Pushpa Patil - Academia.edu (original) (raw)

Papers by Pushpa Patil

Research paper thumbnail of Detection of blood vessels in retinal images for diagnosis of diabetics

2018 2nd International Conference on Inventive Systems and Control (ICISC), 2018

Early detection of blood-vessels in an retinal image and determining diameter of vessels is impor... more Early detection of blood-vessels in an retinal image and determining diameter of vessels is important for analysis and dealing of different diseases including glaucoma, hypertension and diabetic retinopathy (DR). To detect the blood-vessels in a retinal fundus images, we proposed a method consisting of four main steps. The first step is pre-processing. Initially, the contrasts of the blood vessels are not clear in the original retinal images. To improve the appearance of blood vessels we are using several image enhancement techniques. In the second step we are using various filters to improve the blood-vessels appearance in the retinal images. The third step is, feature extraction where we are extracting Grey Level Co-occurrence Matrix (GLCM) and Discrete Wavelet transform (DWT) features formed a feature vector. Finally we are applying Support Vector Machine (SVM) classifier which classifies the diseases based on the features. With the two publically available databases DRIVE and CHASE_DB1 databases we are comparing and analyzing the performance of proposed method which measures the specificity, sensitivity and accuracy.

Research paper thumbnail of Detection of exudates for diabetic retinopathy using wavelet transform

2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI), 2017

Retinopathy is the one of the disorder caused in human retina because of diabetic disease. Exudat... more Retinopathy is the one of the disorder caused in human retina because of diabetic disease. Exudates are the one prime sign of diabetes presence. This paper presents detection of exudates from color retina image using discrete wavelet transform and feature extraction method for classification of human retina as normal or diabetic. Blood vessels are separated using mathematical morphology that helps for extraction of optic disc and exudates. Exudates information is used for classification and the method applied in this paper on color retina images provide good results which can be compared with previous used methods.

Research paper thumbnail of Preprocessing and Segmentation of Retina Images for Blood Vessel Extraction

Communications in Computer and Information Science, 2019

In every field there is use of technology as part of in medical field lot of analysis is done usi... more In every field there is use of technology as part of in medical field lot of analysis is done using images. Processing of images will give good analysis when there is no noise or very less noise is present so processing retina images also gives correct results so we used different filters to find out which filter is suitable for pre-processing of retina images available in DRIVE database by computing mean square error (MSE) and Peak signal to noise ratio (PSNR) for different noises. After pre-processing images are segmented using discrete wavelet transform (DWT) and extracted blood vessel pixels are computed and compared with first observer result available in data base and results are very close to manual segmentation which is given DRIVE database.

Research paper thumbnail of Analysis on diagnosing diabetic retinopathy by segmenting blood vessels, optic disc and retinal abnormalities

Journal of Medical Engineering & Technology, 2020

The main intention of mass screening programmes for Diabetic Retinopathy (DR) is to detect and di... more The main intention of mass screening programmes for Diabetic Retinopathy (DR) is to detect and diagnose the disorder earlier than it leads to vision loss. Automated analysis of retinal images has the likelihood to improve the efficacy of screening programmes when compared over the manual image analysis. This article plans to develop a framework for the detection of DR from the retinal fundus images using three evaluations based on optic disc, blood vessels and retinal abnormalities. Initially, the pre-processing steps like green channel conversion and Contrast Limited Adaptive Histogram Equalisation is done. Further, the segmentation procedure starts with optic disc segmentation by open-close watershed transform, blood vessel segmentation by grey level thresholding and abnormality segmentation (hard exudates, haemorrhages, Microaneurysm and soft exudates) by top hat transform and Gabor filtering mechanisms. From the three segmented images, the feature like local binary pattern, texture energy measurement, Shanon's and Kapur's entropy are extracted, which is subjected to optimal feature selection process using the new hybrid optimisation algorithm termed as Trial-based Bypass Improved Dragonfly Algorithm (TB-DA). These features are given to hybrid machine learning algorithm with the combination of NN and DBN. As a modification, the same hybrid TB-DA is used to enhance the training of hybrid classifier, which outputs the categorisation as normal, mild, moderate or severe images based on three components.

Research paper thumbnail of Computer-aided diabetic retinopathy diagnostic model using optimal thresholding merged with neural network

International Journal of Intelligent Computing and Cybernetics, 2020

PurposeDiabetic retinopathy (DR) is a central root of blindness all over the world. Though DR is ... more PurposeDiabetic retinopathy (DR) is a central root of blindness all over the world. Though DR is tough to diagnose in starting stages, and the detection procedure might be time-consuming even for qualified experts. Nowadays, intelligent disease detection techniques are extremely acceptable for progress analysis and recognition of various diseases. Therefore, a computer-aided diagnosis scheme based on intelligent learning approaches is intended to propose for diagnosing DR effectively using a benchmark dataset.Design/methodology/approachThe proposed DR diagnostic procedure involves four main steps: (1) image pre-processing, (2) blood vessel segmentation, (3) feature extraction, and (4) classification. Initially, the retinal fundus image is taken for pre-processing with the help of Contrast Limited Adaptive Histogram Equalization (CLAHE) and average filter. In the next step, the blood vessel segmentation is carried out using a segmentation process with optimized gray-level thresholdin...

Research paper thumbnail of Detection of blood vessels in retinal images for diagnosis of diabetics

2018 2nd International Conference on Inventive Systems and Control (ICISC), 2018

Early detection of blood-vessels in an retinal image and determining diameter of vessels is impor... more Early detection of blood-vessels in an retinal image and determining diameter of vessels is important for analysis and dealing of different diseases including glaucoma, hypertension and diabetic retinopathy (DR). To detect the blood-vessels in a retinal fundus images, we proposed a method consisting of four main steps. The first step is pre-processing. Initially, the contrasts of the blood vessels are not clear in the original retinal images. To improve the appearance of blood vessels we are using several image enhancement techniques. In the second step we are using various filters to improve the blood-vessels appearance in the retinal images. The third step is, feature extraction where we are extracting Grey Level Co-occurrence Matrix (GLCM) and Discrete Wavelet transform (DWT) features formed a feature vector. Finally we are applying Support Vector Machine (SVM) classifier which classifies the diseases based on the features. With the two publically available databases DRIVE and CHASE_DB1 databases we are comparing and analyzing the performance of proposed method which measures the specificity, sensitivity and accuracy.

Research paper thumbnail of Detection of exudates for diabetic retinopathy using wavelet transform

2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI), 2017

Retinopathy is the one of the disorder caused in human retina because of diabetic disease. Exudat... more Retinopathy is the one of the disorder caused in human retina because of diabetic disease. Exudates are the one prime sign of diabetes presence. This paper presents detection of exudates from color retina image using discrete wavelet transform and feature extraction method for classification of human retina as normal or diabetic. Blood vessels are separated using mathematical morphology that helps for extraction of optic disc and exudates. Exudates information is used for classification and the method applied in this paper on color retina images provide good results which can be compared with previous used methods.

Research paper thumbnail of Preprocessing and Segmentation of Retina Images for Blood Vessel Extraction

Communications in Computer and Information Science, 2019

In every field there is use of technology as part of in medical field lot of analysis is done usi... more In every field there is use of technology as part of in medical field lot of analysis is done using images. Processing of images will give good analysis when there is no noise or very less noise is present so processing retina images also gives correct results so we used different filters to find out which filter is suitable for pre-processing of retina images available in DRIVE database by computing mean square error (MSE) and Peak signal to noise ratio (PSNR) for different noises. After pre-processing images are segmented using discrete wavelet transform (DWT) and extracted blood vessel pixels are computed and compared with first observer result available in data base and results are very close to manual segmentation which is given DRIVE database.

Research paper thumbnail of Analysis on diagnosing diabetic retinopathy by segmenting blood vessels, optic disc and retinal abnormalities

Journal of Medical Engineering & Technology, 2020

The main intention of mass screening programmes for Diabetic Retinopathy (DR) is to detect and di... more The main intention of mass screening programmes for Diabetic Retinopathy (DR) is to detect and diagnose the disorder earlier than it leads to vision loss. Automated analysis of retinal images has the likelihood to improve the efficacy of screening programmes when compared over the manual image analysis. This article plans to develop a framework for the detection of DR from the retinal fundus images using three evaluations based on optic disc, blood vessels and retinal abnormalities. Initially, the pre-processing steps like green channel conversion and Contrast Limited Adaptive Histogram Equalisation is done. Further, the segmentation procedure starts with optic disc segmentation by open-close watershed transform, blood vessel segmentation by grey level thresholding and abnormality segmentation (hard exudates, haemorrhages, Microaneurysm and soft exudates) by top hat transform and Gabor filtering mechanisms. From the three segmented images, the feature like local binary pattern, texture energy measurement, Shanon's and Kapur's entropy are extracted, which is subjected to optimal feature selection process using the new hybrid optimisation algorithm termed as Trial-based Bypass Improved Dragonfly Algorithm (TB-DA). These features are given to hybrid machine learning algorithm with the combination of NN and DBN. As a modification, the same hybrid TB-DA is used to enhance the training of hybrid classifier, which outputs the categorisation as normal, mild, moderate or severe images based on three components.

Research paper thumbnail of Computer-aided diabetic retinopathy diagnostic model using optimal thresholding merged with neural network

International Journal of Intelligent Computing and Cybernetics, 2020

PurposeDiabetic retinopathy (DR) is a central root of blindness all over the world. Though DR is ... more PurposeDiabetic retinopathy (DR) is a central root of blindness all over the world. Though DR is tough to diagnose in starting stages, and the detection procedure might be time-consuming even for qualified experts. Nowadays, intelligent disease detection techniques are extremely acceptable for progress analysis and recognition of various diseases. Therefore, a computer-aided diagnosis scheme based on intelligent learning approaches is intended to propose for diagnosing DR effectively using a benchmark dataset.Design/methodology/approachThe proposed DR diagnostic procedure involves four main steps: (1) image pre-processing, (2) blood vessel segmentation, (3) feature extraction, and (4) classification. Initially, the retinal fundus image is taken for pre-processing with the help of Contrast Limited Adaptive Histogram Equalization (CLAHE) and average filter. In the next step, the blood vessel segmentation is carried out using a segmentation process with optimized gray-level thresholdin...