Preferred Language
Articles
/
fBb2j4oBVTCNdQwCuJ_G
Deep Transfer Learning for Improved Detection of Keratoconus using Corneal Topographic Maps
...Show More Authors
Abstract <p>Clinical keratoconus (KCN) detection is a challenging and time-consuming task. In the diagnosis process, ophthalmologists must revise demographic and clinical ophthalmic examinations. The latter include slit-lamb, corneal topographic maps, and Pentacam indices (PI). We propose an Ensemble of Deep Transfer Learning (EDTL) based on corneal topographic maps. We consider four pretrained networks, SqueezeNet (SqN), AlexNet (AN), ShuffleNet (SfN), and MobileNet-v2 (MN), and fine-tune them on a dataset of KCN and normal cases, each including four topographic maps. We also consider a PI classifier. Then, our EDTL method combines the output probabilities of each of the five classifiers to obtain a decision based on the fusion of probabilities. Individually, the classifier based on PI achieved 93.1% accuracy, whereas the deep classifiers reached classification accuracies over 90% only in isolated cases. Overall, the average accuracy of the deep networks over the four corneal maps ranged from 86% (SfN) to 89.9% (AN). The classifier ensemble increased the accuracy of the deep classifiers based on corneal maps to values ranging (92.2% to 93.1%) for SqN and (93.1% to 94.8%) for AN. Including in the ensemble-specific combinations of corneal maps’ classifiers and PI increased the accuracy to 98.3%. Moreover, visualization of first learner filters in the networks and Grad-CAMs confirmed that the networks had learned relevant clinical features. This study shows the potential of creating ensembles of deep classifiers fine-tuned with a transfer learning strategy as it resulted in an improved accuracy while showing learnable filters and Grad-CAMs that agree with clinical knowledge. This is a step further towards the potential clinical deployment of an improved computer-assisted diagnosis system for KCN detection to help ophthalmologists to confirm the clinical decision and to perform fast and accurate KCN treatment.</p>
Scopus Clarivate Crossref
View Publication
Publication Date
Sun Sep 01 2019
Journal Name
Baghdad Science Journal
Common Fixed Point of a Finite-step Iteration Algorithm Under Total Asymptotically Quasi-nonexpansive Maps
...Show More Authors

      Throughout this paper, a generic iteration algorithm for a finite family of total asymptotically quasi-nonexpansive maps in uniformly convex Banach space is suggested. As well as weak / strong convergence theorems of this algorithm to a common fixed point are established. Finally, illustrative numerical example by using Matlab is presented.

View Publication Preview PDF
Scopus (14)
Crossref (3)
Scopus Clarivate Crossref
Publication Date
Sat Jan 19 2019
Journal Name
Artificial Intelligence Review
Survey on supervised machine learning techniques for automatic text classification
...Show More Authors

View Publication
Scopus (297)
Crossref (269)
Scopus Clarivate Crossref
Publication Date
Wed Oct 20 2021
Journal Name
Ibn Al-haitham Journal For Pure And Applied Sciences
Fully Automated Magnetic Resonance Detection and Segmentation of Brain using Convolutional Neural Network
...Show More Authors

     The brain's magnetic resonance imaging (MRI) is tasked with finding the pixels or voxels that establish where the brain is in a medical image The Convolutional Neural Network (CNN) can process curved baselines that frequently occur in scanned documents. Next, the lines are separated into characters. In the Convolutional Neural Network (CNN) can process curved baselines that frequently occur in scanned documents case of fonts with a fixed MRI width, the gaps are analyzed and split. Otherwise, a limited region above the baseline is analyzed, separated, and classified. The words with the lowest recognition score are split into further characters x until the result improves. If this does not improve the recognition s

... Show More
View Publication Preview PDF
Crossref
Publication Date
Wed Dec 01 2021
Journal Name
Baghdad Science Journal
A Prevalence study of Entamoeba spp. in Basrah Province using Different Detection Methods
...Show More Authors

This study aims to determine the prevalence of Entamoeba histolytica, Entamoeba dispar and
Entamoeba moshkovskii by three methods of diagnosis (microscopic examination, cultivation and PCR) that
were compared to obtain an accurate diagnosis of Entamoeba spp. during amoebiasis. Total (n=150) stool
samples related to patients were (n = 100) and healthy controls (n= 50). Clinically diagnosed stool samples
(n=100) were collected from patients attending the consultant clinics of different hospitals in Basrah during
the period from January 2018 to January 2019. The results showed that 60% of collected samples were
positive in a direct microscopic examination. All samples were cultivated on different media; the Bra

... Show More
View Publication Preview PDF
Scopus (5)
Crossref (4)
Scopus Clarivate Crossref
Publication Date
Fri Jan 01 2016
Journal Name
Iraqi Journal Of Science
Land cover change detection of Baghdad city using multi-spectral remote sensing imagery
...Show More Authors

Publication Date
Wed Oct 17 2018
Journal Name
Journal Of Economics And Administrative Sciences
Comparison Between the Methods Estimate Nonparametric and Semiparametric Transfer Function Model in Time Series Using Simulation
...Show More Authors

Publication Date
Tue Dec 01 2015
Journal Name
Journal Of Engineering
Improved Automatic Registration Adjustment of Multi-source Remote Sensing Datasets
...Show More Authors

Registration techniques are still considered challenging tasks to remote sensing users, especially after enormous increase in the volume of remotely sensed data being acquired by an ever-growing number of earth observation sensors. This surge in use mandates the development of accurate and robust registration procedures that can handle these data with varying geometric and radiometric properties. This paper aims to develop the traditional registration scenarios to reduce discrepancies between registered datasets in two dimensions (2D) space for remote sensing images. This is achieved by designing a computer program written in Visual Basic language following two main stages: The first stage is a traditional registration process by de

... Show More
Crossref (1)
Crossref
Publication Date
Tue Dec 01 2015
Journal Name
Journal Of Engineering
Improved Automatic Registration Adjustment of Multi-source Remote Sensing Datasets
...Show More Authors

Registration techniques are still considered challenging tasks to remote sensing users, especially after enormous increase in the volume of remotely sensed data being acquired by an ever-growing number of earth observation sensors. This surge in use mandates the development of accurate and robust registration procedures that can handle these data with varying geometric and radiometric properties. This paper aims to develop the traditional registration scenarios to reduce discrepancies between registered datasets in two dimensions (2D) space for remote sensing images. This is achieved by designing a computer program written in Visual Basic language following two main stages: The first stage is a traditional registration p

... Show More
View Publication Preview PDF
Publication Date
Thu Jan 12 2017
Journal Name
Journal Of Agricultural And Food Chemistry
Using Standing Gold Nanorod Arrays as Surface-Enhanced Raman Spectroscopy (SERS) Substrates for Detection of Carbaryl Residues in Fruit Juice and Milk
...Show More Authors

View Publication
Scopus (113)
Crossref (105)
Scopus Clarivate Crossref
Publication Date
Sat Oct 29 2022
Journal Name
International Ophthalmology
Comparison of corneal flap thickness predictability and architecture between femtosecond laser and sub-Bowman keratomileusis microkeratome in laser in situ keratomileusis
...Show More Authors

View Publication
Scopus (3)
Crossref (2)
Scopus Clarivate Crossref