- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Computer-Assisted Diagnosis for Diabetic Retinopathy Based on Fundus Images Using Deep Convolutional Neural Network
摘要： Diabetic retinopathy (DR) is a complication of long-standing diabetes, which is hard to detect in its early stage because it only shows a few symptoms. Nowadays, the diagnosis of DR usually requires taking digital fundus images, as well as images using optical coherence tomography (OCT). Since OCT equipment is very expensive, it will benefit both the patients and the ophthalmologists if an accurate diagnosis can be made, based solely on reading digital fundus images. In the paper, we present a novel algorithm based on deep convolutional neural network (DCNN). Unlike the traditional DCNN approach, we replace the commonly used max-pooling layers with fractional max-pooling. Two of these DCNNs with a different number of layers are trained to derive more discriminative features for classification. After combining features from metadata of the image and DCNNs, we train a support vector machine (SVM) classifier to learn the underlying boundary of distributions of each class. For the experiments, we used the publicly available DR detection database provided by Kaggle. We used 34,124 training images and 1,000 validation images to build our model and tested with 53,572 testing images. The proposed DR classifier classifies the stages of DR into five categories, labeled with an integer ranging between zero and four. The experimental results show that the proposed method can achieve a recognition rate up to 86.17%, which is higher than previously reported in the literature. In addition to designing a machine learning algorithm, we also develop an app called 'Deep Retina.' Equipped with a handheld ophthalmoscope, the average person can take fundus images by themselves and obtain an immediate result, calculated by our algorithm. It is beneficial for home care, remote medical care, and self-examination.
关键词： deep convolutional neural network,mobile app,fractional max-pooling,support vector machine,diabetic retinopathy,fundus images,teaching-learning-based optimization
更新于2025-09-23 15:23:52
-
[Communications in Computer and Information Science] Advances in Computing and Data Sciences Volume 905 (Second International Conference, ICACDS 2018, Dehradun, India, April 20-21, 2018, Revised Selected Papers, Part I) || Two Stage Histogram Enhancement Schemes to Improve Visual Quality of Fundus Images
摘要： A fundus image plays a signi?cant role to analyze a wide variety of ophthalmic conditions. One of the major challenges faced by ophthalmologist in the analysis of fundus images is its low contrast nature. In this paper, two stage histogram enhancement schemes to improve the visual quality of fundus images are proposed. Fuzzy logic and Histogram Based Enhancement algorithm (FHBE) and Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm are cascaded one after the other to accomplish the two stage enhancement task. This results in two new enhancement schemes, namely FHBE-CLAHE and CLAHE-FHBE. The analysis of the results based on its visual quality shows that two stage enhancement schemes outperforms individual enhancement schemes.
关键词： Fundus images,FHBE,CLAHE,Image enhancement
更新于2025-09-23 15:23:52
-
[Lecture Notes in Computational Vision and Biomechanics] Computer Aided Intervention and Diagnostics in Clinical and Medical Images Volume 31 || Retina as a Biomarker of Stroke
摘要： Stroke is one of the significant reasons of adult impairment in most of the developing nations worldwide. Various imaging modalities are used to diagnose stroke during its initial hours of occurrence. But early prediction of stroke is still a challenge in the field of biomedical research. Since retinal arterioles share similar anatomical, physiological, and embryological attributes with brain arterioles, analysis of retinal fundus images can be of great significance in stroke prognosis. This research work mainly analyzes the variations in retinal vasculature in predicting the risk of stroke. Fractal dimension, branching coefficients and angle, asymmetry factor and optimality ratio for both arteries and veins were computed from the processed input image and given to a support vector machine classifier which gives promising results.
关键词： Support vector machine,Stroke,Retinal fundus images
更新于2025-09-23 15:23:52
-
Automatic determination of vertical cup-to-disc ratio in retinal fundus images for glaucoma screening
摘要： Glaucoma is a chronic progressive optic neuropathy that causes visual impairment or blindness, if left untreated. It is crucial to diagnose it at an early stage in order to enable treatment. Fundus photography is a viable option for population-based screening. A fundus photograph enables the observation of the excavation of the optic disc - the hallmark of glaucoma. The excavation is quanti?ed as vertical cup-to-disc ratio (VCDR). The manual assessment of retinal fundus images is, however, time-consuming and costly. Thus, an automated system is necessary to assist human observers. We propose a computer aided diagnosis system, which consists of localization of the optic disc, determination of the height of the optic disc and the cup, and computation of the VCDR. We evaluated the performance of our approach on eight publicly available data sets, which have in total 1712 retinal fundus images. We compared the obtained VCDR values with those provided by an experienced ophthalmologist and achieved a weighted VCDR mean difference of 0.11. The system provides a reliable estimation of the height of the optic disc and the cup in terms of the Relative Height Error (RHE = 0.08 and 0.09, respectively). Bland-Altman analysis showed that the system achieves a good agreement with the manual annotations especially for large VCDRs, which indicate pathology.
关键词： GMLVQ,Glaucoma,retinal fundus images,vertical cup-to-disc ratio,trainable COSFIRE ?lters
更新于2025-09-23 15:23:52
-
Automatic detection of diabetic retinopathy and its progression in sequential fundus images of patients with diabetes
摘要： Regular screening by fundus images is known to be effective in detecting the early signs of diabetic retinopathy (DR). Early detection and timely treatment of DR are crucial to prevent the development of sight-threatening DR and visual loss. Due to global increase in the prevalence of diabetes from the current 425 million to 629 million in 2045, also the number of people with DR are estimated to triple from 2005 to 2050. Thus, the workload required for screening for DR will increase tremendously. Novel technological solutions and interventions might fortunately ease this challenging task in the future. We have developed an algorithm to detect early DR and its progression in the chronological follow-up fundus images to minimize the time-consuming evaluation of the images by a trained nurse or an ophthalmologist.
关键词： progression,diabetic retinopathy,fundus images,automatic detection,diabetes
更新于2025-09-23 15:21:01
-
Modified Curvature-based Trigonometric Identities for Retinal Blood Vessel Tortuosity Measurement in Diabetic Retinopathy Fundus Images
摘要： In current clinical practice, there is no specific standard and grading system that can be used to measure the behaviour of the retinal blood vessel curvature. The retinal blood vessel curvature is measured based on clinical experiences. It is very subjective and inconsistent to describe the presence of tortuosity in fundus images. Thus, this paper aims to measure the tortuosity of retinal blood vessel using curvature-based method and investigate its relationship with diabetic retinopathy (DR) disease. The proposed tortuosity measures have been tested on 43 fundus images belonging to patients who have been diagnosed with DR disease and validated by two clinical experts from our collaborative hospital. On average, the proposed algorithm achieved 90.7% (accuracy), 98.72% (sensitivity) and 9.3% (false negative rate), that shows significant tortuosity presence in diabetic retinopathy fundus images.
关键词： Tortuosity,Retinal Blood Vessel,Digital Fundus Images,Diabetic Retinopathy,Curvature-based Method
更新于2025-09-10 09:29:36
-
Retinal vascular tortuosity assessment: inter-intra expert analysis and correlation with computational measurements
摘要： Background: The retinal vascular tortuosity can be a potential indicator of relevant vascular and non-vascular diseases. However, the lack of a precise and standard guide for the tortuosity evaluation hinders its use for diagnostic and treatment purposes. This work aims to advance in the standardization of the retinal vascular tortuosity as a clinical biomarker with diagnostic potential, allowing, thereby, the validation of objective computational measurements on the basis of the entire spectrum of the expert knowledge. Methods: This paper describes a multi-expert validation process of the computational vascular tortuosity measurements of reference. A group of five experts, covering the different clinical profiles of an ophthalmological service, and a four-grade scale from non-tortuous to severe tortuosity as well as non-tortuous / tortuous and asymptomatic / symptomatic binary classifications are considered for the analysis of the the multi-expert validation procedure. The specialists rating process comprises two rounds involving all the experts and a joint round to establish consensual rates. The expert agreement is analyzed throughout the rating procedure and, then, the consensual rates are set as the reference to validate the prognostic performance of four computational tortuosity metrics of reference. Results: The Kappa indexes for the intra-rater agreement analysis were obtained between 0.35 and 0.83 whereas for the inter-rater agreement in the asymptomatic / symptomatic classification were between 0.22 and 0.76. The Area Under the Curve (AUC) for each expert against the consensual rates were placed between 0.61 and 0.83 whereas the prognostic performance of the best objective tortuosity metric was 0.80. Conclusions: There is a high inter and intra-rater variability, especially for the case of the four grade scale. The prognostic performance of the tortuosity measurements is close to the experts’ performance, especially for Grisan measurement. However, there is a gap between the automatic effectiveness and the expert perception given the lack of clinical criteria in the computational measurements.
关键词： Vascular tortuosity,Retinal circulation,Fundus images,Image analysis,Computer-aided diagnosis
更新于2025-09-10 09:29:36
-
Mapping Functions Driven Robust Retinal Vessel Segmentation via Training Patches
摘要： Vein occlusions and diabetic retinopathy are two of many retinal pathologies affecting the retina. Understanding robust vessel segmentation of fundus images is of vital importance for improving the diagnosis results of these diseases. This paper proposes a novel approach for computing the minimum distance for each test patch via the distance comparison within the test patch and cluster centers. The numerous patches are calculated using manual segmentations through the K-means algorithm. We demonstrate the efficiency of learning the simple pattern from each cluster; meanwhile, the mapping function for each cluster is determined by the patches in the training images and their corresponding manual segmentation patches. Two publicly recognized benchmark data sets, namely DRIVE and STARE, are used in our experimental validation. Experimental results show that the proposed approach outperforms conventional methods for vessel segmentation problems validated via public benchmark data sets, i.e., DRIVE and STARE.
关键词： Fundus images,mapping functions,vessel segmentation
更新于2025-09-10 09:29:36
-
High Quality - Low Computational Cost Technique for Automated Principal Object Segmentation Applied in Solar and Medical Imaging
摘要： The objective of this paper is to introduce a fully computerized, simple and low-computational cost technique that can be used in the preprocessing stages of digital images. This technique is specially designed to detect the principal (largest) closed shape object that embody the useful information in certain image types and neglect and avoid other noisy objects and artifacts. The detection process starts by calculating certain statistics of the image to estimate the amount of bit-plane slicing required to exclude the non-informative and noisy background. A simple closing morphological operation is then applied and followed by circular filter applied only on the outer coarse edge to finalize the detection process. The proposed technique takes its importance from the huge explosion of images that need accurate processing in real time speedy manner. The proposed technique is implemented using MATLAB and tested on many solar and medical images; it was shown by the quantitative evaluation that the proposed technique can handle real-life (e.g. solar, medical fundus) images and shows very good potential even under noisy and artifacts conditions. Compared to the publicly available datasets, 97% and 99% of similarity detection is achieved in medical and solar images, respectively. Although it is well-know, the morphological bit-plane slicing technique is hoped to be used in the preprocessing stages of different applications to ease the subsequent image processing stages especially in real time applications where the proposed technique showed dramatic (~100 times) saving in processing time.
关键词： solar images,image preprocessing,medical fundus images,morphological bit-plane slicing
更新于2025-09-09 09:28:46
-
[IEEE 2018 International Conference on Soft-computing and Network Security (ICSNS) - Coimbatore, India (2018.2.14-2018.2.16)] 2018 International Conference on Soft-computing and Network Security (ICSNS) - Severity level detection of diabetic retinopathy using ELM classifier
摘要： An eye disease which destroys the normal vision ability of diabetic patients is known as diabetic retinopathy. Early diagnosis of this disease is necessary because, it is severe in the later stages. The presence exudates, micro aneurysms(MAs) and hemorrhages are the first clinical symptoms of this disease. Exudates are red dots formed by swelling of the weak part of the capillary wall. The detection of exudate in retinal fundus images and the severity level is an important task in applications such as diabetic retinopathy screening and early treatment. Diabetic retinopathy is identified by pouring chemical solution to the eye and then capturing the dilated image of the patient’s eye. This process causes irritation to the patients. This paper proposes a method to find the severity level of diabetic retinopathy. It uses non-dilated retinal fundus image to help ophthalmologists diagnose the disease. The exudates from the low contrast images are detected. A neighborhood based segmentation technique is used for localizing the exudates from the images. A support vector machine (SVM) and Extreme learning Machine (ELM) are used as the classifiers. The method assess the severity of the disease. The average classification accuracy for the ELM is 94.76%.
关键词： Color fundus images,ELM classifier,Micro aneurysms,Diabetic retinopathy
更新于2025-09-09 09:28:46