Caner K.
Synthetic Medical Dataset (MedGym)
Experience
Jan 2024 - Dec 2024
1 yearMunich, Germany
Synthetic Medical Dataset (MedGym)
MEDTANK Corp.
- Generated synthetic datasets for CXR, mammography, and distal radius fracture detection using GANs and diffusion, creating >50k synthetic images for benchmarking.
- Ensured GDPR-compliant workflows and reproducibility, enabling dataset adoption for internal validation and academic collaboration.
- Project highlighted in MedTank’s internal R&D showcase as a flagship synthetic data initiative.
Jan 2024 - Dec 2024
1 yearMunich, Germany
Explainable AI for GANs
Technical University of Munich
- Implemented Saliency Maps, LIME, Shapley, and DeepLift with Captum to improve GAN transparency, making black-box generative models interpretable for medical AI researchers.
- Results presented in a departmental seminar, influencing adoption of explainability tools in ongoing research projects.
Jan 2023 - Dec 2025
3 yearsMunich, Germany
Machine Learning Engineer
MEDTANK Corp.
- Spearheaded development of GAN/diffusion pipelines on radiology datasets (>1M CXRs), boosting synthetic data diversity by 25% and reducing classifier overfitting in regulated medical imaging workflows.
- Optimized Stable Diffusion for chest X-rays, improving SSIM/PSNR by up to 12% and enabling clinically plausible outputs validated by radiologists.
- Designed preprocessing and 3D segmentation workflows (MONAI, SimpleITK), enabling automated anomaly detection and ROI extraction, later integrated into hospital PACS/RIS pipelines.
- Collaborated with cross-functional teams to ensure GDPR-compliant data handling and contributed to deployment of ML systems in production-grade healthcare environments.
Jan 2022 - Dec 2022
1 yearMunich, Germany
Data Science Intern
Data Glacier
- Built machine learning pipelines for predictive analytics on structured healthcare datasets, achieving a 15% improvement in model accuracy compared to baseline.
- Applied feature engineering and data visualization (Pandas, Scikit-learn, Matplotlib) to uncover actionable insights for business stakeholders.
- Deployed a proof-of-concept model to AWS, demonstrating scalability and integration into existing workflows.
Jan 2020 - Dec 2020
1 yearAnkara, Turkey
Freelance Web Developer
Asel Wire Industry
- Delivered responsive React.js web application with reusable UI components.
Jan 2019 - Dec 2019
1 yearAnkara, Turkey
Avionics Test Engineer Intern
ASELSAN A.S
- Built distributed tool for automated documentation, improving team efficiency.
Summary
Specialized in diffusion/GAN pipelines, GDPR-compliant data handling, and deployment of ML systems in regulated medical imaging workflows.
Thesis research on integrating Roentgen and MRM for synthetic radiology image generation.
Languages
Turkish
NativeEnglish
AdvancedGerman
ElementaryEducation
Oct 2021 - Jun 2025
Technical University of Munich
M.Sc. · Informatics · Munich, Germany
Oct 2016 - Jun 2020
Ankara University
B.Sc. · Computer Engineering · Ankara, Turkey
Need a freelancer? Find your match in seconds.
Try FRATCH GPT More actions
Similar Freelancers
Discover other experts with similar qualifications and experience
- English
- Deutsch
2025 © FRATCH.IO GmbH. All rights reserved.