Limits...
A computational modeling for the detection of diabetic retinopathy severity.

Mishra PK, Sinha A, Teja KR, Bhojwani N, Sahu S, Kumar A - Bioinformation (2014)

Bottom Line: Algorithms or method developed here may also be used for pooling diagnostic knowledge for serving mankind.Here we have described a computational based low cost retinal diagnostic approach which can aid an ophthalmologist to quickly diagnose the various stages of DR.This system can accept retinal images and can successfully detect any pathological condition associated with DR.

View Article: PubMed Central - PubMed

Affiliation: Department of Information Technology, National Institute of Technology, Raipur, Chhattisgarh, India.

ABSTRACT
Prolonged diabetes ultimately leads to Diabetic Retinopathy (DR) which is one of the leading causes of preventable blindness in the world. Through advanced image analysis techniques are used for abnormalities detection in retina that define and correlate the severity of DR. A thorough study is done in this area in recent past years and on the basis of these studies we have developed a computer based prediction model that is used to determine the severity of DR. To identify severity DR, we have analyzed the human eye image. We have extracted some important features from human eye image i.e. Blood Artery, Optical disc, Exudates. Based on these image and data we have designed an automated system for the determination of DR severity. This automated DR severity assessment methods can be used to predict the clinical case and conditions when young clinicians would agree or disagree with their more experienced fellow members. The algorithms described in this study may be used in clinical practice to validate or invalidate the diagnoses. Algorithms or method developed here may also be used for pooling diagnostic knowledge for serving mankind. Here we have described a computational based low cost retinal diagnostic approach which can aid an ophthalmologist to quickly diagnose the various stages of DR. This system can accept retinal images and can successfully detect any pathological condition associated with DR.

No MeSH data available.


Related in: MedlinePlus

Set of multimodal photographs of eye analysed foroptic disc detection a) Input Image b) Applying AdaptiveHistogram Equalization c) After Closing MorphologicalOperation d) After Image Segmentation e) After removingsmall regions f) Optic Disc Mapped.
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC4209363&req=5

Figure 2: Set of multimodal photographs of eye analysed foroptic disc detection a) Input Image b) Applying AdaptiveHistogram Equalization c) After Closing MorphologicalOperation d) After Image Segmentation e) After removingsmall regions f) Optic Disc Mapped.

Mentions: The results were obtained from fundus images which wereused for detection and diagnosis of DR. The individualsegmentation modules were developed using MATLAB, laterintegrated with other computational approaches as mentionedin methodology. We have to determine the thickness of theblood vessels because diseased eye have more thick bloodvessels when compared to normal eye. In order to determinethe thickness of the blood vessels we had applied the edgedetection algorithms like sobel operator, Morphological edgedetector etc, through this we had calculated the thickness of thediseased blood vessels and compared with normal eye imagedata. In this way we have estimate the disease level andseverity of DR (Figure 1). Image enhancement process has beenapplied on filtered image (Figure 1a) by using adaptivethreshold as shown in Figure 1b. The output image is a brighterand contains blood vessel and exudates that has to be removed.It is done by applying closing morphological operation (erosionand dilation) so that the blood vessel is removed from theimage. The erosion operation narrows and remove blood vesselwhile the dilation operation restore the image without bloodvessel as shown in Figure 1c. The image as shown in Figure 1dconsists of small bright spots that are mostly exudates or fatsetc. Such small bright spots (that covers less than 1% pixels ofimage) are removed from the image by bwareaopen built-inmethod in Matlab as shown in Figure 1e. After that we haveidentified the size of the optical disc in eye because diseasedeye have expanded optical disc size compare with standard eyedata (Figure 2). In order to find boundaries and the border ofthe optical disc in the eye image, we have implementeddifferent algorithms as discussed in methadology. Hemorrhageis mainly caused due to clotting of blood these clotting of bloodin eye is identified as dark spots. In diseased eye there is hugepercentage of dark spots. So we have identified these darkspots in Figure 3 as output image. The output image wasbinary threshold to a particular value such that image containsclear boundaries of the exudates. After getting the boundarieswe have two types of exudates present in it soft exudates andhard exudates. Hard exudates have closed boundaries in thethreshold image while the soft exudates breaks in the contoursare connected by smoothing spines.


A computational modeling for the detection of diabetic retinopathy severity.

Mishra PK, Sinha A, Teja KR, Bhojwani N, Sahu S, Kumar A - Bioinformation (2014)

Set of multimodal photographs of eye analysed foroptic disc detection a) Input Image b) Applying AdaptiveHistogram Equalization c) After Closing MorphologicalOperation d) After Image Segmentation e) After removingsmall regions f) Optic Disc Mapped.
© Copyright Policy - open-access
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC4209363&req=5

Figure 2: Set of multimodal photographs of eye analysed foroptic disc detection a) Input Image b) Applying AdaptiveHistogram Equalization c) After Closing MorphologicalOperation d) After Image Segmentation e) After removingsmall regions f) Optic Disc Mapped.
Mentions: The results were obtained from fundus images which wereused for detection and diagnosis of DR. The individualsegmentation modules were developed using MATLAB, laterintegrated with other computational approaches as mentionedin methodology. We have to determine the thickness of theblood vessels because diseased eye have more thick bloodvessels when compared to normal eye. In order to determinethe thickness of the blood vessels we had applied the edgedetection algorithms like sobel operator, Morphological edgedetector etc, through this we had calculated the thickness of thediseased blood vessels and compared with normal eye imagedata. In this way we have estimate the disease level andseverity of DR (Figure 1). Image enhancement process has beenapplied on filtered image (Figure 1a) by using adaptivethreshold as shown in Figure 1b. The output image is a brighterand contains blood vessel and exudates that has to be removed.It is done by applying closing morphological operation (erosionand dilation) so that the blood vessel is removed from theimage. The erosion operation narrows and remove blood vesselwhile the dilation operation restore the image without bloodvessel as shown in Figure 1c. The image as shown in Figure 1dconsists of small bright spots that are mostly exudates or fatsetc. Such small bright spots (that covers less than 1% pixels ofimage) are removed from the image by bwareaopen built-inmethod in Matlab as shown in Figure 1e. After that we haveidentified the size of the optical disc in eye because diseasedeye have expanded optical disc size compare with standard eyedata (Figure 2). In order to find boundaries and the border ofthe optical disc in the eye image, we have implementeddifferent algorithms as discussed in methadology. Hemorrhageis mainly caused due to clotting of blood these clotting of bloodin eye is identified as dark spots. In diseased eye there is hugepercentage of dark spots. So we have identified these darkspots in Figure 3 as output image. The output image wasbinary threshold to a particular value such that image containsclear boundaries of the exudates. After getting the boundarieswe have two types of exudates present in it soft exudates andhard exudates. Hard exudates have closed boundaries in thethreshold image while the soft exudates breaks in the contoursare connected by smoothing spines.

Bottom Line: Algorithms or method developed here may also be used for pooling diagnostic knowledge for serving mankind.Here we have described a computational based low cost retinal diagnostic approach which can aid an ophthalmologist to quickly diagnose the various stages of DR.This system can accept retinal images and can successfully detect any pathological condition associated with DR.

View Article: PubMed Central - PubMed

Affiliation: Department of Information Technology, National Institute of Technology, Raipur, Chhattisgarh, India.

ABSTRACT
Prolonged diabetes ultimately leads to Diabetic Retinopathy (DR) which is one of the leading causes of preventable blindness in the world. Through advanced image analysis techniques are used for abnormalities detection in retina that define and correlate the severity of DR. A thorough study is done in this area in recent past years and on the basis of these studies we have developed a computer based prediction model that is used to determine the severity of DR. To identify severity DR, we have analyzed the human eye image. We have extracted some important features from human eye image i.e. Blood Artery, Optical disc, Exudates. Based on these image and data we have designed an automated system for the determination of DR severity. This automated DR severity assessment methods can be used to predict the clinical case and conditions when young clinicians would agree or disagree with their more experienced fellow members. The algorithms described in this study may be used in clinical practice to validate or invalidate the diagnoses. Algorithms or method developed here may also be used for pooling diagnostic knowledge for serving mankind. Here we have described a computational based low cost retinal diagnostic approach which can aid an ophthalmologist to quickly diagnose the various stages of DR. This system can accept retinal images and can successfully detect any pathological condition associated with DR.

No MeSH data available.


Related in: MedlinePlus