Convert NII to AI

Technical note

What changes when you convert NII to AI

The standard NII header has no fields for a patient's name, birth date or accession number, only an 80-character free-text description, which is one reason research pipelines convert DICOM to NIfTI before data is shared. That does not make every output anonymous. A head scan contains the face, and a 3D rendering of the volume can reconstruct it well enough to recognise someone, which is why public datasets are usually defaced first. Slices that pass through the front of the head carry the same risk. A line in a NII image is several pixels wide, so tracing it can mean different things and the mode is yours to choose. Centreline returns a single line running down the middle of each stroke, which is what a scanned drawing needs: one entity per line, snappable and dimensionable, rather than a long thin rectangle around it. Outline follows both edges and returns closed shapes, which suits clipart, logos and anything that will be filled or cut. A precision setting controls how closely the traced paths follow the pixel edges. One thing to plan for: vectorised output from this path is black and white, so colour in the NII does not survive as colour in the AI.