Wyniki wyszukiwania - BazTech

1

Automated diagnosis of diabetic retinopathy enabled by optimized thresholding-based blood vessel segmentation and hybrid classifier

Narhari Bansode Balbhim, Murlidhar Bakwad Kamlakar, Sayyad Ajij Dildar, Sable Ganesh Shahubha

Bio-Algorithms and Med-Systems

|

2021

|

Vol. 17, no. 1

9--23

EN

Objectives: The focus of this paper is to introduce an automated early Diabetic Retinopathy (DR) detection scheme from colour fundus images through enhanced segmentation and classification strategies by analyzing blood vessels. Methods: The occurrence of DR is increasing from the past years, impacting the eyes due to a sudden rise in the glucose level of blood. All over the world, half of the people who are under age 70 are severely suffered from diabetes. The patients who are affected by DR will lose their vision during the absence of early recognition of DR and appropriate treatment. To decrease the growth and occurrence of loss of vision, the early detection and timely treatment of DR are desirable. At present, deep learning models have presented better performance using retinal images for DR detection. In this work, the input retinal fundus images are initially subjected to pre-processing that undergoes contrast enhancement by Contrast Limited Adaptive Histogram Equalization (CLAHE) and average filtering. Further, the optimized binary thresholding-based segmentation is done for blood vessel segmentation. For the segmented image, Tri-level Discrete Level Decomposition (Tri-DWT) is performed to decompose it. In the feature extraction phase, Local Binary Pattern (LBP), and Gray-Level Co-occurrence Matrices (GLCMs) are extracted. Next, the classification of images is done through the combination of two algorithms, one is Neural Network (NN), and the other Convolutional Neural Network (CNN). The extracted features are subjected to NN, and the triDWT-based segmented image is subjected to CNN. Both the segmentation and classification phases are enhanced by the improved meta-heuristic algorithm called Fitness Ratebased Crow Search Algorithm (FR-CSA), in which few parameters are optimized for attaining maximum detection accuracy. Results: The proposed DR detection model was implemented in MATLAB 2018a, and the analysis was done using three datasets, HRF, Messidor, and DIARETDB. Conclusions: The developed FR-CSA algorithm has the best detection accuracy in diagnosing DR.

2

Retinal vasculature segmentation and measurement framework for color fundus and SLO images

Pachade Samiksha, Porwal Prasanna, Kokare Manesh, Giancardo Luca, Meriaudeau Fabrice

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 3

865--900

EN

The change in vascular geometry is an indicator of various health issues linked with vision and cardiovascular risk factors. Early detection and diagnosis of these changes can help patients to select an appropriate treatment option when the disease is in its primary phase. Automatic segmentation and quantification of these vessels would decrease the cost and eliminate inconsistency related to manual grading. However, automatic detection of the vessels is challenging in the presence of retinal pathologies and non-uniform illumination, two common occurrences in clinical settings. This paper presents a novel framework to address the issue of retinal blood vessel detection and width measurement under these challenging circumstances and also on two different imaging modalities: color fundus imaging and Scanning Laser Ophthalmoscopy (SLO). In this framework, initially, vessel enhancement is done using linear recursive filtering. Then, a unique combination of morphological operations, background estimation, and iterative thresholding are applied to segment the blood vessels. Further, vessel diameter is estimated in two steps: firstly, vessel centerlines are extracted using the graph-based algorithm. Then, vessel edges are localized from the image profiles, by utilizing spline fitting to obtain vascular orientations and then finding the zero-crossings. Extensive experiments have been carried out on several publicly accessible datasets for vessel segmentation and diameter measurement, i.e., DRIVE, STARE, IOSTAR, RC-SLO and REVIEW dataset. Results demonstrate the competitive and comparable performance than earlier methods. The encouraging quantitative and visual performance of the proposed framework makes it an important component of a decision support system for retinal images.

3

Modified U-Net architecture for semantic segmentation of diabetic retinopathy images

Sambyal Nitigya, Saini Poonam, Syal Rupali, Gupta Varun

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 3

1094--1109

EN

Segmentation of lesions from fundus images is an essential prerequisite for accurate severity assessment of diabetic retinopathy. Due to variation in morphologies, number and size of lesions, the manual grading process becomes extremely challenging and time-consuming. This necessitates the need of an automatic segmentation system that can precisely define the region of interest boundaries and assist ophthalmologists in speedy diagnosis along with diabetic retinopathy severity grading. The paper presents a modified U-Net architecture based on residual network and employs periodic shuffling with sub-pixel convolution initialized to convolution nearest neighbour resize. The proposed architecture has been trained and validated for microaneurysm and hard exudate segmentation on two publicly available datasets namely IDRiD and e-ophtha. For IDRiD dataset, the network obtains 99.88% accuracy, 99.85% sensitivity, 99.95% specificity and dice score of 0.9998 for both microaneurysm and exudate segmentation. Further, when trained on e-ophtha and validated on IDRiD dataset, the network shows 99.98% accuracy, 99.88% sensitivity, 99.89% specificity and dice score of 0.9998 for microaneurysm segmentation. For exudates segmen-tation, the model obtained 99.98% accuracy, 99.88% sensitivity, 99.89% specificity and dice score of 0.9999, when trained on e-ophtha and validated on IDRiD dataset. In comparison to existing literature, the proposed model provides state-of-the-art results for retinal lesion segmentation.

4

Enhanced CAE system for detection of exudates and diagnosis of diabetic retinopathy stages in fundus retinal images using soft computing techniques

Janaki Sathya D., Geetha K.

Polish Journal of Medical Physics and Engineering

|

2019

|

Vol. 25, Iss. 2

131--139

EN

Diabetic Retinopathy (DR) is one of the leading causes of visual impairment. Diabetic Retinopathy is the most recent technique of identifying the intensity of acid secretion in the eye for diabetic patients. The identification of DR is performed by visual analysis of retinal images for exudates (fat deposits) and the main patterns are traced by ophthalmologists. This paper proposes a fully automated Computer Assisted Evaluation (CAE) system which comprises of a set of algorithms for exudates detection and to classify the different stages of Diabetics Retinopathy, which are identified as either normal or mild or moderate or severe. Experimental validation is performed on a real fundus retinal image database. The segmentation of exudates is achieved using fuzzy C-means clustering and entropy filtering. An optimal set obtained from the statistical textural features (GLCM and GLHM) is extracted from the segmented exudates for classifying the different stages of Diabetics Retinopathy. The different stages of Diabetic Retinopathy are classified using three classifiers such as Back Propagation Neural Network (BPN), Probabilistic Neural Network (PNN) and Support Vector Machine (SVM). The experimental results show that the SVM classifiers outperformed other classifiers for the examined fundus retinal image dataset. The results obtained confirm that with new a set of texture features, the proposed methodology provides better performance when compared to the other methods available in the literature. These results suggest that our proposed method in this paper can be useful as a diagnostic aid system for Diabetic Retinopathy.

5

Robust intensity variation and inverse surface adaptive thresholding techniques for detection of optic disc and exudates in retinal fundus images

Karkuzhali S., Manimegalai D.

Biocybernetics and Biomedical Engineering

|

2019

|

Vol. 39, no. 3

753--764

EN

Diabetic Retinopathy (DR) is an adverse change in retinal blood vessels leads to blindness for diabetic patients without any symptoms. Diabetes is characterized by imbalance level of glucose in the human body. The optic disc (OD) is the major retinal landmark. Localization of OD is an important step in fundus image analysis and to develop Computer Aided Diagnosis tool for DR. OD center detection is necessary to reduce false positive rate in the detection of exudates (EXs). EXs is the white lesion present in the retina which is the early symptom for the diagnosis of DR. OD is detected using intensity variation algorithm and EXs is segmented using inverse surface adaptive thresholding algorithm. This algorithm achieves better result in localizing OD and segmenting EXs when compared to literature-reviewed methods. The maximum intensity variance method is used to locate OD with average ACC of 96.54%, 98.65%, 98.12%, 99.23%, 99.81% and 98.47% in DIARETDB0, DIARETDB1, MESSIDOR, DRIVE, STARE and Bejan Singh Eye Hospital databases with less computation time of 102 ms, 108 ms, 120 ms, 93 ms, 110 ms and 131 ms. The inverse surface adaptive thresholding method has achieved an SE of 97.43%, 98.87%, 99.12%, 97.21%, 98.72%, and 96.63%, a SPE of 91.56%, 92.31%, 90.21%, 90.14%, 89.58%, 92.56% and an ACC of 99.34%, 99.67%, 98.34%, 98.87%, 99.13%, 98.34% for DIARETDB0, DIARETDB1, MESSIDOR, DRIVE, STARE and Bejan Singh Eye Hospital databases respectively.

6

Diagnozowanie stanu retinopatii cukrzycowej przy pomocy głębokich sieci neuronowych

Jarzembiński B., Kwasigroch A., Grochowski M.

Zeszyty Naukowe Wydziału Elektrotechniki i Automatyki Politechniki Gdańskiej

|

2018

|

Nr 60

37--40

PL

W referacie opisano problem wykrywania oraz klasyfikacji stanu retinopatii cukrzycowej ze zdjęć dna oka przy pomocy głębokich sieci neuronowych. Retinopatia cukrzycowa jest chorobą oczu często występującą u osób z cukrzycą. Nieleczona prowadzi do uszkodzenia wzroku, a nawet ślepoty. W pracy badawczej opracowano system wykrywania retinopatii cukrzycowej na podstawie zdjęć dna oka. Opracowana sieć neuronowa przypisuje stan choroby w 5 stopniowej skali – od braku choroby do najbardziej zaawansowanego stanu choroby. Zaproponowano specjalny system kodowania klas w celu uchwycenia wielkości różnicy pomiędzy rzeczywistymi a predykowanymi stanami choroby. Uzyskano wysokie wyniki klasyfikacji na zbiorze testowym. W celu oceny skuteczności działania systemu wykorzystano miary statystyczne takie jak ważona Kappa i dokładność.

EN

In the paper we described computer aided detection system of diabetic retinopathy based on fundus photos of retina. Diabetic retinopathy is an eye disease associated with diabetes. Non-treated diabetic retinopathy leads to sight degeneration and even blindness. Early detection is crucial due to provide effective treatment. Currently, diabetic retinopathy detection is time consuming process, done manualy by medical specialist. The disease is dangerous issue in places where the availability of phisicians is limited. We employed the computer system that detect diabetic retinopathy and assess a stage of the disease based on retinal photo of fundus. We used one of the best image classification system – deep neural networks. Employed system assess the stage of the disease in 5 level scale – from absence of disease to the most severe stage of disease. We employed transfer learning and data augmentation to enhance classification result. Moreover we proposed special class coding system to catch the difference between real and predicted stage of disease. We tested employed system using different statistical measures like accuracy, sensitivity, specificity and Kappa score.

7

A generalized method for the segmentation of exudates from pathological retinal fundus images

Kaur J., Mittal D.

Biocybernetics and Biomedical Engineering

|

2018

|

Vol. 38, no. 1

27--53

EN

Diabetic retinopathy, an asymptomatic complication of diabetes, is one of the leading causes of blindness in the world. The exudates, abnormal leaked fatty deposits on retina, are one of the most prevalent and earliest clinical signs of diabetic retinopathy. In this paper, a generalized exudates segmentation method to assist ophthalmologists for timely treatment and effective planning in the diagnosis of diabetic retinopathy is developed. The main contribution of the proposed method is the reliable segmentation of exudates using dynamic decision thresholding irrespective of associated heterogeneity, bright and faint edges. The method is robust in the sense that it selects the threshold value dynamically irrespective of the large variations in retinal fundus images from varying databases. Since no performance comparison of state of the art methods is available on common database, therefore, to make a fair comparison of the proposed method, this work has been performed on a diversified database having 1307 retinal fundus images of varying characteristics namely: location, shapes, color and sizes. The database comprises of 649 clinically acquired retinal fundus images from eye hospital and 658 retinal images from publicly available databases such as STARE, MESSIDOR, DIARETDB1 and e-Optha EX. The segmentation results are validated by performing two sets of experiments namely: lesion based evaluation criteria and image based evaluation criteria. Experimental results at lesion level show that the proposed method outperforms other existing methods with a mean sensitivity/specificity/accuracy of 88.85/96.15/93.46 on a composite database of retinal fundus images. The segmentation results for image-based evaluation with a mean sensitivity/specificity/accuracy of 94.62/ 98.64/96.74 respectively prove the clinical effectiveness of the method. Furthermore, the significant collective performance of these experiments on clinically as well as publicly available standard databases proves the generalization ability and the strong candidature of the proposed method in the real-time diagnosis of diabetic retinopathy.

8

An intelligible deep convolution neural network based approach for classification of diabetic retinopathy

Sharma S., Maheshwari S., Shukla A.

Bio-Algorithms and Med-Systems

|

2018

|

Vol. 14, no. 2

art. no. 20180011

EN

Deep convolution neural networks (CNNs) have demonstrated their capabilities in modern-day medical image classification and analysis. The vital edge of deep CNN over other techniques is their ability to train without expert knowledge. Time bound detection is very beneficial for the early cure of disease. In this paper, a deep CNN architecture is proposed to classify nondiabetic retinopathy and diabetic retinopathy fundus eye images. Kaggle 2015 diabetic retinopathy competition dataset and messier experiment dataset are used in this study. The proposed deep CNN algorithm produces significant results with 93% area under the curve (AUC) for the Kaggle dataset and 91% AUC for the Messidor dataset. The sensitivity and specificity for the Kaggle dataset are 90.22% and 85.13%, respectively; the corresponding values of the Messidor dataset are 91.07% and 80.23%, respectively. The results outperformed many existing studies. The present architecture is a promising tool for diabetic retinopathy image classification.

9

Robust and accurate optic disk localization using vessel symmetry line measure in fundus images

Panda R., Puhan N. B., Panda G.

Biocybernetics and Biomedical Engineering

|

2017

|

Vol. 37, no. 3

466--476

EN

Accurate optic disk (OD) localization is an important step in fundus image based computer-aided diagnosis of glaucoma and diabetic retinopathy. Robust OD localization becomes more challenging with the presence of common pathological variations which could alter its overall appearance. This paper presents a novel OD localization method by incorporating salient visual cues of retinal vasculature: (1) global vessel symmetry, (2) vessel component count and (3) local vessel symmetry inside OD region. In the proposed method, a new vessel symmetry line (VSL) measure is designed to demarcate the lines that divide the retinal vasculature into approximately similar halves. The initial OD center location is computed using the highest number of major blood vessel components in the skeleton image. The final OD center localization involves an iterative center of mass computation to exploit the local vessel symmetry in the OD region of interest. The proposed method shows effectiveness in diseased retinas having diverse symptoms like bright lesions, hemorrhages, and tortuous vessels that create potential ambiguity for OD localization. A total of ten publicly available retinal image databases are considered for extensive evaluation of the proposed method. The experimental results demonstrate high average OD detection accuracy of 99.49%, while achieving state-of-the-art OD localization error in all databases.

10

New Binary Hausdorff Symmetry measure based seeded region growing for retinal vessel segmentation

Panda R., Puhan N. B., Panda G.

Biocybernetics and Biomedical Engineering

|

2016

|

Vol. 36, no. 1

119--129

EN

Automated retinal vessel segmentation plays an important role in computer-aided diagnosis of serious diseases such as glaucoma and diabetic retinopathy. This paper contributes, (1) new Binary Hausdorff Symmetry (BHS) measure based automatic seed selection, and (2) new edge distance seeded region growing (EDSRG) algorithm for retinal vessel segmentation. The proposed BHS measure directly provides a binary symmetry decision at each pixel without the computation of continuous symmetry map and image thresholding. In a multiscale mask, the BHS measure is computed using the distance sets of opposite direction angle bins with sub-pixel resolution. The computation of the BHS measure from the Hausdorff distance sets involves point set matching based geometrical interpretation of symmetry. Then, we design a new edge distance seeded region growing (EDSRG) algorithm with the acquired seeds. The performance evaluation in terms of sensitivity, specificity and accuracy is done on the publicly available DRIVE, STARE and HRF databases. The proposed method is found to achieve state-of-the-art vessel segmentation accuracy in three retinal databases; DRIVE- sensitivity (0.7337), specificity (0.9752), accuracy (0.9539); STARE-sensitivity (0.8403), specificity (0.9547), accuracy (0.9424); and HRF-sensitivity (0.8159), specificity (0.9525), accuracy (0.9420).

11

Computerized screening of diabetic retinopathy employing blood vessel segmentation in retinal images

Franklin S. W., Rajan S. E.

Biocybernetics and Biomedical Engineering

|

2014

|

Vol. 34, no. 2

117--124

EN

Diabetic retinopathy is a severe sight threatening disease which causes blindness among working age people. This research work presents a retinal vessel segmentation technique, which can be used in computer based retinal image analysis. This proposed method could be used as a prescreening system for the early detection of diabetic retinopathy. The algorithm implemented in this work can be effectively used for detection and analysis of vascular structures in retinal images. The retinal blood vessel morphology helps to classify the severity and identify the successive stages of a number of diseases. The changes in retinal vessel diameter are one of the symptoms for diseases based on vascular pathology. The size of typical retinal vessel is a few pixels wide and it becomes critical and challenging to obtain precise measurements using computer based automatic analysis of retinal images. This method classifies each image pixel as vessel or non-vessel and thereby produces the segmentation of vasculature in retinal images. Retinal blood vessels are identified and segmented by making use of a multilayer perceptron neural network, for which the inputs are derived from three primary colour components of the image, i.e., red, green and blue. Back propagation algorithm which provides a proficient technique to change the weights in a feed-forward network is employed. The performance of this method was evaluated and tested using the retinal images from the DRIVE database and has obtained illustrative results. The measured accuracy of the proposed system was 95.03% for the segmentation algorithm tested on this database.

12

Zaburzenia widzenia u osób chorych na cukrzycę typu I: zmiany wrażliwości siatkówki na bodziec świetlny u chorych na cukrzycę typu I – szczegółowa analiza danych perymetrycznych

Brenk J., Szuba R., Schlaffke J., Wierusz-Wysocka B., Tomczak P.

Optyka

|

2013

|

Nr 1

42--46

PL

Zaburzenia w układzie wzrokowym chorych na cukrzycę typu I są wywołane przez nieprawidłowe wartości glikemii oraz zakłóconą gospodarkę metaboliczną. Odchylenia w stężeniach glukozy we krwi są przyczyną zmian refrakcji oka. Mogą też wpływać na sensoryczne funkcje układu wzrokowego (widzenie barwne, poczucie kontrastu, pole widzenia). Ponadto niewyrównana glikemia skutkuje późnymi powikłaniami, np. retinopatią cukrzycową. Jednym z celów specjalistów zajmujących się ochroną zdrowia narządu wzroku u chorych na cukrzycę jest doskonalenie metod wczesnej diagnozy zmian cukrzycowych. Progowa perymetria statyczna jest użyteczną metodą badania wrażliwości siatkówki na bodziec świetlny. Pozwala ona określić granicę rozpoznawalności punktu świetlnego o danej luminancji w określonych kierunkach pola widzenia. Ponadto założyć można, iż badania te, powtórzone po określonym czasie, mogą informować o stabilności odbioru bodźców przez układ wzrokowy.

EN

Dysfunctions in the visual system of patients with type 1 diabetes mellitus (DM 1) are caused by abnormal levels of blood glucose and abnormal metabolic economy. Fluctuations in the blood glucose level cause changes in the refraction error of the eye. It may also affect the sensory function of the visual system (color vision, contrast sensitivity, visual field). In addition, instability in blood glucose levels cause further consequences, such as diabetic retinopathy. One of the main aims of eye healthcare professionals who work with diabetics is to improve early diagnostic methods of diabetic changes. Static threshold perimetry is a useful method for testing of the retina sensitivity to the light stimuli. These measurements allow for determining the lowest luminance which the patients are able to reach as a threshold value in certain directions of the visual field. In addition, threshold perimetry repeated in a given time can indicate the stability of the reception of stimuli by the visual system.

13

Preventive systems for the late complications of diabetes

Ładyżyński P., Wójcicki J. M., Foltyński P.

Biocybernetics and Biomedical Engineering

|

2011

|

Vol. 31, no. 2

3-21

EN

Aim of this work is to review and characterize methods and systems that are used to prevent onset and to slow down the progression of the late complications of diabetes. Two groups of methods and systems that might be used to prevent or to slow down the progression of the late complications of diabetes are characterized in this paper. Each of these two groups serves a different purpose. The first group is composed of the systems that facilitate a maintenance of strict metabolic control in diabetic patients, i.e. the systems which are used for monitoring and treatment of diabetes. The second group contains systems that are aimed at screening/monitoring or treatment of the risk factors or the early signs of the late complications. Obesity increases risk of diabetes and its complications. Thus, body mass monitoring and control systems are examples of the tools that belong to this group. Other examples include the diabetic retinopathy telescreening systems and the systems for monitoring of the diabetic foot syndrome.

14

Automated vessel segmentation of 35mm colour non-mydriatic images in a community health screening project

Jelinek H. F.

Machine Graphics and Vision

|

2008

|

Vol. 17, No. 1/2

57-68

EN

Proliferative diabetic retinopathy is a complication of diabetes that can eventually lead to blindness. Early identification of this complication reduces the risk of blindness so that timely treatment can be initiated. In rural and remote regions, widespread population screening is practically impossible due to the lack of ophthalmologists and the cost associated with rural visits by specialists. Several methods for vessel segmentation have been discussed in the literature, but none have used non-mydriatic colour images obtained from community screening initiatives. Rural screening clinics currently use either 35mm or Polaroid photography. In addition, the quality of the images is often much lower. Scanning images at 300dpi provides very low resolution images which combined with the low quality requires a robust algorithm to identify vessels with high accuracy. Visual inspection by an ophthalmologist judged 46 images (88%) to represent an acceptable level of segmentation. Despite the low resolution and quality of images, the Gabor wavelet provided vessel segmentation results that were usable in rural community screening projects and in some cases identified vessels obscured by haemorrhages better than the expert observer.

15

Application of telemedicine technique in screening for diabetic retinopathy

Ładyżyński P., Wójcicki J. M., Chihara K.

Biocybernetics and Biomedical Engineering

|

2007

|

Vol. 27, no. 1-2

253-263

EN

Diabetic retinopathy is one of the most serious long-term microvascular complications of diabetes. It is a sight-threatening, chronic ocular disorder, which is currently the most common cause of blindness in people of working age in western societies. Slit lamp biomicroscopy and seven-field stereoscopic 30o fundus photography (with dilated pupil) represent the current gold standard techniques for detecting diabetic retinopathy. These methods are too expensive for widespread use in the screening process, even in the most developed countries. At present, retinopathy is usually detected by the direct ophthalmoscopic examination. Simple wide angle color fundus photography is another much more accurate and widely used method. The introduction of digital imaging cameras made the application of the telemedicine technique possible. First feasibility studies concerning application of the telemedicine technique in screening for diabetic retinopathy were reported in the late 1990s. These early systems used mobile fundus cameras or e-mail messages for transmission of digital fundus photographs between distant locations in a store–and–forward mode. Then, more advanced systems followed, which either based on proprietary software solutions or on the latest advances of the internet technology. One of such systems has been developed in co-operation between NAIST and IBBE PAS. The developed DRWeb system consists of the image acquisition station, the database and communication server and the image grading station. Two modes of operation are possible: telediagnosis – when all the mentioned above stages are conducted independently, one after another and teleconsultation – when real time interaction between the physician and the expert is possible. The system is supplemented by an algorithm ensuring that the quality of the transmitted digital images is good enough for a successful making of the diagnosis.

16

Automatic detection of exudates from fundus eye images based on mathematical morphology for diabetic retinopathy monitoring

Stąpor K., Świtoński A.

Studia Informatica

|

2005

|

Vol. 26, nr 1

5-14

EN

In this paper the method for automatic segmentation of exudates from fundus eye images is proposed. The method is composed of the following steps: 1) preprocessing, 2) finding marker image and 3) geodesic reconstraction. The mean sensitivity is 95%.

PL

W artykule przedstawiono metodę segmentacji wysięków na cyfrowych obrazach dna oka. Metoda składa się z następujących kroków: 1) przetwarzanie wstępne, 2) znajdowanie obrazu znaczników, 3) rekonstrukcja geodezyjna. Średnia czułość metody wynosi 95%.

17

Automatic detection of early symptoms of diabetic retinopathy from fundus eye images using mathematical morphology

Stąpor K., Świtoński A.

Studia Informatica

|

2004

|

Vol. 25, nr 3

29-39

EN

In this paper the new method for automatic segmentation of microaneurysms from fundus eye images is proposed. It relies on methods from mathematical grayscale morphology. The new HitAndMiss transformation has been defined forthe detection of markers of watershed transformation.

PL

W artykule przedstawiono nową metodę automatycznej segmentacji mikroaneuryzmatów na cyfrowych obrazach dna oka. Zaproponowana metoda F wykorzystuje narzędzia wieloodcieniowej morfologii matematycznej. Zdefiniowano |: nowe przekształcenie trafi-nie-trafi dla detekcji markerów transformaty wododziało-i wej.

18

Segmentation of fundus eye images : detection of microaneurysms and blood vessels using mathematical morphology

Stąpor K., Świtoński A.

Archiwum Informatyki Teoretycznej i Stosowanej

|

2004

|

T. 16, z. 2

77-92

EN

In this paper the new method for automatic segmentation of fundus eye images are proposed: one for the detection of microaneurysms, the second for the detection of blood vessels. Both rely on tools from mathematical, grayscale morphology. The proposed method can be integrated in a tool for diagnosis of diabetic retinopathy which is under development.

PL

W artykule przedstawiono nowe metody automatycznej segmentacji obrazów dna oka pozyskanych z funduskamery: jedna dla detekcji mikroaneurazymów, druga dla naczyń krwionośnych na siatkówce oka. Metoda detekcji mikroaneurazymów składa się z następujących kroków: 1) przetwarzanie wstępne, 2) detekcja markerów dla transformaty wodnej, 3) transformata wodna, 4) klasyfikacja. W celu automatycznej detekcji markerów wewnętrznych dla transformaty wodnej zdefiniowano nowe przekształcenie trafi-nie-trafi w morfologii wieloodcieniowej. Uzyskana średnia sprawność metody wynosi 89,4% i jest wyższa od wyników uzyskanych w metodach poprzednich (84%). Metoda detekcji naczyń krwionośnych składa się z następujących kroków: 1) lokalna poprawa kontrastu, 2) odszumianie, 3) detekcja naczyń, 4)klasyfikacja. W celu odszumienia zastosowano operacje złożone ze specjalnie zaprojektowanych operacji dylatacji i erozji wieloodcieniowej. Sama detekcja naczyń wykorzystuje operację czubek-kapelusza. Opracowane algorytmy detekcji stanowić będą podstawowe moduły systemu komputerowego wspomagającego diagnozowanie jak również monitorowanie tej retinopatii cukrzycowej.