Amira J. Zaylaa

Prof. Dr. Amira J. Zaylaa

Beirut Arab University, Beirut, Beyrouth, Lebanon
orcid

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 October 2017
Verified
Conference Paper
Closed access
MSM. Shaib
M. Shaib
MRM. Rashid
M. Rashid
LHL. Hamawy
L. Hamawy
MAM. Arnout
M. Arnout
IMI. El Majzoub
I. El Majzoub
Amira J. ZaylaaAmira J. Zaylaa
Amira J. Zaylaa
Nearly 20 million premature and Low Birth Weight infants are born each year in developing countries, 4 million die within their first month. These deaths occur due to the unavailability or unreliability of traditional incubators. Moreover, although Telemedicine is helpful in rural areas, the shortage of healthcare providers have made it inaccessible in both basic healthcare. Thereby, traditional preterm baby and low-birth weight incubators and therapeutic techniques lack Telemedicine communication and feedback. The aim of our project is to develop an advanced portable and wireless-base incubator. We tend to provide an affordable, feasible, patient friendly and reliable premature baby incubator especially in low-income countries. The project focuses on the premature babies in the third trimester of pregnancy. The design is based on Wi-Fi and infrared technologies that measure the essential parameters that must be controlled for preemies. These parameters include the heart rate, oxygen level in the blood and temperature. Results showed the advanced design building blocks. The response of the generated power-voltage proves that the power can be regulated by the voltage. The thermal isolation can decrease the thermal lose and increase the time needed to drop temperature 6 times. In the room temperature of premature infant, 20° C and 45° C, the resistance decreases from 12.69 kQ to 4.82 kü. The voltage and the temperature were inversely proportional. The heaters were efficient when tested on water. One of the major advantages of the device is that it surpasses existing techniques. As a future prospect more electronic components needs to be tested and features needs to be extracted.

5 April 2024 in Sensors
Verified
Journal Article
Open access
PDF file
Amira J. ZaylaaAmira J. Zaylaa
Amira J. Zaylaa
SKSylva Kourtian
Sylva Kourtian
Breast cancer results from a disruption of certain cells in breast tissue that undergo uncontrolled growth and cell division. These cells most often accumulate and form a lump called a tumor, which may be benign (non-cancerous) or malignant (cancerous). Malignant tumors can spread quickly throughout the body, forming tumors in other areas, which is called metastasis. Standard screening techniques are insufficient in the case of metastasis; therefore, new and advanced techniques based on artificial intelligence (AI), machine learning, and regression models have been introduced, the primary aim of which is to automatically diagnose breast cancer through the use of advanced techniques, classifiers, and real images. Real fine-needle aspiration (FNA) images were collected from Wisconsin, and four classifiers were used, including three machine learning models and one regression model: the support vector machine (SVM), naive Bayes (NB), k-nearest neighbors (k-NN), and decision tree (DT)-C4.5. According to the accuracy, sensitivity, and specificity results, the SVM algorithm had the best performance; it was the most powerful computational classifier with a 97.13% accuracy and 97.5% specificity. It also had around a 96% sensitivity for the diagnosis of breast cancer, unlike the models used for comparison, thereby providing an exact diagnosis on the one hand and a clear classification between benign and malignant tumors on the other hand. As a future research prospect, more algorithms and combinations of features can be considered for the precise, rapid, and effective classification and diagnosis of breast cancer images for imperative decisions.

10 November 2022
Verified
Conference Paper
Closed access
Amira J. ZaylaaAmira J. Zaylaa
Amira J. Zaylaa
MMMohammad Makki
Mohammad Makki
RKRola Kassem
Rola Kassem
Thalassemia is the most common single-gene disorder throughout the world and represents a major public health problem resulting in abnormal ratios of hemoglobin subunits. It is widely spread throughout the Mediterranean region, Middle East, Southeast Asia, and some parts of Africa. There are different types of Thalassemia characterized by abnormal hemoglobin production. Most of the current hemoglobinopathy screening methods include High Performance Liquid Chromatography (HPLC), hemoglobin electrophoresis, screening of Polymerase Chain Reaction (PCR) mutations, and Deoxyribonucleic Acid (DNA) tests. However, all these methods are costly and require specialized instrumentation and trained technicians. Despite some studies used Artificial Intelligence (AI) they focused merely on Machine Learning (ML) and results were not optimal. This study aims to design a new AI-based framework for Thalassemia diagnosis using Deep Learning (DL) and a new combination of metrics for evaluation. This was achieved through the development and evaluation of a supervised semantic image segmentation model, and the implementation of different data engineering methods such as data annotation, augmentation, pre-processing, and preparation. Transfer learning was utilized and the Prediction Time Augmentation (PTA) was employed to get smoother and more accurate predictions. Quantitative results showed that, the mean Intersection Over Union (IoU) score of prediction of Thalassemia was 88% with PTA and 82% without PTA. Results also showed that as the combined metric of loss scores decreases the prediction of Thalassemia increases. Qualitative results showed that the final prediction of Thalassemia focuses on the Codocytes and labels the other unidentified cells as the background. Also, the resulting image was smoother and less bulky than the original annotated ground truth, and thus could be feasibly diagnosed. As a future prospect we aim to implement more algorithms and extend the diagnosis to include other diseases.

1 January 2018 in Journal of Healthcare Engineering
Verified
Journal Article
Open access
PDF file
Amira J. ZaylaaAmira J. Zaylaa
Amira J. Zaylaa
MRMohamad Rashid
Mohamad Rashid
MSMounir Shaib
Mounir Shaib
IMImad El Majzoub
Imad El Majzoub
Preterm infants encounter an abrupt delivery before their complete maturity during the third trimester of pregnancy. Polls anticipate an increase in the rates of preterm infants for 2025, especially in middle- and low-income countries. Despite the abundance of intensive care methods for preterm infants, such as, but not limited to, commercial, transport, embrace warmer, radiant warmer, and Kangaroo Mother Care methods, they are either expensive, lack the most essential requirements or specifications, or lack the maternal-preterm bond. This drove us to carry this original research and innovative idea of developing a new 3D printed prototype of a Handy preterm infant incubator. We aim to provide the most indispensable intensive care with the lowest cost, to bestow low-income countries with the Handy incubator’s care, preserve the maternal -preterm’s bond, and diminish the rate of mortality. Biomedical features, electronics, and biocompatible materials were utilized. The design was simulated, the prototype was 3D printed, and the outcomes were tested and evaluated. Simulation results showed the best fit for the Handy incubator’s components. Experimental results showed the 3D-printed prototype and the time elapsed to obtain it. Evaluation results revealed that the overall performance of Kangaroo Mother Care and the embrace warmer was 75 ± 1.4% and 66.7 ± 1.5%, respectively, while the overall performance of our Handy incubator was 91.7 ± 1.6%, thereby our cost-effective Handy incubator surpassed existing intensive care methods. The future step is associating the Handy incubator with more specifications and advancements.

1 September 2015
Verified
Conference Paper
Closed access
Amira J. ZaylaaAmira J. Zaylaa
Amira J. Zaylaa
AHA. Harb
A. Harb
FKF. I. Khatib
F. I. Khatib
ZNZ. Nahas
Z. Nahas
FKF. N. Karameh
F. N. Karameh
Epileptic seizures reflect runaway excitation that severely hinders normal brain functions. With EEG recordings reflecting real-time brain activity, it is essential to both predict seizures and improve the classification of seizures in EEG signs. Towards this aim, nonlinear tools are strongly recommended to select the seizure-sensitive features prior to classification. However, the choice of the feature remains challenging. With the multitude of entropy parameters available in literature, and in order to perform a judicious selection of features that are fed to classifiers, this paper presents a comparative study of a host of candidate promising feature extraction techniques. Four entropy features namely Approximate Entropy, Sample Entropy and Renyi entropy of order 2 and Renyi entropy of order 3, were implemented as the standard techniques. Three kernel-based features namely Triangular Entropy, Spherical Entropy and Cauchy entropy were implemented. The former and latter entropies were computed from EEG recordings during induced seizures in three distinct phases: the pre-ictal (pre-seizure) phase, the ictal (seizure) phase, and the post-ictal (post-seizure) phase. Results showed that, among kernel-based methods, Spherical entropy features exhibited the largest parameter sensitivity to (Seizure-Normal) phase changes with the highest normalized relative separation (100%). The sample entropy feature in turn showed the most sensitive to EEG phase changes with the highest relative separation (94.85%), among the studied entropy alternatives.

3 March 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Amira J. ZaylaaAmira J. Zaylaa
Amira J. Zaylaa
SKSylva Kourtian
Sylva Kourtian
The detection of diabetic retinopathy (DR) is challenging, as the current diagnostic methods rely heavily on the expertise of specialists and require the mass screening of diabetic patients. The prevalence of avoidable vision impairment due to DR necessitates the exploration of alternative diagnostic techniques. Specifically, it is necessary to develop reliable automatic methods to enable the early diagnosis and detection of DR from optical images. To address the lack of such methods, this research focused on employing various pre-trained deep neural networks (DNNs) and statistical metrics to provide an automatic framework for detecting DR in optical images. The receiver operating characteristic (ROC) was employed to examine the performance of each network. Ethically obtained real datasets were utilized to validate and enhance the robustness of the proposed detection framework. The experimental results showed that, in terms of the overall performance in DR detection, ResNet-50 was the best, followed by GoogleNet, with 99.44% sensitivity, while they were similar in terms of accuracy (93.56%). ResNet-50 outperformed GoogleNet in terms of the specificity (89.74%) and precision (90.07%) of DR detection. The ROC curves of both ResNet-50 and GoogleNet yielded optimal results, followed by SqueezeNet. MobileNet-v2 showed the weakest performance in terms of the ROC, while all networks showed negligible errors in diagnosis and detection. These results show that the automatic detection and diagnosis framework for DR is a promising tool enabling doctors to diagnose DR early and save time. As future directions, it is necessary to develop a grading algorithm and to explore other strategies to further improve the automatic detection and diagnosis of DR and integrate it into digital slit lamp machines.