Ahmed Sabeeh Yousif -

Gender	MALE
Place of Work	Technical college of Management/ Mosul
Position	Lecturer
Qualification	Ph.d
Speciality	Computer engineering and Microelectronics
Email	Ahmedsabeeh123@ntu.edu.iq
Phone	07748063082
Address	ALMINSSA, MOUSL, Mosul, Iraq

Optimization of PET Image Reconstruction for Enhanced Image Quality in Various Tasks Using a Conventional PET Scanner

Apr 17, 2025

Journal Journal of Electrical and Computer Engineering

publisher Institute of Advanced Engineering and Science

DOI https://doi.org/10.1155/jece/8108611

Volume 2025

Positron emission tomography (PET) imaging requires high-quality yet rapid reconstruction to ensure clinical effectiveness, as these reconstructions enable timely and accurate diagnosis, guide treatment decisions, and reduce the risk of delayed interventions in critical clinical settings. This study introduces a deep learning-based method that employs conditional generative adversarial networks (cGANs) for direct sinogram-to-image PET reconstruction. A dual approach was used: simulation experiments with Zubal phantoms, which provided a controlled and reproducible environment to test the reconstruction accuracy and robustness, and validation with real patient datasets, ensuring the method’s applicability and effectiveness in clinical settings. The primary objective was to evaluate the ability of the cGAN-based method to enhance image quality, reduce noise, and improve reconstruction speed compared to conventional algorithms, such as maximum likelihood expectation maximization (MLEM) and total variation (TV). The methodology involved training a U-net-based generator and a whole-image discriminator iteratively to reconstruct PET images with superior resolution and accuracy. Key outcome measures included bias, variance, structural similarity index (SSIM), and relative root mean square error (rRMSE), as these metrics effectively quantify image fidelity, noise levels, and structural accuracy, which are critical for evaluating the clinical reliability and precision of reconstructed PET images. The results showed that the proposed method achieved significant improvements in image clarity, noise suppression, and computational efficiency, outperforming the traditional techniques. These findings highlight the potential of cGAN-based reconstruction in improving diagnostic accuracy and clinical workflow.

Read Publication

Patch-based Histopathological Images for Non- Hodgkin Lymphoma Detection using Voting CNN with Layer Freezing

Jan 23, 2025

Journal IAENG International Journal of Computer Science

publisher International Association of Engineers

DOI 109/A.3804/UDN-09/XI/2023.

Issue 4

Volume 52

Non-Hodgkin Lymphoma (NHL) is characterized by its diverse subtypes of lymphoid malignancies, presenting challenges for accurate diagnosis due to the variability in tissue morphology and immunophenotypic profiles. This research proposes a novel automated approach for NHL subtype classification using histopathological images, integrating a combination of patch-based analysis with a voting ensemble of Convolutional Neural Networks (CNN). Pre-trained CNN models such as DenseNet169, MobileNetV2, and NASNetMobile were enhanced using a layer-freezing technique to preserve learned low-level features while fine-tuning higher-level layers for improved specificity in NHL detection. A majority voting mechanism aggregates predictions from individual image patches, enhancing classification robustness. The proposed model was evaluated on the IICBU 2008 Lymphoma image dataset, achieving a classification accuracy of 99.11% and an F1score of 99.11%, surpassing previous methods. This approach demonstrates significant potential in improving the accuracy, efficiency, and clinical applicability of automated NHL subtype classification from histopathological images.

Read Publication

Genetic Algorithm-based Convolutional Neural Network Feature Engineering for Optimizing Coronary Heart Disease Prediction Performance

Jul 31, 2024

Journal Healthcare Informatics Research

publisher Korean Society of Medical Informatics

DOI DOI: 10.4258/hir.2024.30.3.234

Volume 30(3)

Objectives: This study aimed to optimize early coronary heart disease (CHD) prediction using a genetic algorithm (GA)-based convolutional neural network (CNN) feature engineering approach. We sought to overcome the limitations of traditional hyperparameter optimization techniques by leveraging a GA for superior predictive performance in CHD detection. Methods: Utilizing a GA for hyperparameter optimization, we navigated a complex combinatorial space to identify optimal configurations for a CNN model. We also employed information gain for feature selection optimization, transforming the CHD datasets into an image-like input for the CNN architecture. The efficacy of this method was benchmarked against traditional optimization strategies. Results: The advanced GA-based CNN model outperformed traditional methods, achieving a substantial increase in accuracy. The optimized model delivered a promising accuracy range, with a peak of 85% in hyperparameter optimization and 100% accuracy when integrated with machine learning algorithms, namely naïve Bayes, support vector machine, decision tree, logistic regression, and random forest, for both binary and multiclass CHD prediction tasks. Conclusions: The integration of a GA into CNN feature engineering is a powerful technique for improving the accuracy of CHD predictions. This approach results in a high degree of predictive reliability and can significantly contribute to the field of AI-driven healthcare, with the possibility of clinical deployment for early CHD detection. Future work will focus on expanding the approach to encompass a wider set of CHD data and potential integration with wearable technology for continuous health monitoring.

Read Publication

An Empirical Study on the Impact of Digital Innovation in Achieving the Digital Organizational Identity

Mar 1, 2023

Journal Journal of System and Management Sciences

publisher Korean Society of Medical Informatics

DOI DOI:10.33168/JSMS.2023.0125

Volume 13

Universities began to compete with each other and acquire all new technologies by adopting the fifth generation of computers that provided huge storage and speed Telecommunications Universities did create virtual reality systems (VR) and Augmented Reality (AR) systems, as well as connected smart cities with the internet, take advantage of artificial intelligence systems (AI) in Building an innovative digital organizational structure. Digital to uniquely grant its students and graduates a unified form of organizational identity that serves it from the scientific, financial and social points of view, in addition to facilitating the task of obtaining jobs and free professions. The idea of the study is to unify the information and data of postgraduate and undergraduate students of the Northern Technical University by designing a digital organizational identity through innovative skills that are fluent in programming applications of computer engineering, artificial intelligence, digital security, communication networks, digital strategies and physical tools, as we surveyed the opinions of 377 academics to be analyzed by the method of structural modeling of relationships And the unmeasurable opinions were dominated by the AMOS system and the SPSS statistical program to calculate the indicators of the conformity of the hypothetical model with the standard model, the regression equation, the degree of freedom, the correlation relationship and the moral influence to deduce the extent of the technical development of the Northern Technical University and its susceptibility to the sustainability of its scientific center within the universities that are geared towards investment and the competition of major universities and the increase in the number of student admissions.

Read Publication