Mohamed Chetoui

Artificial Intelligence Scientist with 5+ years of experience in deep learning and machine learning across academic and industrial projects. Skilled in designing, developing, and deploying AI solutions with expertise in federated learning, computer vision, NLP, medical imaging, and robotics. Author of 20+ peer-reviewed publications, advancing methods in healthcare, robotics, and industrial AI. Passionate about developing scalable, real-world AI applications and driving innovation at the intersection of research and engineering.

[1] M. Chetoui and M. A. Akhloufi, “Stacking Ensemble Learning for Accurate Polyp Segmentation,” in Proc. 2025 6th Int. Conf. Bio-engineering for Smart Technologies (BioSMART), May 2025, pp. 1–5.

[2] M. Chetoui and M. A. Akhloufi, "A Novel Ensemble Meta-Model for Enhanced Retinal Blood Vessel Segmentation Using Deep Learning Architectures," Biomedicines, vol. 13, no. 1, p. 141, 2025.

[3] M. Chetoui and M. A. Akhloufi, "Fire and smoke detection using fine-tuned YOLOv8 and YOLOv7 deep models," Fire, vol. 7, no. 4, p. 135, 2024.

[4] M. Chetoui and M. A. Akhloufi, "Enhancing Fish Detection and Classification in Sonar Images Through Deep Learning," in OCEANS 2024-Halifax, IEEE, 2024.

[5] M. Chetoui and M. A. Akhloufi, ‘Peer-to-peer federated learning for COVID-19 detection using transformers’, Computers, vol. 12, no. 5, p. 106, 2023.

[6] M. Chetoui, M. A. Akhloufi, E. M. Bouattane, J. Abdulnour, S. Roux, and C. D. Bernard, ‘Explainable COVID-19 detection based on chest x-rays using an end-to-end RegNet architecture’, Viruses, vol. 15, no. 6, p. 1327, 2023.

[7] M. Chetoui and M. A. Akhloufi, ‘Object detection model-based quality inspection using a deep CNN’, in Sixteenth International Conference on Quality Control by Artificial Vision, 2023, vol. 12749, pp. 65–72.

[8] M. Chetoui and M. A. Akhloufi, ‘Federated Learning for Diabetic Retinopathy Detection Using Vision Transformers’, BioMedInformatics, vol. 3, no. 4, pp. 948–961, 2023.

[9] M. Chetoui and M. A. Akhloufi, ‘Explainable vision transformers and radiomics for covid-19 detection in chest x-rays’, Journal of Clinical Medicine, vol. 11, no. 11, p. 3013, 2022.

[10] M. Chetoui and M. A. Akhloufi, ‘Deep efficient neural networks for explainable COVID-19 detection on CXR images’, in International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, 2021, pp. 329–340.

[11] A. Traoré, M. Chetoui, F.-G. Landry, and M. A. Akhloufi, ‘Ensemble Learning Framework to Detect Partial Discharges and Predict Power Line Faults’, in 2021 IEEE Electrical Power and Energy Conference (EPEC), 2021, pp. 285–289.

[12] M. Chetoui, M. A. Akhloufi, B. Yousefi, and E. M. Bouattane, ‘Explainable COVID-19 detection on chest X-rays using an end-to-end deep convolutional neural network architecture’, Big Data and Cognitive Computing, vol. 5, no. 4, p. 73, 2021.

[13] M. Chetoui and M. A. Akhloufi, ‘Automated Detection of COVID-19 Cases using Recent Deep Convolutional Neural Networks and CT images’, in 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2021, pp. 3297–3300.

[14] M. Chetoui and M. A. Akhloufi, ‘Efficient deep neural network for an automated detection of COVID-19 using CT images’, in 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2021, pp. 1769–1774.

[15] M. Chetoui and M. A. Akhloufi, ‘Explainable end-to-end deep learning for diabetic retinopathy detection across multiple datasets’, Journal of Medical Imaging, vol. 7, no. 4, pp. 044503–044503, 2020.

[16] M. Chetoui and M. A. Akhloufi, ‘Deep retinal diseases detection and explainability using OCT images’, in International Conference on Image Analysis and Recognition, 2020, pp. 358–366.

[17] M. Chetoui, M. A. Akhloufi, and M. Kardouchi, ‘Diabetic retinopathy detection using machine learning and texture features’, in 2018 IEEE Canadian conference on electrical & computer engineering (CCECE), 2018, pp. 1–4.

• Lab2Market Validate Program (2024)
  Completed a 16-week entrepreneurship training designed for researchers to evaluate and validate the business potential of their ideas. Gained hands-on experience in market exploration, customer discovery, and business development, supported by industry mentorship, workshops, and funding opportunities. Developed entrepreneurial skills to bridge the gap between research and commercialization.
• LiDAR Processing & 3D Point Cloud Analysis – Université de Sherbrooke
  Completed specialized training on LiDAR principles, 3D imaging, and point cloud processing, including data acquisition, preprocessing, segmentation, and feature extraction for real-world applications in computer vision and robotics.

• AI System for Pulmonary Disease Detection (COVID-19)
  Developed in collaboration with Hôpital Montfort (Canada). Achieved 98% accuracy in detecting COVID-related pulmonary diseases from medical imaging. The system is currently under clinical testing.
• Diabetic Retinopathy & Macular Edema Detection
  Designed and deployed an AI-based system using fundus and OCT images, reaching 96% accuracy. Integrated into a web application and an Android mobile app for real-time medical diagnosis support.
• Robotic System for Automated Lobster Processing
  Developed an end-to-end solution for bin picking and pick-and-place using FANUC robotic arms, a Zivid 3D camera, and computer vision + deep learning algorithms. Enhanced automation for seafood industry processing.
• Super-Resolution Imaging Application
  Built a deep learning model capable of x8 image upscaling, improving resolution for medical and industrial imaging. Deployed as a standalone application with web interface.
• AI-Powered Forest Fire Detection System
  Designed and integrated a detection framework with 90% mAP performance, using satellite imagery and JSON annotations. Applied for early wildfire monitoring and environmental safety.
• Industrial Quality Control System
  Developed and deployed a computer vision application for detecting manufacturing defects (e.g., bent screws) with 95% accuracy. Integrated into industrial production lines for automated inspection.