AI and computer vision expert (PhD) with 7+ years of experience developing deep learning pipelines for image recognition, 3D reconstruction, and multimodal data fusion. Designed and deployed object detection and classification algorithms using transformer-based and self-supervised models, and has extensive experience processing 3D point cloud data, multimodal imaging (MRI, CT, endoscopy), and video streams for real-time analysis. Worked on projects requiring precise spatial mapping, feature extraction, and attribute analysis, integrating video, sensor, and imaging data across heterogeneous formats. Proficient in Python, PyTorch, TensorFlow, and OpenCV, specializing in building reproducible pipelines that bridge high-resolution data processing with accurate, production-ready outputs.…

Yasmina Al

AI and computer vision expert (PhD) with 7+ years of experience developing deep learning pipelines for image recognition, 3D reconstruction, and multimodal data fusion. Designed and deployed object detection and classification algorithms using transformer-based and self-supervised models, and has extensive experience processing 3D point cloud data, multimodal imaging (MRI, CT, endoscopy), and video streams for real-time analysis. Worked on projects requiring precise spatial mapping, feature extraction, and attribute analysis, integrating video, sensor, and imaging data across heterogeneous formats. Proficient in Python, PyTorch, TensorFlow, and OpenCV, specializing in building reproducible pipelines that bridge high-resolution data processing with accurate, production-ready outputs.…

Available to hire

AI and computer vision expert (PhD) with 7+ years of experience developing deep learning pipelines for image recognition, 3D reconstruction, and multimodal data fusion. Designed and deployed object detection and classification algorithms using transformer-based and self-supervised models, and has extensive experience processing 3D point cloud data, multimodal imaging (MRI, CT, endoscopy), and video streams for real-time analysis. Worked on projects requiring precise spatial mapping, feature extraction, and attribute analysis, integrating video, sensor, and imaging data across heterogeneous formats. Proficient in Python, PyTorch, TensorFlow, and OpenCV, specializing in building reproducible pipelines that bridge high-resolution data processing with accurate, production-ready outputs.

See more

Skills

Language

English
Fluent
Croatian
Fluent
German
Beginner

Work Experience

Postdoctoral researcher in medical imaging / surgical AI at Eindhoven University of Technology
September 1, 2023 - Present
- Designed and deployed a real-time anatomical structure recognition pipeline on da Vinci surgical videos (30 fps), using transformer-based and self-supervised models with 15% accuracy gain over CNN baselines. - Led the development of CT-to-video registration and SLAM-based 3D surgical field reconstruction methods using monocular and stereoscopic endoscopic input, incorporating intrinsic and extrinsic camera calibration to derive depth maps and enable sub-millimeter 3D intraoperative guidance.

Education

Doctor of philosophy, PhD at Eindhoven University of Technology
October 1, 2018 - August 1, 2023

Qualifications

Add your qualifications or awards here.

Skills