Early detection of microaneurysms (MAs), the first sign of Diabetic Retinopathy (DR), is an essential first step in automated detection of DR to prevent vision loss and blindness. This study presents a novel and different algorithm for automatic detection of MAs in fluorescein angiography (FA) fundus images, based on Radon transform (RT) and multi-overlapping windows. This project addresses a novel method, in detection of retinal land marks and lesions to diagnose the DR. At the first step, optic nerve head (ONH) was detected and masked. In preprocessing stage, top-hat transformation and averaging filter were applied to remove the background. In main processing section, firstly, we divided the whole preprocessed image into sub-images and then segmented and masked the vascular tree by applying RT in each sub-image. After detecting and masking retinal vessels and ONH, MAs were detected and numbered by using RT and appropriated thresholding. The results of the proposed method were evaluated reported on three different retinal images databases, the Mashhad Database with 120 FA fundus images, Second Local Database from Tehran with 50 FA retinal images and a part of Retinopathy Online Challenge (ROC) database with 22images. Automated DR detection demonstrated a sensitivity and specificity of 94% and 75% for Mashhad database and 100% and 70% for the Second Local Database respectively.

Ab stract-In medical images linear patterns such as blood vessels are important structures for computer-aided diagnosis and follow-up of many diseases. Moreover, image processing techniques are required to extract suitable information about vascular tree and its alteration. Analyzing of retinal blood vessel is critical work for the investigation of some diseases. In this study, we present an automated method for detecting retinal vasculatures based upon Radon transform. In preprocessing, we used top-hat transformation and averaging filter. Our main processing was included applying Radon transform, vessel certifying, and vessel refinement. Comparing the results of our method with gold standard showed that our results have more than 93% for true positive rate. In conclusion, it is possible to use Radon transform for vessel segmentation in fluorescein angiography fundus images, with acceptable sensitivity and specificity, as a necessary step in some diagnostic algorithm for retinal pathology.

The identification of the optic nerve head (ONH) is necessary preprocessing step in retinal image analysis, for automated extraction of the anatomical components in retinal images. In this study, a new image processing method based on Radon transform (RT) and multi-overlapping windows was proposed for ONH detection in fluorescein angiography (FA) fundus images. At first, RT was applied to all fundus sub images to find candidates for the location of the ONH. Then, the accurate location was found using the minimum mean square error estimation. The results of our automated method for the ONH detection in the images showed sensitivity and specificity of 90.54%, 98.51% respectively for pixel based analysis, and according to manual ONH detection, our automated algorithm found 89 ONH out of 100 in true location for FA images. This study addresses a novel method in detection of retinal land marks. Sensitivity and specificity of this algorithm seems to be acceptable in comparison with other detection methods.

No abstract

Background:The aim of the present study was to evaluate how left ventricular twist and torsion are associated with sex between sex groups of the same age. Materials and Methods: In this analytical study, twenty one healthy subjects were scanned in left ventricle basal and apical short axis views to run the block matching algorithm; instantaneous changes in the base and apex rotation angels were estimated by this algorithm and then instantaneous changes of the twist and torsion were calculated over the cardiac cycle. Results:The rotation amount between the consecutive frames in basal and apical levels was extracted from short axis views by tracking the speckle pattern of images. The maximum basal rotation angle for men and women were -6.94°±1.84 and 9.85°±2.36 degrees (p-value = 0.054), respectively. Apex maximum rotation for men was -8.89°±2.04 and for women was 12.18°±2.33 (p-value < 0.05). The peak of twist angle for men and women was 16.78 ± 1.83 and 20.95± 2.09 degrees (p-value < 0.05), respectively. In men and women groups, the peak of calculated torsion angle was 5.49°±1.04 and 7.12± 1.38 degrees (p-value < 0.05), respectively. Conclusion:The conclusion is that although torsion is an efficient parameter for left ventricle function assessment, because it can take in account the heart diameter and length, statistic evaluation of the results shows that among men and women LV mechanical parameters are significantly different. This study was mainly ascribed to the dependency of the torsion and twist on patient sex.