize pathological lesions from images. Diabetes has high morbidity, with millions of people who need to be screened for diabetic retinopathy (DR). Deep neural networks offer a great advantage of screening for DR from retinal images, in improved identification of DR lesions and risk factors for diseases, with high accuracy and reliability. This review aims to compare the current evidences on various deep learning models for diagnosis of diabetic retinopathy (DR).

/pdf/fundus-photograph-based-deep-learning-algorithms-in-504gir29ow.pdf

Fundus photograph-based deep learning algorithms in detecting diabetic retinopathy.

Diabetic retinopathy (DR) is a disease resulting from diabetes complications, causing non-reversible damage to retina blood vessels. DR is a leading cause of blindness if not detected early. The currently available DR treatments are limited to stopping or delaying the deterioration of sight, highlighting the importance of regular scanning using high-efficiency computer-based systems to diagnose cases early. The current work presented fully automatic diagnosis systems that exceed manual techniques to avoid misdiagnosis, reducing time, effort and cost. The proposed system classifies DR images into five stages-no-DR, mild, moderate, severe and proliferative DR-as well as localizing the affected lesions on retain surface. The system comprises two deep learning-based models. The first model (CNN512) used the whole image as an input to the CNN model to classify it into one of the five DR stages. It achieved an accuracy of 88.6% and 84.1% on the DDR and the APTOS Kaggle 2019 public datasets, respectively, compared to the state-of-the-art results. Simultaneously, the second model used an adopted YOLOv3 model to detect and localize the DR lesions, achieving a 0.216 mAP in lesion localization on the DDR dataset, which improves the current state-of-the-art results. Finally, both of the proposed structures, CNN512 and YOLOv3, were fused to classify DR images and localize DR lesions, obtaining an accuracy of 89% with 89% sensitivity, 97.3 specificity and that exceeds the current state-of-the-art results.

https://www.mdpi.com/1424-8220/21/11/3704/pdf

Diabetic Retinopathy Fundus Image Classification and Lesions Localization System Using Deep Learning

Diabetes or more precisely Diabetes Mellitus (DM) is a metabolic disorder happens because of high blood sugar level in the body. Over the time, diabetes creates eye deficiency also called as Diabetic Retinopathy (DR) causes major loss of vision. The symptoms can originate in the retinal area are augmented blood vessels, fluid drip, exudates, hemorrhages, and micro aneurysms. In modern medical science, images are the indispensable tool for precise diagnosis of patients. In the meantime evaluation of contemporary medical imageries remains complex. In recent times computer vision with Deep Neural Networks can train a model perfectly and level of accuracy also will be higher than other neural network models. In this study fundus images containing diabetic retinopathy has been taken into consideration. The idea behind this paper is to propose an automated knowledge model to identify the key antecedents of DR. Proposed Model have been trained with three types, back propagation NN, Deep Neural Network (DNN) and Convolutional Neural Network (CNN) after testing models with CPU trained Neural network gives lowest accuracy because of one hidden layers whereas the deep learning models are out performing NN. The Deep Learning models are capable of quantifying the features as blood vessels, fluid drip, exudates, hemorrhages and micro aneurysms into different classes. Model will calculate the weights which gives severity level of the patient’s eye. The foremost challenge of this study is the accurate verdict of each feature class thresholds. To identify the target class thresholds weighted Fuzzy C-means algorithm has been used. The model will be helpful to identify the proper class of severity of diabetic retinopathy images.

/pdf/classification-of-diabetic-retinopathy-images-by-using-deep-31ffo5811u.pdf

Classification of Diabetic Retinopathy Images by Using Deep Learning Models

Deep Learning(DL) techniques are conquering over the prevailing traditional approaches of neural network, when it comes to the huge amount of dataset, applications requiring complex functions demanding increase accuracy with lower time complexities. Neurosciences has already exploited DL techniques, thus portrayed itself as an inspirational source for researchers exploring the domain of Machine learning. DL enthusiasts cover the areas of vision, speech recognition, motion planning and NLP as well, moving back and forth among fields. This concerns with building models that can successfully solve variety of tasks requiring intelligence and distributed representation. The accessibility to faster CPUs, introduction of GPUs-performing complex vector and matrix computations, supported agile connectivity to network. Enhanced software infrastructures for distributed computing worked in strengthening the thought that made researchers suffice DL methodologies. The paper emphases on the following DL procedures to traditional approaches which are performed manually for classifying medical images. The medical images are used for the study Diabetic Retinopathy(DR) and computed tomography (CT) emphysema data. Both DR and CT data diagnosis is difficult task for normal image classification methods. The initial work was carried out with basic image processing along with K-means clustering for identification of image severity levels. After determining image severity levels ANN has been applied on the data to get the basic classification result, then it is compared with the result of DNNs (Deep Neural Networks), which performed efficiently because of its multiple hidden layer features basically which increases accuracy factors, but the problem of vanishing gradient in DNNs made to consider Convolution Neural Networks (CNNs) as well for better results. The CNNs are found to be providing better outcomes when compared to other learning models aimed at classification of images. CNNs are favoured as they provide better visual processing models successfully classifying the noisy data as well. The work centres on the detection on Diabetic Retinopathy-loss in vision and recognition of computed tomography (CT) emphysema data measuring the severity levels for both cases. The paper discovers how various Machine Learning algorithms can be implemented ensuing a supervised approach, so as to get accurate results with less complexity possible.

https://iopscience.iop.org/article/10.1088/1757-899X/263/4/042097/pdf

A comparative study of deep learning models for medical image classification

In today’s computer world security, integrity, confidentiality of the organization’s data is the most important issue. This paper deals with the confidentiality of electronic data which is transmitted over the internet. Data encryption is widely used to ensure security of the data. Genetic algorithms (GAs) are a class of optimization algorithms. Many problems can be solved using genetic algorithms through modeling a simplified version of genetic processes. In our approach we are using the concept of genetic algorithms with pseudorandom function to encrypt and decrypt data stream. The encryption process is applied over a binary file so that the algorithm can be applied over any type of txt as well as multimedia data.

/pdf/a-cryptography-algorithm-using-the-operations-of-genetic-4nzoplcb0o.pdf

A Cryptography Algorithm Using the Operations of Genetic Algorithm & Pseudo Random Sequence Generating Functions

. minimum spanning tree (MST) of a connected, undirected and weighted network is a tree of that network consisting of all its nodes and the sum of weights of all its edges is minimum among all such possible spanning trees of the same network. In this study, we have developed a new GIS tool using most commonly known rudimentary algorithm called Prim’s algorithm to construct the minimum spanning tree of a connected, undirected and weighted road network. This algorithm is based on the weight (adjacency) matrix of a weighted network and helps to solve complex network MST problem easily, efficiently and effectively. The selection of the appropriate algorithm is very essential otherwise it will be very hard to get an optimal result. In case of Road Transportation Network, it is very essential to find the optimal results by considering all the necessary points based on cost factor (time or distance). This paper is based on solving the Minimum Spanning Tree (MST) problem of a road network by finding it’s minimum span by considering all the important network junction point. GIS technology is usually used to solve the network related problems like the optimal path problem, travelling salesman problem, vehicle routing problems, location-allocation problems etc. Therefore, in this study we have developed a customized GIS tool using Python script in ArcGIS software for the solution of MST problem for a Road Transportation Network of Dehradun city by considering distance and time as the impedance (cost) factors. It has a number of advantages like the users do not need a greater knowledge of the subject as the tool is user-friendly and that allows to access information varied and adapted the needs of the users. This GIS tool for MST can be applied for a nationwide plan called Prime Minister Gram Sadak Yojana in India to provide optimal all weather road connectivity to unconnected villages (points). This tool is also useful for constructing highways or railways spanning several cities optimally or connecting all cities with minimum total road length.

/pdf/development-of-gis-tool-for-the-solution-of-minimum-spanning-3vacngdvt5.pdf

Development of Gis Tool for the Solution of Minimum Spanning Tree Problem using Prim's Algorithm

The Indian Space Research Organisation (ISRO) and the Centre National d'etudes Spatiales (CNES) jointly launched
SARAL/AltiKa (Satellite with ARgos and ALtiKa) in February 2013. AltiKa is the first mono frequency (Ka-band) radar
altimeter with dual frequency radiometer. SARAL/AltiKa promises reliable results on retrieving water level of inland
water and coastal bodies, though recognition pattern as well as interpreting and modeling of AltiKa waveforms at land
water boundary is still a challenge. Different Retracking methods are widely used for determining the water level more
correctly. An altimetry waveform also gives vital information about the reflecting surface. So, waveform classification is
many times needed for retrieving surface information or before applying retracking method. In this paper, SARAL/AltiKa
40 Hz waveform dataset (Pass #152) over the Maithon Reservoir, Jharkhand, India were classified using evolutionary
minimize indexing function (EMIF) with k-means. A fitness function was used in EMIF to map sampled AltiKa waveforms
into single valued scalar. Four waveform groups were identified according to reflection from water, land and land-water
boundary. Land-water boundary again divided into two classes viz., land-to-water and water-to-land based on direction of
the AltiKa pass over the reservoir. Normalized Differenced Water Index (NDWI) derived from Landsat 8 OLI and Google
Earth imagery of nearest date of AltiKa pass was used for accuracy assessment of the proposed method. It was found that
the waveforms were classified with 85.7 kappa accuracy. The results of the proposed EMIF will be helpful for identify the
SARAL/AltiKa waveforms classes over the inland water bodies.

Suvajit Dutta

Papers

Classification of Diabetic Retinopathy Images by Using Deep Learning Models

A comparative study of deep learning models for medical image classification

A Cryptography Algorithm Using the Operations of Genetic Algorithm & Pseudo Random Sequence Generating Functions

Development of Gis Tool for the Solution of Minimum Spanning Tree Problem using Prim's Algorithm

A new method for SARAL/AltiKa waveform classification: contextual analysis over the Maithon Reservoir, Jharkhand, India