Dawood Al Chanti
Dawood Al Chanti
Embedded Files
Associate Professor (Maître de conférences)
Associate Professor (Maître de conférences)
Department of Data Science, PICSA Team, GIPSA-Lab
Department of Data Science, PICSA Team, GIPSA-Lab
Grenoble-INP, Phelma, Gipsa-Lab
Grenoble-INP, Phelma, Gipsa-Lab
Biography
Biography
Dawood Al Chanti received the Doctor of Philosophy, PhD degree in Image and Signal Processing from Université Grenoble Alpes in 2019. He obtained an MSc degree in Machine Learning and Data Mining in 2016 through a joint programme between Université Jean Monnet, Saint Étienne and the University of Alicante, Spain. He previously earned a Bachelor of Engineering degree in Biomedical. He then worked at LS2N laboratory, École Centrale de Nantes, as a Postdoctoral Researcher for nearly two years, focusing on medical image analysis and developing weakly supervised deep learning based methods. In 2021, he joined Grenoble INP, where he is currently an Associate Professor at the National School of Physics, Electronics and Materials, Phelma. He is also a permanent research member of the PICSA team within the Data Science Department at Gipsa Lab.
Dawood Al Chanti received the Doctor of Philosophy, PhD degree in Image and Signal Processing from Université Grenoble Alpes in 2019. He obtained an MSc degree in Machine Learning and Data Mining in 2016 through a joint programme between Université Jean Monnet, Saint Étienne and the University of Alicante, Spain. He previously earned a Bachelor of Engineering degree in Biomedical. He then worked at LS2N laboratory, École Centrale de Nantes, as a Postdoctoral Researcher for nearly two years, focusing on medical image analysis and developing weakly supervised deep learning based methods. In 2021, he joined Grenoble INP, where he is currently an Associate Professor at the National School of Physics, Electronics and Materials, Phelma. He is also a permanent research member of the PICSA team within the Data Science Department at Gipsa Lab.
His research lies at the intersection of computer vision and machine learning for medical image understanding, with particular emphasis on anomaly detection, uncertainty aware segmentation, multimodal fusion, and explainable AI for high stakes clinical and industrial applications. He supervises doctoral research in collaboration with university hospitals and industrial partners, with the aim of accelerating the transfer of reliable vision technologies into real world deployment. He is an IEEE Fellow and regularly contributes to the community through programme committee service and peer review for leading journals and conferences, including IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Medical Imaging, IEEE Transactions on Biomedical Engineering, IEEE Transactions on Affective Computing, IEEE Transactions on Image Processing, Pattern Recognition, Medical Image Analysis, and Artificial Intelligence in Medicine, as well as conferences such as IEEE WCCI, IPCAI, MICCAI, and CVPR. He also serves as an expert reviewer for funding proposals for the French National Research Agency, ANR. At Phelma, he is responsible for advanced courses taught in English across the BIOMED, SICOM, and Daleth programmes, covering image and video analysis, hardware accelerated deep learning, medical image processing, machine learning fundamentals, and artificial intelligence. He also coordinates enterprise relations for final year SICOM students, strengthening collaboration between academia and industry through internships and joint projects.
His research lies at the intersection of computer vision and machine learning for medical image understanding, with particular emphasis on anomaly detection, uncertainty aware segmentation, multimodal fusion, and explainable AI for high stakes clinical and industrial applications. He supervises doctoral research in collaboration with university hospitals and industrial partners, with the aim of accelerating the transfer of reliable vision technologies into real world deployment. He is an IEEE Fellow and regularly contributes to the community through programme committee service and peer review for leading journals and conferences, including IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Medical Imaging, IEEE Transactions on Biomedical Engineering, IEEE Transactions on Affective Computing, IEEE Transactions on Image Processing, Pattern Recognition, Medical Image Analysis, and Artificial Intelligence in Medicine, as well as conferences such as IEEE WCCI, IPCAI, MICCAI, and CVPR. He also serves as an expert reviewer for funding proposals for the French National Research Agency, ANR. At Phelma, he is responsible for advanced courses taught in English across the BIOMED, SICOM, and Daleth programmes, covering image and video analysis, hardware accelerated deep learning, medical image processing, machine learning fundamentals, and artificial intelligence. He also coordinates enterprise relations for final year SICOM students, strengthening collaboration between academia and industry through internships and joint projects.
Research Interest & Fields of Experties
Research Interest & Fields of Experties
- Computer Vision (Anomaly detection, Semantic segmentation, Localization, Classification).
- Uncertainty Quantification and Explainable Analysis in Deep Learning.
- Deep Learning Strategies: (Semi Supervised Learning, Self-Supervised, Few-Shot Learning).
- Active Learning ( Smart data selection, Exploration and Exploitation).
- Medical Image Analysis and Applications: Segmentation, Pathology detection and localization, Volume Quantifications.
- Hybrid AI: blending physical models and big data.
Teaching Responsibilities:
Teaching Responsibilities:
Image, vidéo et vision par ordinateur (3A/M2 SICOM, S9, 5PMSIVV3)
Projet d'apprentissage profond - Accélération Matérielle (3A/M2 SICOM, S9, 5PMSPAM1)
Introduction to Machine learning and Deep learning (3A/M2 BIOMED, S9,5PMBMLD0)
Traitement de l'image (M1 Daleth, S8, VPMDIPR1)
Dynamic System Analysis (M1 Daleth, S8, VPMDDSA2)
Traitement d'images et applications médicales (2A/M1 BIOMED, S8, 4PMBIPM9)
Traitement d'image avancé (2A/M1 SICOM, S8, 4PMSTIA5)
Introduction à l'intelligence artificielle (2A/M1 SICOM, S7, 4PMSIIA4)
Pedagogical Responsability:
Pedagogical Responsability:
Chargé des Relations Entreprises de la filière 3A SICOM / Correspondance Relations Entreprises 3A SICOM
NEWS!
NEWS!
11 February 2026: Project SAFE-Med: Sensitivity Aware Fragility and Explainability for Medical imaging AI, under my lead, got selected for International Research Booster 2026, in partnership with UiT The Arctic University of Norway in Tromsø, and the Bio AI Lab, to advance trustworthy and explainable AI for medical imaging.
19 January 2025: Publishd Journal Article entitled: "Trust but Verify, Image Aware Evaluation of Radiology Report Generators", Journal: Machine Learning with Applications (Elsevier). https://doi.org/10.1016/j.mlwa.2026.100851
16 December 2025: Dr. Sayeh Gholipour Picha, under my supervision, successfully defend her dissertation at Université Grenoble Alpes, and graduate with the PhD, specialty Artificial Intelligence and Computer Vision.
6-9 October 2025: Within the framework of the UNITE! European University collaboration, I have been invited to Aalto University as a visiting researcher and lecturer to present my ongoing project on AI Explainable Fragility, fostering interdisciplinary dialogue and advancing innovation in education and research and to collaborate on building collaborative courses with other EU universities.
26 September 2025: SpinePredict project got accepted! It is a La Région funded collaboration between Gipsa-lab and SQI that advances decision support in spine surgery. As the scientific leader of the project, i will lead the designs multimodal AI that fuses consultation notes, pre operative images, and dynamic posture measures to suggest optimal curvature correction.
July 2025: Dawood Al Chanti has been awarded an ANR JCJC grant for EQUR-XSM (Evidential Quantification of Uncertainty for Reliability in XAI Saliency Maps). The project will develop evidential deep learning methods to calibrate model uncertainty, produce trustworthy saliency explanations, and extend them to multimodal medical image segmentation in collaboration with LS2N (Centrale Nantes) and clinical partners.
June 2025: A new journal paper titled "VICCA: Visual Interpretation and Comprehension of Chest X-ray Anomalies in Generated Report Without Human Feedback" has been published in Machine Learning with Applications. The study introduces VICCA, a novel framework enabling interpretable analysis of chest X-ray anomalies directly from generated reports, without relying on human feedback. The work addresses the challenge of visual grounding in automated radiology reporting and offers a promising step forward in explainable AI for medical imaging. https://doi.org/10.1016/j.mlwa.2025.100684
May 2025: A new book chapter titled "An Introduction to Artificial Intelligence in Medicine and Its Role in Oral Potentially Malignant Disorders (OPMD)" has been published. The chapter provides a foundational overview of artificial intelligence in the medical domain, with a focus on its applications for early detection, diagnosis, and management of OPMDs. It highlights the potential of AI to enhance clinical decision-making and improve patient outcomes in oral healthcare.
March 2024: The conference paper "Semantic Textual Similarity Assessment in Chest X-ray Reports Using a Domain-Specific Cosine-Based Metric" by S. Gholipour Picha, D. Chanti, and A. Caplier was presented at the 17th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOINFORMATICS 2024). The study proposes a domain-specific cosine-based metric tailored to assess semantic similarity in chest X-ray radiology reports. The work was recognized with the Best Poster Award. https://doi.org/10.5220/0012429600003657
Page updated
Google Sites
Report abuse