Imaging Evidence Path

About this project

Imaging Evidence Path is an independent learning and research project by Adrian Tkacz, MD, MSc Computer Science. My background spans medicine, computer science, bioinformatics, healthcare IT and large-scale data platforms.

I created this guide while systematically rebuilding and deepening my own knowledge of medical imaging, quantitative imaging and radiomics. The aim is to connect imaging physics, DICOM, quantitative methods, statistical validation and clinical evidence into one technically rigorous path, grounded where possible in primary literature, reproducible examples and lessons from real research work.

About the author

Where to find things

• Literature map — the intellectual map of the literature (PMIDs/DOIs; PDFs live in Zotero).
• Courses & videos — selected external instruction, bridged not duplicated.
• Standards & reference — DICOM, SimpleITK, 3D Slicer, IBSI, PyRadiomics, CLAIM/TRIPOD+AI.
• TRACE-CT learning map — real worked examples from the driving laboratory.
• EuSoMII 2026 note — MSK and generalist imaging AI.

If you have 60 minutes tonight

Pick one: open a RIDER slice in pydicom and convert stored pixels to HU (Ch. 1); compute a real series’ slice normal (Ch. 4); continue the ISLP chapter (Ch. 7); or dissect Tran et al. through the research-methodology lens ([Ch. 9]). Depth over breadth.

This reader renders the repository’s canonical Markdown directly — it does not duplicate it. The source of truth is BioMedical-IT/imaging-evidence-path on Forgejo.