Sameh Oueslati | Medical Image Processing | Editorial Board Member

Published on by Computer Vision Awards

Editorial Board Member

Sameh Oueslati
IMT-Atlantique, Tunisia

Sameh Oueslati
Affiliation IMT-Atlantique
Country Tunisia
Scopus ID 42861895800
Documents 10
Citations 62
h-index 3
Subject Area Medical Image Processing
Event Global Tech Excellence Awards

Sameh Oueslati is a researcher affiliated with IMT-Atlantique whose scholarly profile is associated with medical image processing and deep-learning-based image segmentation. His documented research includes comparative work on convolutional and fully convolutional neural-network approaches for short-axis left-ventricle segmentation in cardiac cine magnetic resonance imaging. [1] His indexed Scopus profile records 10 documents, 62 citations, and an h-index of 3. [2]

Abstract

Sameh Oueslati is affiliated with IMT-Atlantique and works in medical image processing, with research interests reflected in deep-learning approaches for cardiac magnetic resonance image analysis. His documented publication examines CNN and FCN approaches for short-axis left-ventricle segmentation in cardiac cine MR sequences, highlighting automated segmentation as a means of supporting efficient and reproducible cardiac image analysis. [1] His Scopus profile records 10 documents, 62 citations, and an h-index of 3. [2]

Keywords

  • Medical Image Processing
  • Cardiac Magnetic Resonance Imaging
  • Left-Ventricle Segmentation
  • Deep Learning
  • Convolutional Neural Networks
  • Fully Convolutional Networks

Introduction

Medical image processing combines computational methods with clinical imaging to support quantitative analysis and interpretation. In cardiac MRI, automated segmentation of the left ventricle can assist assessment of cardiac structures and reduce dependence on time-intensive manual delineation. Oueslati’s documented research addresses this problem through comparative evaluation of CNN and FCN approaches. [1]

Research Profile

Oueslati’s research profile is centered on medical image processing, particularly deep-learning methods for segmentation of cardiac MRI images. The available publication record identifies work involving short-axis cardiac cine MR sequences and automated left-ventricle delineation. Scopus records 10 documents, 62 citations, and an h-index of 3 for the indexed author profile. [2]

Research Contributions

A documented contribution by Oueslati is the comparative investigation of CNN and FCN performance for short-axis left-ventricle segmentation in cardiac cine MR sequences. The study evaluates automated segmentation methods and reports that the investigated FCN approach was particularly suitable for the task, demonstrating the relevance of deep-learning architectures to cardiac image analysis. [1]

Publications

The identified publication by Oueslati and Basel Solaiman examines CNN and FCN performance for short-axis left-ventricle segmentation in cardiac cine MR sequences. It appears in Procedia Computer Science, volume 278, with pages 1120–1127. The article addresses image segmentation, deep learning, cardiac cine MRI, CNNs, and FCNs within a medical imaging context. [1]

  • Oueslati, S., & Solaiman, B. (2026). A comparative study of CNN and FCN performance for short-axis left ventricle segmentation in cardiac cine MR sequences. Procedia Computer Science, 278, 1120–1127.

Research Impact

The available indexed record indicates measurable scholarly visibility, with 62 citations and an h-index of 3 reported for the Scopus author profile. [2] The documented cardiac MRI study contributes to the broader development of automated medical image segmentation by examining alternative neural-network architectures for left-ventricle delineation and computational support of cardiac image analysis. [1]

Award Suitability

Oueslati’s documented work is relevant to recognition in medical image processing because it applies deep-learning techniques to a clinically meaningful cardiac imaging problem. The comparative analysis of CNN and FCN architectures demonstrates engagement with automated segmentation methodology, while the indexed publication and citation record provide identifiable scholarly evidence for evaluating research activity and contribution. [1] [2]

Conclusion

Sameh Oueslati’s documented research profile reflects activity in medical image processing, particularly automated cardiac MRI segmentation using deep-learning architectures. His identified publication provides evidence of comparative methodological research involving CNN and FCN approaches, while the Scopus profile indicates an established indexed record with 10 documents, 62 citations, and an h-index of 3. [1] [2]

References

  1. Oueslati, S., & Solaiman, B. (2026). A comparative study of CNN and FCN performance for short-axis left ventricle segmentation in cardiac cine MR sequences. Procedia Computer Science, 278, 1120–1127.
    https://doi.org/10.1016/j.procs.2026.03.091
  2. Elsevier. (n.d.). Scopus author details: Sameh Oueslati, Author ID 42861895800. Scopus.
    https://www.scopus.com/pages/authors/42861895800

Dimitrios Theodoropoulos | Deep Learning | Best Researcher Award

Published on by Computer Vision Awards

Mr. Dimitrios Theodoropoulos | Deep Learning | Best Researcher Award

University of Crete Medical School | Greece

Dimitrios Theodoropoulos is a researcher and AI specialist in medical imaging with expertise in machine learning, deep learning, computer vision, and artificial intelligence applications in healthcare, particularly in radiology and diabetic retinopathy analysis. He is currently pursuing a PhD in Artificial Intelligence in Medical Imaging at the University of Crete, Medical School, building on a master’s degree in computer engineering from Hellenic Mediterranean University and a bachelor’s degree in physics with specialization in microelectronics from the University of Crete, complemented by training as a radiology assistant. Alongside his academic path, he has worked extensively as a radiographer in MRI, CT, X-ray, mammography, DEXA, and EEG imaging, effectively integrating research with clinical practice. He has served as a visiting research fellow at FORTH-CBML and collaborated with institutions such as the Athens Neurotraining Center and Alexandra Hospital, bridging advanced AI research with healthcare innovation. His research focuses on the development of machine learning and deep learning algorithms for classification, segmentation, and detection tasks in medical imaging, with emphasis on diabetic retinopathy, intensive care monitoring, and noninvasive intracranial pressure assessment, while also extending to areas such as pollen analysis. He has published widely in Scopus-indexed journals and conferences, presented at international congresses and academic symposiums, and delivered guest lectures at the National and Kapodistrian University of Athens. Proficient in Python, MATLAB, TensorFlow, PyTorch, Scikit-learn, Linux, and Docker, he has advanced expertise in data preprocessing, model optimization, and AI-driven biomedical solutions. With certifications in Python programming, machine learning, and deep learning, combined with memberships in the Hellenic Artificial Intelligence Society and the Union of Greek Physicists, he demonstrates a rare integration of technical, clinical, and analytical skills, enabling him to advance scientific progress while contributing to patient-centered healthcare innovation.

Profile: Google Scholar | Scopus Profile

Featured Publications

Tsiknakis N., Theodoropoulos D., Manikis G., Ktistakis E., Boutsora O., et al., Deep learning for diabetic retinopathy detection and classification based on fundus images: A review, Comput. Biol. Med., 135, 104599.

Chatziadam P., Dimitriadis A., Gikas S., Logothetis I., Michalodimitrakis M., Theodoropoulos D., et al., TwiFly: A data analysis framework for Twitter, Information, 11(5), 247.

Theodoropoulos D., Karabetsos D.A., Antonios V., Efrosini P., Karantanas A., et al., The current status of noninvasive intracranial pressure monitoring: A literature review, Clin. Neurol. Neurosurg., 108209.

Theodoropoulos D., Sifakis N., Manikis G., Papadourakis G., Armyras K., et al., Semantic segmentation of diabetic retinopathy lesions using deep learning, SN Comput. Sci., 6(7), 782.

Theodoropoulos D., Trivizakis E., Marias K., Xirouchaki N., Vakis A., et al., Predicting intracranial pressure levels: A deep learning approach using computed tomography brain scans, Neurosurgery, 10.1227.