Bridging AI and science to transform research.

Key Work:

• Modular Registration Pipeline: Sequential composition of global rigid/affine alignment (Elastix RRA) followed by B-spline local deformations and VoxelMorph deep learning dense flow fields — coarse-to-fine refinement of extreme non-linear tissue deformations.
• Custom Evaluation Framework: Two novel tissue-based metrics beyond standard intensity measures — area-based (Dice, Jaccard, Hausdorff) and landmark-based (expert pathologist-annotated anatomical keypoints), yielding clinically meaningful spatial validation.
• Annotation Software: Built a side-by-side annotation tool for expert pathologists to manually define biologically relevant MRI–WSI landmark.

Impact:

• First modular MRI–WSI registration framework validated for ovarian cancer.
• Enables transfer of biological feature maps from invasive WSI to non-invasive MRI coordinate space.
• Foundation for future clinical virtual biopsy tools — reducing reliance on invasive tissue sampling.

Next: Complete landmark annotation for the full IRCM cohort; extend to clinical 3T whole-body MRI; explore Virtual Biopsy deep learning models for direct biological feature prediction from MRI.

Key Projects:

• HixLoop: Built a modular AI platform for object detection/segmentation in scientific images, cutting manual annotation effort by 80% and improving model precision to 98%. (FastAPI, PyTorch, Docker, Streamlit)
• Abbelight: Developed CNN models for super-resolution microscopy, boosting recall/precision by 15–20% and delivering a cross-platform pipeline. (PyTorch, MLflow, GPU optimization)
• Davele: Simulated solar panel shadows on crops to optimize agronomic layouts, enhancing light exposure predictions by 30%. (Python, Geometric Modeling)
• Aicet: Created an application to generate and validate AI certification questions, streamlining content creation by 50%. (Python, DevOps)
• Tools: Created GPUBalancer (GPU queue system), CIRToolbox (time-tracking with voice AI), and solar shadow simulators for agronomic research.

Skills:
AI/ML: PyTorch, TensorFlow, Keras, Detectron2
DevOps: Docker, FastAPI, GPU clusters
Collaboration: Git, Notion, Agile

Impact:

• Delivered 3 core platforms now used daily by BionomeeX and partners (IRCM, Abbelight).
• Set standards for modular AI pipelines and Docker-based deployment, reducing project time by 60%.
• Contributed to publication-ready tools for oncology and microscopy research.

Next: Applying this expertise in my PhD at IRCM, developing multi-modal AI for ovarian cancer detection.