Preferred Language
Articles
/
joe-1913
Deep Learning of Diabetic Retinopathy Classification in Fundus Images
...Show More Authors

Diabetic retinopathy is an eye disease in diabetic patients due to damage to the small blood vessels in the retina due to high and low blood sugar levels. Accurate detection and classification of Diabetic Retinopathy is an important task in computer-aided diagnosis, especially when planning for diabetic retinopathy surgery. Therefore, this study aims to design an automated model based on deep learning, which helps ophthalmologists detect and classify diabetic retinopathy severity through fundus images. In this work, a deep convolutional neural network (CNN) with transfer learning and fine tunes has been proposed by using pre-trained networks known as Residual Network-50 (ResNet-50). The overall framework of the proposed classification model is divided into three major phases, including pre-processing, training the Resnet-50 network, and classification with evaluation. In the first phase, pre-processing techniques are applied to the APTOS2019 fundus images dataset to find the best features and highlight some fine details of these images. The resnet-50 network was trained in the second phase using the training set and saved the best model obtained that gives high accuracy during the training process. Finally, this saved model has been implemented on the testing dataset for classification DR grades. The proposed model shows good and best classification performance, which was obtained with an accuracy of 98.3%, a precision of 98.4%, an F1-Score of 98.5 % and the recall of 98.4%.

 

Crossref
View Publication Preview PDF
Quick Preview PDF
Publication Date
Fri Oct 23 2020
Journal Name
Palarch’s Journal Of Archaeology Of Egypt/egyptology
A Multimodal Discourse Analysis of Visual Images in UNHCR Reports on Displaced Iraqis
...Show More Authors

The advent of UNHCR reports has given rise to the uniqueness of its distinctive way of image representation and using semiotic features. So, there are a lot of researches that have investigated UNHCR reports, but no research has examined images in UNHCR reports of displaced Iraqis from a multimodal discourse perspective. The present study suggests that the images are, like language, rich in many potential meanings and are governed by clearly visual grammar structures that can be employed to decode these multiple meanings. Seven images are examined in terms of their representational, interactional and compositional aspects. Depending on the results, this study concludes that the findings support the visual grammar theory and highlight the va

... Show More
View Publication Preview PDF
Publication Date
Thu Jun 30 2011
Journal Name
Al-kindy College Medical Journal
Asymptomatic Bacteriuria in Pregnant and Diabetic Women
...Show More Authors

Background: Asymptomatic bacteriuria (ASB) is
defined as isolation of a specified quantitative count
of bacteria in an appropriately collected urine
specimen from an individual without symptoms or
signs of urinary tract infection.
Aim of study: To evaluate the frequency of
bacteriuria according to age, pregnancy, and type II
diabetes mellitus in a sample of Iraqi women.
Patients and Methods: A total of 125 female
individuals were involved. The study participants
were classified into the following groups: nonpregnant
women with type II diabetes mellitus,
pregnant women with type II diabetes mellitus,
pregnant women without type II diabetes mellitus, and
apparently healthy non-pregnant women. Urine

... Show More
View Publication Preview PDF
Publication Date
Sun Feb 10 2019
Journal Name
Journal Of The College Of Education For Women
Movement Skills in Diabetic children Kindergarten Department
...Show More Authors

The current research aims at studying the precise and big movement skills and the ability
of the diabetic child to do them, The research sample consisted of ten diabetic children who
go to the Diabetes Center of Research that is apart of the Yarmook hospital. The sample was
chosen according to the intentional method and it wasn’t possible to have bigger sample
because the parents of the children didn’t agree for fear on the children’s health. It was
apparent through the research that the diabetic child performs the big movement skills better
than his ability to do the precise movement skills because they require accuracy,
concentration and high attention.
The most prominent recommendations and suggestions.

... Show More
View Publication Preview PDF
Publication Date
Tue Jun 01 2021
Journal Name
Iraqi Journal Of Physics
Studying Audio Capacity as Carrier of Secret Images in Steganographic System
...Show More Authors

Steganography art is a technique for hiding information where the unsuspicious cover signal carrying the secret information. Good steganography technique must be includes the important criterions robustness, security, imperceptibility and capacity. The improving each one of these criterions is affects on the others, because of these criterions are overlapped each other.  In this work, a good high capacity audio steganography safely method has been proposed based on LSB random replacing of encrypted cover with encrypted message bits at random positions. The research also included a capacity studying for the audio file, speech or music, by safely manner to carrying secret images, so it is difficult for unauthorized persons to suspect

... Show More
View Publication Preview PDF
Crossref
Publication Date
Wed Mar 01 2017
Journal Name
Un Published
Search Engine for Identification of Personal Images
...Show More Authors

Publication Date
Fri Jun 30 2006
Journal Name
Al-kindy College Medical Journal
Oral Carriage Rate of Candida Species in Diabetic Patients
...Show More Authors

Background: It is well known that oral carriage
of Candida species increase in many situations, like
obesity, debility, leukemia, viral infection, use of
certain drugs in addition to diabetes mellitus.
Objective: find the relation between diabetes and
its control on oral carriage of Candida.
Methods: Thirty four hundred oral swabs from
diabetic patients 67% are females and 33% are
males, 41.7% are type 1 diabetes and 58.3% are type
2.different culture media are used.
Results: we found that 37.9% of diabetics had oral
carriage, older age group had more but the
difference is not significant statistically P>0.05, in
addition females carry more Candida than males
P<0.05, while type of diabetes

... Show More
View Publication Preview PDF
Publication Date
Mon Feb 04 2019
Journal Name
Journal Of The College Of Education For Women
Classification of Rural Road Network in Al-Najaf Governorate
...Show More Authors

This study has dealt with, the issue of classification of rural road network , in addition to prepare a suggested for the classification for this network in Iraq , this classification account , the specifications and characteristics of rural roads, population, and the range taking of settlements , then this classification was applied on the rural road network in the Najaf province there are four categories of classification ,the first is major arterial rural roads divided into two major arterial and minor arterial roads , while the second category collected roads which was divided into minor arterial roads and main collected roads. The third category was represented by Local Roads , it has been divided into paved roads and unpaved, the f

... Show More
View Publication Preview PDF
Publication Date
Sat Aug 01 2015
Journal Name
Modern Applied Science
A New Method for Detecting Cerebral Tissues Abnormality in Magnetic Resonance Images
...Show More Authors

We propose a new method for detecting the abnormality in cerebral tissues present within Magnetic Resonance Images (MRI). Present classifier is comprised of cerebral tissue extraction, image division into angular and distance span vectors, acquirement of four features for each portion and classification to ascertain the abnormality location. The threshold value and region of interest are discerned using operator input and Otsu algorithm. Novel brain slices image division is introduced via angular and distance span vectors of sizes 24˚ with 15 pixels. Rotation invariance of the angular span vector is determined. An automatic image categorization into normal and abnormal brain tissues is performed using Support Vector Machine (SVM). St

... Show More
Publication Date
Fri Jan 01 2016
Journal Name
Diabetic Foot &amp; Ankle
Risk factors for occurrence and recurrence of diabetic foot ulcers among Iraqi diabetic patients
...Show More Authors

View Publication
Scopus (18)
Crossref (13)
Scopus Crossref
Publication Date
Sat Dec 01 2012
Journal Name
Iraqi Journal Of Physics
Wavelet compression for remotely sensed images
...Show More Authors

Image compression is very important in reducing the costs of data storage transmission in relatively slow channels. Wavelet transform has received significant attention because their multiresolution decomposition that allows efficient image analysis. This paper attempts to give an understanding of the wavelet transform using two more popular examples for wavelet transform, Haar and Daubechies techniques, and make compression between their effects on the image compression.

View Publication Preview PDF