What If Your Medical AI Pipeline Could Evolve?

A patient needs a custom knee implant. The clinical workflow looks like this: acquire a CT scan, segment the femur and tibia, reconstruct full 3D bone geometry, extract 77 morphological parameters, and generate a patient-specific implant design. A team at Brest University Hospital recently automated this entire pipeline — from raw CT to finished implant CAD — in 15 minutes. That's impressive engineering. But look at the architecture: each step is hardcoded into the next. The segmentation model is welded to the reconstruction algorithm, which is welded to the parameter extractor. If a better segmentation model appears next month, swapping it in means rewriting integration code, re-validating the pipeline, and re-running regulatory checks. This is the static pipeline problem — and it exists far beyond medical imaging. Every AI system that chains models together faces it. The question is: what changes when you stop treating pipeline steps as code and start treating them as genes? Each Ste