VISION

Open neurosurgery, end-to-end. For every brain.

The case for an open, federated infrastructure across neurosurgical disease — and the principles we will not negotiate while building it.

manifestoprinciplespilot
I · The argument

The brain deserves open infrastructure.

Neurosurgical disease is rare, severe and lifelong. No single hospital sees enough cases to be self-sufficient. AURORA is the answer to that, written out plainly.

  1. 01
    Neurosurgical disease is rare, severe, and lifelong. No single hospital sees enough cases to be self-sufficient — yet the field acts as if each one could be.
  2. 02
    Closed clinical AI compounds the mistake. Models trained on one population, validated in one room, deployed behind one paywall, audited by no one.
  3. 03
    AURORA is the alternative. One open substrate per disease, federated across hospitals, governed by a public council, and re-runnable from a single command.
  4. 04
    We are not selling a product. We are seeding an infrastructure — so that twenty years from now, the questions that take a career to answer take a quarter.
II · Principles

Six commitments. Non-negotiable.

01

Open by default

MIT at public alpha. No CLA. Every model card, every benchmark, every endpoint published with the code that produced it.

02

Federation, not extraction

Patient data does not leave the institution. AURORA federates compute to data, never the other way around.

03

Reproducible or it didn't happen

Pinned weights, pinned containers, pinned data hashes. Every result can be re-run from a single command.

04

Mechanism + learning

Foundation models are powerful and brittle. Mechanistic simulators are robust and blind. AURORA fuses both, deliberately.

05

Equity is a feature

Bias and equity checks run inside the training loop, not on a slide deck after release.

06

The clinician is the override

Every recommendation explains itself. Every override is logged. AURORA augments judgement; it never replaces it.

III · The horizon

From 8 modules to the whole field.

AURORA's first eight modules were chosen because they together span the disease landscape: oncology, congenital, biomechanical, fluid-dynamic, vascular-adjacent, and developmental. The next eight are already drafted as RFCs.

The pilot is intentionally narrow. The horizon is not. Once the architecture proves itself across eight diseases of profoundly different character, the cost of adding the ninth, the twentieth and the fortieth drops with every iteration. The point of AURORA is not the modules we ship — it is the modules we make possible.

Some of what is next on the council's table:

  • Meningioma — molecular subtyping and recurrence forecasting on open data.
  • Chiari malformation — CSF mechanics, posterior fossa morphometry and decompression decisions.
  • Trigeminal neuralgia — vascular conflict imaging and microvascular decompression planning.
  • Pediatric epilepsy — focus localization and SEEG planning.
  • Spinal cord injury — acute trajectory and long-term rehabilitation modeling.
  • Cavernous malformations — natural history priors and resection thresholds.
  • Aneurysm — rupture risk, follow-up cadence, treatment selection.
  • Cerebral palsy / spasticity — selective dorsal rhizotomy planning and gait outcomes.
We are not building a product. We are seeding an infrastructure — so that twenty years from now, the questions that take a career to answer take a quarter.
Changelogv0.6.0