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
Sat Mar 04 2023
Journal Name
Baghdad Science Journal
Exploration of CPCD number for power graph
...Show More Authors

Recently, complementary perfect corona domination in graphs was introduced. A dominating set S of a graph G is said to be a complementary perfect corona dominating set (CPCD – set) if each vertex in  is either a pendent vertex or a support vertex and  has a perfect matching. The minimum cardinality of a complementary perfect corona dominating set is called the complementary perfect corona domination number and is denoted by . In this paper, our parameter hasbeen discussed for power graphs of path and cycle.

View Publication Preview PDF
Scopus (1)
Scopus Clarivate Crossref
Publication Date
Wed Mar 01 2017
Journal Name
Un Published
Search Engine for Identification of Personal Images
...Show More Authors

Publication Date
Fri Jan 19 2024
Journal Name
Turkish Journal Of Pharmaceutical Sciences
Taste Masking of Steroids for Oral Formulations
...Show More Authors

View Publication
Scopus (8)
Crossref (7)
Scopus Clarivate Crossref
Publication Date
Sun Jan 01 2023
Journal Name
2nd International Conference On Mathematical Techniques And Applications: Icmta2021
Review of clustering for gene expression data
...Show More Authors

View Publication
Crossref (2)
Crossref
Publication Date
Mon Mar 08 2021
Journal Name
Baghdad Science Journal
Calculation of the charcteristic electronenergy for mercury
...Show More Authors

numerical study is applied to the mercury-argon mixture by solving the boltzman transport equation for different mixture percentage.

View Publication Preview PDF
Crossref
Publication Date
Thu Mar 05 2020
Journal Name
International Journal Of Psychosocial Rehabilitation
The history of rhythmic gymnastics for women
...Show More Authors

Publication Date
Wed Apr 01 2020
Journal Name
Journal Of Construction Engineering And Management
Development of Assessment Tool for Workforce Sustainability
...Show More Authors

View Publication
Scopus (46)
Crossref (42)
Scopus Clarivate Crossref
Publication Date
Mon May 01 2017
Journal Name
Journal Of Arab Studies In Education & Psychology (asep)
Procedural Knowledge for the, Mathematics Departments Students, College of Education for Pure Sciences / Ibn al-Haytham, University of Baghdad
...Show More Authors

Publication Date
Sat Dec 01 2018
Journal Name
Al-khwarizmi Engineering Journal
Design and Implementation of an Automatic Control for Two Axis Tracking System for Applications of Concentrated Solar Thermal Power
...Show More Authors

The present work presents design and implementation of an automated two-axis solar tracking system using local materials with minimum cost, light weight and reliable structure. The tracking system consists of two parts, mechanical units (fixed and moving parts) and control units (four LDR sensors and Arduino UNO microcontroller to control two DC servomotors). The tracking system was fitted and assembled together with a parabolic trough solar concentrator (PTSC) system to move it according to information come from the sensors so as to keep the PTSC always perpendicular to sun rays. The experimental tests have been done on the PTSC system to investigate its thermal performance in two cases, with tracking system (case 1) and without trackin

... Show More
View Publication Preview PDF
Crossref (2)
Crossref
Publication Date
Wed Aug 07 2019
Journal Name
Iraqi National Journal Of Nursing Specialties
Determination of the Cardiac Patients Knowledge toward Using Anticoagulant Medications at Missan Governorate Hospitals
...Show More Authors

Objective- the study aim to determine the cardiac patient knowledge about anticoagulant medications using and its relationship with demographic data(age. gender. level of education. occupational). Methodology- A descriptive study(quasi-experimental)design was carried out to determine cardiac patient knowledge consider to using anticoagulant medications . Starting from(1th Jun 2017 to5th October 2018).To achieve the objectives of the study, a non-probability sample (a purposive sample) consisted of random sample comprised of (30) patients were taken anticoagulant medications ..The measurement of patient knowledge were collected through the use of questionnaire which is related to patient knowledge toward using the anticoagulant medication

... Show More
View Publication Preview PDF