Start here

A practical advanced guide for technically experienced readers — software/data/ML engineers, technically minded clinicians, researchers crossing from another quantitative field, healthcare-IT professionals — moving into medical imaging → quantitative imaging / radiomics → clinically rigorous ML → imaging informatics → medical imaging AI. It assumes you can code; it does not re-teach Python, Git, or basic ML, and it does not assume prior mastery of DICOM, radiomics, or imaging physics. The common requirement is willingness to work at technical depth.

The book follows the path from scanner and DICOM through geometry, quantitative measurement, modelling, evidence, and clinical deployment. Read it in sequence for the full argument, or enter through the chapter that matches your question.

Where to begin reading

This is a book, not a gated sequence. The chapter map below gives the overall route; the overview pages and cross-links provide a way to move through a topic at the depth you need.

• Starting with imaging fundamentals? Begin with CT image formation/reconstruction.
• Focusing on quantitative reliability? Read physical geometry/segmentation/resampling.
• Reading a paper critically? Start with the Tran et al. dissection.
• Looking for MRI foundations? Begin with MRI signal/contrast/reconstruction.

The chapters at a glance

Each chapter has an overview that introduces its argument and points to deeper sections, references, and companion material. This is a reading map, not a mandatory linear pipeline: informatics supports data handling across stages; AI may contribute to reconstruction, segmentation, or analysis; geometry and measurement checks can require revisiting earlier choices. The 3D Slicer companion supports visual inspection of images, geometry, and segmentations.

#	Chapter	Entry point
1	CT image formation/reconstruction	CT foundations
2	MRI signal/contrast/reconstruction	MRI foundations
3	DICOM objects/identity/stored meaning	DICOM meaning
4	physical geometry/segmentation/resampling	Spatial correctness
5	quantitative measurement	Measurement foundations
6	radiomics as measurement	Feature meaning
7	statistical learning / validation	Model evaluation
8	medical imaging AI	Imaging AI systems
9	evidence/claims	Evidence and inference
10	imaging informatics	Information systems
11	clinical deployment	Real-world use

Read the chapters in this order for a coherent path, or use the entry points to move directly to a problem. Optional self-checks and hands-on activities are invitations to test understanding, not gates to the material.

How does TRACE-CT fit in?

TRACE-CT is the practical laboratory: a real project whose DICOM, radiomics and validation work is first-class learning material here. Many sections end with a TRACE-CT connection — a real script or dataset that makes the concept concrete. Treat it as worked examples and an evidence-generating project, not a gate.

Where to find things

• A paper → literature map.
• A standard, tool, or reporting framework → standards & reference.
• Curated video/courses → courses & videos.
• TRACE-CT worked examples → TRACE-CT learning map.
• 3D Slicer, hands-on → visual QC as complementary evidence.
• Conference notes → EuSoMII 2026.