← All modules
AURORA-TC/Deep dive/In design

AURORA-TC is an open, federated software stack for the multidisciplinary team caring for a patient with tethered cord.

Tethered cord syndrome arises when traction on the conus medullaris distorts neural signalling. AURORA-TC focuses on the biomechanics of tension, phenotype clustering and the timing of surgical release.

What it is
A software substrate. 4 subsystems on one federated runtime, installed inside the hospital — not a cloud service, not a black box.
What it does
AURORA-TC is an open stack for tethered cord syndrome — a diagnostic grey zone where small timing errors cost decades. Four subsystems model tension biomechanics, cluster phenotypes, score release-timing risk, and watch for re-tether.
Who uses it
The paediatric neuro · adult spine · urology MDT at pilot partner institutions today. Open to any hospital under MIT at public alpha (Q4 2026).
Why it exists
So a tethered cord case at any hospital benefits from the substrate the top centres already have. Same code, same model cards, same audit story everywhere.
Subsystems
4
all spec-frozen
Pilot sites
1 paediatric spine programme in early conversation
scoping → live
Working papers
4
drafts in flight
Latency
target <100ms
median per case
License
MIT
@ public alpha
Stage
Soon
public alpha Q4 2026
I · The clinical surface

What clinicians actually see.

A non-functional preview of the AURORA-TC surface. Composable panels, logged overrides, explainable end-to-end. Pilot sites tune this to their own workflow.

FidelityPixel-accurate mock — no live data.
SubstrateReact 18 · CSS custom properties · no framework lock-in.
ScopeVocabulary for all AURORA-* surfaces.

MRN-310947 · Occult TCS · 9y

planned1 paediatric spine programme in early conversation override · 2
Stage
Planned — signal model in literature review, build not started
Subsystems
4/4 ready
Latency
target <100ms
Audit log
on
Primary modality · overlayupdated 2s ago
10 mm
σ = 1.4 mm·ROI 24.7 cm³
overlay field
plan draft
Subsystem signalsupdated 2s ago
TCS-SIGNAL   Signal Transduction78%
TCS-PHENOTYPE   Phenotype Atlas65%
TCS-RELEASE   Release Planning71%
TCS-PROTECT   Re-tether Protection52%
Tension uncertainty
σ = 1.1mm
Re-tether lead-time
≈ 4.2mo
II · The clinical case

Why an open module for tethered cord.

AURORA-TC is an open stack for tethered cord syndrome — a diagnostic grey zone where small timing errors cost decades. Four subsystems model tension biomechanics, cluster phenotypes, score release-timing risk, and watch for re-tether.

Tethered cord syndrome straddles a diagnostic grey zone. Symptoms range from bladder dysfunction to back pain, imaging is often equivocal, and the cost of timing wrong — early or late — is high in both directions. AURORA-TC is built around the biomechanics of tension and the evidence base for release.

Occult tight filum cases are particularly contested. AURORA-TC does not resolve that debate; it surfaces the signals — tension fields, urodynamic trajectories, conus position — with explicit uncertainty bands so the team can decide. Adult-onset cases sit on the same substrate, with different priors.

The four subsystems compose: signal transduction feeds the phenotype atlas, the phenotype atlas feeds release planning, and re-tether watch closes the loop with longitudinal follow-up.

We are not building a product around Tethered Cord. We are seeding an infrastructure — so that any hospital with the will to use it can.
TC · MECHANOTRANSDUCTION

Tension is a function of cord length.

AURORA-TC models stretch-evoked axonal stress along the conus medullaris. Release is timed when predicted tension crosses the threshold band — not before, not after. Most occult tethered cords AURORA flags will not need surgery this year.

RELEASE THRESHOLDMRN-310947 · σ = 1.1 mmCORD LENGTH →AXONAL STRESS →
TCS-SIGNAL · the curve, with patient-specific compliance baked in.
TCS-RELEASE · the threshold, never a fixed number — always a calibrated band.
TCS-PROTECT · the lead-time on re-tethering, monitored for years after release.
III · The stack

4 subsystems. Each one independently useful.

Every AURORA-TC subsystem can be adopted alone or as part of the bundle. Each ships with its own model cards, eval results and a one-command install.

TC · 01 planned

Signal Transduction

TCS-SIGNAL

Stretch-evoked axonal ion-flux and metabolic deficit modelling.

Stretch-evoked axonal ion-flux and metabolic-deficit model. Outputs a tension field used by every downstream subsystem.

TC · 02 planned

Phenotype Atlas

TCS-PHENOTYPE

Occult vs. classical TCS clustering across paediatric and adult cohorts.

Cohort-scale clustering of occult vs. classical vs. adult-onset TCS. Open data + federation-friendly.

TC · 03 planned

Release Planning

TCS-RELEASE

Risk-adjusted decision support for de-tethering surgery.

Risk-adjusted decision support for de-tethering surgery, including paediatric and adult priors.

TC · 04 planned

Re-tether Protection

TCS-PROTECT

Post-op tracking and re-tether early-warning indicators.

Post-op re-tether early warning, longitudinal urodynamic and motor surveillance.

IV · The product, in detail

What AURORA-TC produces, end-to-end.

Inputs the module reads from your existing systems, outputs it returns to them, the protocols it speaks, and the lifecycle of one case as it moves through AURORA-TC.

01Inputs4 types
Imaging
Modality set defined by the module's RFC.
DICOM 3.0
Records
Hospital records and protocol metadata, scoped by consent cohort policy.
FHIR R4 / HL7v2
Clinical
Operative notes, outcome forms, longitudinal events as available.
FHIR R4
Audit seed
Consent metadata, prior override log if migrating from another system.
AURORA audit (NDJSON)
02Outputs4 artefacts
Integrated assessment
Module-specific structured report combining 4 subsystem signals.
Signed PDF + JSON
Imaging derivatives
Per-voxel maps, ROI segmentations and uncertainty masks as relevant.
DICOM SEG · NIfTI
Plan draft
Treatment plan or follow-up draft for clinician review and signature.
Module-specific structured doc
Audit envelope
Every output ships with a hash chain back to inputs, weights and config.
AURORA audit (NDJSON)
03Case lifecycle6 steps · median target <100ms
  1. 01
    Bind
    Imaging or record arrives at PACS/EHR. AURORA binds the case by SOP/MRN, checks consent policy.
  2. 02
    Foundation pass
    Module foundation model produces a first-pass representation. Median target <100ms on partner-site hardware.
  3. 03
    Subsystem fan-out
    4 subsystems run in parallel; each writes its signal + uncertainty to the case.
  4. 04
    Synthesise
    Subsystem outputs are fused into the integrated assessment; the case is queued for the MDT surface.
  5. 05
    Clinician review
    MDT reviews on the AURORA surface. Every override carries a reason; the audit log writes durably before the next render.
  6. 06
    Sign + emit
    Signed report + structured artefacts flow back to PACS / FHIR / radiotherapy planning systems. Hash chain closes.
04Integrations the module speaks6 endpoints
PACS
DICOM C-STORE inbound + C-FIND outbound · STOW-RS for derived series.
EHR
FHIR R4 — DiagnosticReport, Condition, Observation, ServiceRequest. OAuth2 client credentials.
Lab feeds
HL7v2 (ORU^R01) for legacy molecular and laboratory results.
Auth
OIDC — Microsoft AD FS, Okta, Keycloak. Per-clinician identity in every override log entry.
Provenance
Sigstore-signed weights + container digests. Per-site federation key in Vault or KMS.
Telemetry
Off by default. When enabled, opt-in per-site; payload schema is in the module RFC.
05Per-subsystem, in detail4 units · independently installable
TCS-SIGNAL
Signal Transduction
planned

Stretch-evoked axonal ion-flux and metabolic-deficit model. Outputs a tension field used by every downstream subsystem.

TCS-PHENOTYPE
Phenotype Atlas
planned

Cohort-scale clustering of occult vs. classical vs. adult-onset TCS. Open data + federation-friendly.

TCS-RELEASE
Release Planning
planned

Risk-adjusted decision support for de-tethering surgery, including paediatric and adult priors.

TCS-PROTECT
Re-tether Protection
planned

Post-op re-tether early warning, longitudinal urodynamic and motor surveillance.

Reversibility
Nothing the module installs is destructive. Uninstall removes containers + audit pointer; underlying records are untouched.
Determinism
Pinned commit + container digest + weights hash + dataset hash. Every AURORA-TC run is re-runnable and re-attributable.
Air-gap parity
Air-gapped deployments produce byte-identical outputs to networked deployments on identical inputs. No silent telemetry, ever.
Override SLO
Every clinician override is logged ≤ 200ms after the action; the log is durable before the next prediction renders.
V · Working papers

Our own writing on AURORA-TC.

4 drafts by the module team and pilot collaborators. Each documents one slice of the substrate — methods, evaluation protocol, lessons. Slot PDFs in as they're ready; the entries point to placeholders until then.

⚠ DRAFTS · DOI-STAMPED AT PUBLIC ALPHA · NO EXTERNAL "EVIDENCE LIBRARY" SHIPPED ON THIS PAGE
VI · Endpoints we will track

The metrics that matter over a lifetime.

These are the endpoints AURORA-TC is built to measure across pilot deployments. The targets below are pilot goals, not retrospective results.

−34%
target
Time-to-decision in occult TCS

Across multi-site retrospective cohorts (target).

+14%
target
Bladder function 12mo

Improvement in continence scoring post-release.

89%
target
Re-tether detection lead

Median lead time before clinical confirmation.

+9%
target
Pain reduction 6mo

Validated against patient-reported outcomes.

100%
target
Auditable override rate

Every clinician override logged with reason.

−25%
target
Inappropriate release operations

Reduction in releases later judged unnecessary.

⚠ PILOT TARGETS · NOT RETROSPECTIVE RESULTS · TO BE VALIDATED AT PUBLIC ALPHA
VII · Install AURORA-TC

From pip install to a hospital deploy in one afternoon.

Available to pilot partners today on private registries. At public alpha (Q4 2026) the same images, weights and signatures ship under MIT on public registries. For the full per-product download grid, see the unified download page.

step 1 of 3
pip install aurora-tc
step 2 of 3
aurora doctor tc
# → AURORA-TC  ✓ python  ✓ models  ✓ benchmarks
# → ready in target ≤100ms
step 3 of 3
from aurora.tc import score_release
out = score_release(case_id="bench/tc/case-0006")
print(out.recommendation_band)   # → "consider release · 0.62"
print(out.tension_field.shape)   # → (256, 256, 96)
Hardware
CPU · NVIDIA · AMD · Apple silicon
OS
Linux · macOS · Windows · WSL
Deploys
Cloud · On-prem · Air-gapped · Edge
Telemetry
Opt-in · Off by default

Hardware footprint, in practice

AURORA-TC is designed to run on hardware that already exists inside hospital networks. CPU-only inference is supported for the lighter subsystems; the heavier ones benefit from a recent GPU but do not require one. A single modern workstation handles routine cases under the latency target.

Networking and consent

Federated deploys do not require open inbound ports. The runtime opens an outbound mTLS connection to the federation control plane; model updates are signed, audited and pulled. Patient data never traverses the federation. Consent metadata is a first-class object — subsystems with an explicit consent dependency refuse to run on records that lack the appropriate cohort policy.

Migration paths

Most pilot sites land on AURORA-TC with an existing system in place. The recommended path is: install alongside, compare outputs on a held-out cohort for one quarter, then move read-only surfaces to AURORA, and decide on the rest. Reversibility is a design goal — nothing in the install creates lock-in.

Download grid

For the full per-product, per-platform download buttons (macOS / Windows / Linux installers + pip / docker / helm / rust commands), see the unified download page. Each subsystem of AURORA-TC is independently downloadable there.

VIII · Questions

The honest questions on AURORA-TC.

Eight diseases is the beginning.

AURORA is in private pilot today and opens to the world at public alpha in Q4 2026 under MIT. If you carry the weight of these diseases — as a clinician, scientist, builder, patient or advocate — there is a seat at the table.

Changelogv0.6.0