Improvement of automatic hemorrhages detection methods using brightness correction on fundus images - art. no. 69153E

Dept. of Ophthalmology, School of Medicine, Gifu University, 501-1194, Gifu, Japan
Proceedings of SPIE - The International Society for Optical Engineering (Impact Factor: 0.2). 04/2008; 81:58-320. DOI: 10.1117/12.771051


We have been developing several automated methods for detecting abnormalities in fundus images. The purpose of this study is to improve our automated hemorrhage detection method to help diagnose diabetic retinopathy. We propose a new method for preprocessing and false positive elimination in the present study. The brightness of the fundus image was changed by the nonlinear curve with brightness values of the hue saturation value (HSV) space. In order to emphasize brown regions, gamma correction was performed on each red, green, and blue-bit image. Subsequently, the histograms of each red, blue, and blue-bit image were extended. After that, the hemorrhage candidates were detected. The brown regions indicated hemorrhages and blood vessels and their candidates were detected using density analysis. We removed the large candidates such as blood vessels. Finally, false positives were removed by using a 45-feature analysis. To evaluate the new method for the detection of hemorrhages, we examined 125 fundus images, including 35 images with hemorrhages and 90 normal images. The sensitivity and specificity for the detection of abnormal cases was were 80% and 88%, respectively. These results indicate that the new method may effectively improve the performance of our computer-aided diagnosis system for hemorrhages.

Download full-text


Available from: Hiroshi Fujita
    • "Automated microaneurysm detection method based on double-ring Filter was achieved by the authors in [9]. In [10], a method to detect the hemorrhages using hue saturation value (HSV) space was proposed. Automated fundus photograph analysis algorithms for the detection of primary lesions and a computer-assisted diagnostic system for grading diabetic retinopathy (DR) and the risk of macular edema (ME) are introduced [11]. "
    Dataset: 4- GVIP

    No preview · Dataset · Sep 2013
  • Source
    • "Large hemorrhages indicate more severe disease, and improved detection of such lesions will lead to elimination of more severe false negatives. Small hemorrhages are regular in shape and many systems have been developed by us and others to detect them [4]–[6]. A review of most recent work on hemorrhage detection can be found in [7]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: A novel splat feature classification method is presented with application to retinal hemorrhage detection in fundus images. Reliable detection of retinal hemorrhages is important in the development of automated screening systems which can be translated into practice. Under our supervised approach, retinal color images are partitioned into non-overlapping segments covering the entire image. Each segment, i.e. splat, contains pixels with similar color and spatial location. A set of features is extracted from each splat to describe its characteristics relative to its surroundings, employing responses from a variety of filter bank, interactions with neighboring splats, and shape and texture information. An optimal subset of splat features is selected by a filter approach followed by a wrapper approach. A classifier is trained with splat-based expert annotations and evaluated on the publicly available Messidor dataset. An area under the ROC curve of 0.96 is achieved at the splat level and 0.87 at the image level. While we are focused on retinal hemorrhage detection, our approach has potential to be applied to other object detection tasks.
    Full-text · Article · Nov 2012
  • Source
    • "The differences in brightness and retinal fundus images were due to th conditions. In order to reduce the brightness correction [9], gamma histogram expansion were applied to e contrast of microaneurysms tends to b color; therefore, RGB color images we green-channeled images. Because the i also be amplified, a low-pass filter bas Fourier Transform) was applied for red noise. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Microaneurysm in the retina is one of the signs of simple diabetic retinopathy. We have been investigating a computerized method for the detection of microaneurysms on retinal fundus images. In this study, the computerized scheme was developed by using twenty five cases. After image preprocessing, candidate regions for microaneurysms were detected using a double-ring filter. Any potential false positives located in the regions corresponding to blood vessels were removed by automatic extraction of blood vessels from the images. One hundred twenty six image features were determined, and 28 components were selected by using principal component analysis, and the candidate lesions were classified into microaneurysms or false positives using the rule-based method and an artificial neural network. The true positive rate of the proposed method was 68% at 15 false positives per image.
    Full-text · Article · Jun 2012 · Proceedings of the IEEE Symposium on Computer-Based Medical Systems
Show more