Laboratoire de Génie Informatique et d’Automatique de l’Artois

Niama Assia EL JOUDI

Ph.D. student, ATER
Member of the research themes:
Contact information:

    Revue Internationale avec Comité de Lecture

    Adaptive transfer learning using SegFormer for imbalanced pixel in medical image segmentation
    Signal, Image and Video Processing, pp 617, Vol. 19, Springer Verlag, 05/2025

    Conférence Internationale avec Comité de Lecture

    Active Learning and Adaptive Semi-Supervised Approach for Medical Image Segmentation
    2025 International Conference on Control, Automation and Diagnosis (ICCAD), pp 1-6, Barcelona, Spain, 07/2025
    2024
    International conference with review committee
    Niama Assia EL JOUDI -- Mohamed LAZAAR -- François DELMOTTE -- Hamid ALLAOUI
    Fine-tuned SegFormer for enhanced fetal head segmentation
    14th International Conference on Current and Future Trends of Information and Communication Technologies in Healthcare, ICTH 2024, pp 350–357, Vol. 251, Leuven, Belgium, Procedia Computer Science, October 28-30, 01/2024

    Author of the Ph.D. thesis "Smart Health Monitoring using Deep Learning and Artificial Intelligence"

    2023 - 2025

    Artificial intelligence has positively impacted several fields, such as agriculture, automotive, and many others. Recently and especially with the emergence ofCovid, this technology has been used extensively in the medical field. AI is composed of different subfields: the most popular ones are Machine Learning (ML) and Deep Learning (DL).

    ML algorithms allow computers to learn autonomously from data to accomplish a particular task. However, for computer vision, these traditional techniques require human intervention for feature extraction. Thus, with the development of deep learning, this phase is realized automatically without any intervention. Its architecture is inspired by the human brain, allowing it to deal with the most complex problems.

    Innovation in AI technologies continues to bring new automated applications that improve the medical field. In the medical field. Deep learning models such as CNN can analyze different types of X-rays and thus detect and classify several diseases like cancer and glaucoma. Convolutional neural networks (CNNs) dominate complex computer vision problems thanks to their flexible and sophisticated architecture. Nevertheless, this architecture needs to be optimized in order to achieve surprising and outstanding results. AI applications will help improve the quality of diagnosis by quickly and early detecting infectious and life-threatening diseases, recommending treatment as well as facilitating and assisting practitioners in decision-making.