Cemal Köse

Automatic segmentation of age-related macular degeneration in retinal fundus images

Every year an increasing number of people are affected by age-related macular degeneration (ARMD). Consequently, vast amount of information is accumulated in medical databases and manual classification of this information is becoming more and more difficult. Therefore, there is an increasing interest in developing automated evaluation methods to follow up the diseases. In this paper, we have presented an automatic method for segmenting the ARMD in retinal fundus images. Previously used direct segmentation techniques, generating unsatisfactory results in some cases, are more complex and costly than our inverse method. This is because of the fact that the texture of unhealthy areas of macula is quite irregular and varies from eye to eye. Therefore, a simple inverse segmentation method is proposed to exploit the homogeneity of healthy areas of the macula rather than unhealthy areas. This method first extracts healthy areas of the macula by employing a simple region growing method. Then, blood vessels are also extracted and classified as healthy regions. In order to produce the final segmented image, the inverse image of the segmented image is generated as unhealthy region of the macula. The performance of the method is examined on various qualities of retinal fundus images. The segmentation method without any user involvement provides over 90% segmentation accuracy. Segmented images with reference invariants are also compared with consecutive images of the same patient to follow up the changes in the disease.

Simple methods for segmentation and measurement of diabetic retinopathy lesions in retinal fundus images

Diabetic retinopathy (DR) is one of the most important complications of diabetes mellitus, which causes serious damages in the retina, consequently visual loss and sometimes blindness if necessary medical treatment is not applied on time. One of the difficulties in this illness is that the patient with diabetes mellitus requires a continuous screening for early detection. So far, numerous methods have been proposed by researchers to automate the detection process of DR in retinal fundus images. In this paper, we developed an alternative simple approach to detect DR. This method was built on the inverse segmentation method, which we suggested before to detect Age Related Macular Degeneration (ARMDs). Background image approach along with inverse segmentation is employed to measure and follow up the degenerations in retinal fundus images. Direct segmentation techniques generate unsatisfactory results in some cases. This is because of the fact that the texture of unhealthy areas such as DR is not homogenous. The inverse method is proposed to exploit the homogeneity of healthy areas rather than dealing with varying structure of unhealthy areas for segmenting bright lesions (hard exudates and cotton wool spots). On the other hand, the background image, dividing the retinal image into high and low intensity areas, is exploited in segmentation of hard exudates and cotton wool spots, and microaneurysms (MAs) and hemorrhages (HEMs), separately. Therefore, a complete segmentation system is developed for segmenting DR, including hard exudates, cotton wool spots, MAs, and HEMs. This application is able to measure total changes across the whole retinal image. Hence, retinal images that belong to the same patients are examined in order to monitor the trend of the illness. To make a comparison with other methods, a Naïve Bayes method is applied for segmentation of DR. The performance of the system, tested on different data sets including various qualities of retinal fundus images, is over 95% in detection of the optic disc (OD), and 90% in segmentation of the DR.

A personal identification system using retinal vasculature in retinal fundus images

Abstract The characteristics of human body such as fingerprint, face, hand palm and iris are measured, recorded and identified by performing comparison using biometric devices. Even though it has not seen widespread acceptance yet, retinal identification based on retinal vasculatures in retina provides the most secure and accurate authentication means among biometric systems. Using retinal images taken from individuals, retinal identification is employed in environments such as nuclear research centers and facilities, weapon factories, where extremely high security measures are needed. The superiority of this method stems from the fact that retina is unique to every human being and it would not be changed during human life. Adversely, other identification approaches such as fingerprint, face, palm and iris recognition, are all vulnerable in that those characteristics can be corrupted via plastic surgeries and other changes. In this study we propose an alternate personal identification system based on retinal vascular network in retinal images, which tolerates scale, rotation and translation in comparison. In order to accurately identify a person our new approach first segments vessel structure and then employ similarity measurement along with the tolerations. The developed system, tested on about four hundred images, presents over 95% of success which is quite promising.

A Statistical Segmentation Method for Measuring Age-Related Macular Degeneration in Retinal Fundus Images

Day by day, huge amount of information is collected in medical databases. These databases include quite interesting information that could be exploited in diagnosis of illnesses and medical treatment of patients. Classification of these data is getting harder as the databases are expanded. On the other hand, automated image analysis and processing is one of the most promising areas of computer vision used in medical diagnosis and treatment. In this context, retinal fundus images, offering very high resolutions that are sufficient for most of the clinical cases, provide many indications that could be exploited in diagnosing and screening retinal degenerations or diseases. Consequently, there is a strong demand in developing automated evaluation systems to utilize the information stored in the medical databases. This study proposes an automatic method for segmentation of ARMD in retinal fundus images. The method used in the automated system extracts lesions of the ARMD by employing a statistical method. In order to do this, the statistical segmentation method is first used to extract the healthy area of the macula that is more familiar and regular than the unhealthy parts. Here, characteristic images of the patterns of the macula are extracted and used to segment the healthy textures of an eye. In addition to this, blood vessels are also extracted and then classified as healthy regions. Finally, the inverse image of the segmented image is generated which determines the unhealthy regions of the macula. The performance of the method is examined on various quality retinal fundus images. Segmented images are also compared with consecutive images of the same patient to follow up the changes in the disease.

An automatic diagnosis method for the knee meniscus tears in MR images

Everyday vast amount of information accumulated in medical databases. These databases include quite useful information that could be exploited to improve diagnosis of illnesses and their treatments. However, classification of this information is becoming more and more difficult. In this paper, an automatic method to diagnose the knee meniscus tears from MR medical images is presented. This proposed system uses histogram based method with edge detection filtering and statistical segmentation based methods to locate meniscus at knee joint. A template matching technique is also employed to extract the meniscus. Finally, the meniscus area is analyzed to detect the meniscus tears automatically. Accurate segmentation of the statistical pattern requires a technique that eliminates background effects. Hence, the density distributions of the statistical patterns on images with varying background are corrected. Here, the statistical segmentation method also extracts a representing image of the statistical patterns such as bone and uses the image to enhance the segmentation. Performance of this method is examined on MR images in varying qualities. The results show that our method is quite successful in segmentation of knee bones and diagnosis of the meniscus tears. This system has achieved accuracy about 93% in the diagnosis of meniscus tears on MR images.

Chat mining: Automatically determination of chat conversations' topic in Turkish text based chat mediums

Mostly, the conversations taking place in chat mediums bear important information concerning the speakers. This information can vary in many fields such as tendencies, habits, attitudes, guilt situations, and intentions of the speakers. Therefore, analysis and processing of these conversations are of much importance. Many social and semantic inferences can be made from these conversations. In determining characteristics of conversations and analysis of conversations, subject designation can be grounded on. In this study, chat mining is chosen as an application of text mining, and a study concerning determination of subject in the Turkish text based chat conversations is conducted. In sorting the conversations, supervised learning methods are used in this study. As for classifiers, Naive Bayes, k-Nearest Neighbor and Support Vector Machine are used. Ninety-one percent success is achieved in determination of subject.

A surface-based method for detection of coronary vessel boundaries in poor quality X-ray angiogram images

In this paper, we propose a surface-based method for simultaneous detection of left and right coronary borders that is suitable for analysis of poor quality X-ray angiogram images. Coronary artery is modelled with a 3D generalized cylinder (GC) with elliptic cross-sections. Based on this model, we developed a 2D surface function for the projection intensity distribution of a vessel part. The parameters associated with vessel edges are estimated from this model. The model takes into account local background intensity, noise and blurring. In simulation and real experiments over a range of imaging conditions, the proposed method consistently produced lower estimation error and variability in detecting edges than our previously reported 1D profile-based method. The improvement is most significant especially for noisy and low-contrast angiograms.

Identification of suitable fundus images using automated quality assessment methods

Abstract. Retinal image quality assessment (IQA) is a crucial process for automated retinal image analysis systems to obtain an accurate and successful diagnosis of retinal diseases. Consequently, the first step in a good retinal image analysis system is measuring the quality of the input image. We present an approach for finding medically suitable retinal images for retinal diagnosis. We used a three-class grading system that consists of good, bad, and outlier classes. We created a retinal image quality dataset with a total of 216 consecutive images called the Diabetic Retinopathy Image Database. We identified the suitable images within the good images for automatic retinal image analysis systems using a novel method. Subsequently, we evaluated our retinal image suitability approach using the Digital Retinal Images for Vessel Extraction and Standard Diabetic Retinopathy Database Calibration level 1 public datasets. The results were measured through the F1 metric, which is a harmonic mean of precision and recall metrics. The highest F1 scores of the IQA tests were 99.60%, 96.50%, and 85.00% for good, bad, and outlier classes, respectively. Additionally, the accuracy of our suitable image detection approach was 98.08%. Our approach can be integrated into any automatic retinal analysis system with sufficient performance scores.

Fully automatic segmentation of coronary vessel structures in poor quality x-ray angiogram images

In this paper a fully automatic method is presented for extracting blood vessel structures in poor quality coronary angiograms. The method extracts blood vessels by exploiting the spatial coherence in the image. Accurate sampling of a blood vessel requires a background elimination technique. A circular sampling technique is employed to exploit the coherence. This circular sampling technique is also applied to determine the distribution of intersection lengths between the circles and blood vessels at various threshold depths. After this sampling process, disconnected parts to the centered object are eliminated, and then the distribution of the intersection length is examined to make the decision about whether the point is on the blood vessel. To produce the final segmented image, mis-segmented noisy parts and discontinuous parts are eliminated by using angle couples and circular filtering techniques. The performance of the method is examined on various poor quality X-ray angiogram images.

Profiling for efficient parallel volume visualisation

Visualising a multi-dimensional volume data set is a computationally intensive process. Parallel processing offers the potential for achieving the visualisation in a reasonable time. This paper discusses how an appropriate data management approach and the correct management of tasks in the parallel implementation can improve overall system performance. A number of profiling and load balancing strategies are considered to exploit any coherence that may exist as the view point moves.