AI-Powered Auto-Contouring Platform

Auto-contouring
that fits your
clinical pace.

Save hours of manual delineation per patient. Orcrist ContourOAI delivers GPU-accelerated auto-contouring across 225+ structures.

<3min*
Head & neck OARs
225+
Structures across
all model groups
Fast
GPU-accelerated inference
all treatment sites
BULK
Overnight batch processing
— upload & come back
<3
min H&N
Head & neck OARs completed in under 3 minutes. All other treatment sites at matching GPU-accelerated speed — so your team spends time on clinical decisions, not manual delineation.
~40 OAR structures
~14 H&N nodal levels
GPU Accelerated inference

* Under ideal conditions with a stable, low-latency network connection. Actual processing time may vary depending on network latency, image size, and server load.

What Orcrist ContourOAI Does

One unified
platform.

From automated contouring to fine-tuning, training, and deployment — every step integrated into a single workflow.

OAR structures
OAR Auto-Contouring
Deep learning segmentation across 225+ structures — from cranial and head & neck to thorax, abdomen, and pelvis. Every major treatment site, one platform.
  • Cranial & Brain structures
  • Head & Neck OARs — glands, vessels, muscles, bones
  • Thorax — lungs, heart, great vessels
  • Abdomen & Pelvis — organs, bowel, reproductive structures
  • Skeleton — vertebrae, ribs, sternum, pelvis, long bones
Deep Learning · 225+ Structures
Lymph node regions
Lymph Node Region Contouring
Atlas-consistent nodal volumes delineated automatically. Eliminates the most variable, time-intensive step in head & neck radiotherapy planning.
  • Bilateral Levels IA, IB, IIA, IIB, III, IV, VA, VB
  • Retropharyngeal and Level VI nodes
Head & Neck Coverage
Annotation and contouring
Contour Station: Annotation, Contouring & Fine Tuning
A cloud-based annotation workspace — used for three purposes in one tool: correcting AI-generated contours post auto-contouring, manual contouring from scratch, and creating high-quality training data for custom ML models.
  • Slice-by-slice brush and eraser correction of AI contours
  • Full manual contouring — draw any structure from scratch
  • Contour interpolation between manually edited slices
  • Structure addition, splitting, and merging tools
DUAL PURPOSE — ONE TOOL
The same annotation interface used clinically is also the training data creation tool — annotated cases flow directly into the custom ML training pipeline, eliminating any separate labelling workflow.
Cloud-Based · Post-AI Correction · Training Data
Clinician review
Mandatory Clinician Review Gate
No RT Struct leaves the platform without explicit clinician sign-off. The review gate is a hard architectural constraint — it cannot be bypassed — ensuring Orcrist ContourOAI operates strictly as a decision-support tool.
  • Per-structure approval workflow
  • Timestamped, identity-linked audit log
  • AI-generated vs. clinician-edited versions tracked
Regulatory-Grade Safety
Education & Training
Orcrist ContourOAI accelerates radiotherapy education for residents, fellows, and practising clinicians — providing AI-generated reference contours to compare against, critique, and correct, building contouring skills faster than manual-only workflows.
  • AI contour as a teaching baseline for residents
  • Side-by-side comparison: trainee vs. AI vs. consultant
  • Annotation tools for supervised correction exercises
  • Tracked edits support structured feedback sessions
Research & Clinical Studies
A complete research instrument — from DICOM ingestion to annotated dataset export. Supports prospective and retrospective clinical studies with full audit trails and DSC benchmarking built in.
  • Batch processing across large patient cohorts
  • DSC and volumetric metrics computed per structure
  • Export annotated datasets for publication or peer review
  • Anonymisation pipeline integrated end-to-end

Infrastructure & Security

Cloud-powered. On-prem secure.
Your data never leaves your control.

Orcrist ContourOAI runs as a cloud-based AI service, connected to your hospital via a secure on-premises DICOM gateway. Anonymisation happens before any data leaves your network — zero patient-identifiable data is retained in the cloud.

Hospital Infrastructure
Existing PACS, TPS, and imaging systems remain fully on-premises. No changes to clinical workflow.
PACS (Orthanc / Sectra / Synapse)
TPS (Eclipse / RayStation / Monaco)
CT / MRI modalities
DICOM
TLS 1.3
ON-PREMISES GATEWAY
Secure DICOM Gateway
Lightweight agent in your hospital network. Anonymises data, manages encrypted transfer, routes RT Structs back to PACS/TPS.
Anonymises before any cloud transfer
TLS 1.3 encrypted tunnel
DICOMweb STOW-RS / WADO-RS
Routes RT Struct back on completion
Anonymised
DICOM only
ORCRIST CLOUD
Orcrist ContourOAI Engine
GPU-accelerated deep learning inference. Anonymised DICOM in, RT Struct out. No patient data retained post-processing.
Deep learning GPU inference (<3 min)
Zero data retention post-inference
Region-appropriate cloud infrastructure
Your hospital perimeter
Anonymised CT → cloud
RT Struct ← returned
Orcrist cloud infrastructure
Patient data privacy
Patient Data Privacy
Full anonymisation before transfer. GDPR-compliant. Zero identifiable data retained post-processing.
Cloud data residency
Cloud Data Residency
Deploy on region-specific cloud infrastructure for data residency — EU, Mumbai, or Hyderabad regions based on your requirements.
No TPS plugin required
No TPS Plugin Required
Pure DICOMweb. Works with any DICOM-compatible PACS or TPS — no vendor agreements, no plugin installs.
Full on-prem option
Full On-Prem Option
For air-gapped environments, Orcrist ContourOAI deploys fully on-premises on hospital GPU servers. Same workflow, zero cloud dependency.

BATCH MODE

Upload tonight. Review in the morning.

Queue your entire day's caseload before you leave. Orcrist ContourOAI processes every CT scan, patient by patient, back to back — so your team arrives to a full set of ready-to-review contours.

  • Upload multiple DICOM series in a single batch
  • Queue processes automatically — no manual triggering per case
  • Morning review dashboard shows batch status at a glance
↑
8:00 PM — END OF DAY
Upload batch — example, 20 patients
Drag and drop DICOM series or connect via DICOMweb. Queue starts immediately.
Processing
8:00 PM → 9:00 PM
Orcrist ContourOAI processes queue
Each patient: OARs contoured in under 3 minutes. 20 cases ≈ 60 minutes.
✓
9:00 AM — NEXT MORNING
All 20 patients ready to review
Complete RT Structs delivered to TPS. Your team reviews, approves, and plans.

Custom ML Training

Train your own structures.
Even tumors.

ContourOAI is not a closed black box. Institutions can upload their own annotated datasets and fine-tune the model — adding custom structures, institutional protocols, or tumor contours specific to their patient population.

01
Annotate Your Data
Use Orcrist ContourOAI's built-in annotation tools to label your own CT cases. Any structure — from unusual OARs to GTV/CTV tumor volumes — can be annotated and curated as training data.
02
Train a Custom Model
Submit your annotated dataset to the Orcrist ContourOAI training pipeline. Models are fine-tuned on your institution's own cases, capturing your patient population, scanner protocols, and delineation style.
03
Deploy Your Model
Your custom model becomes available alongside the base OAR models. Select it at contouring time — it runs with the same speed and DICOMweb integration as the standard workflow.

Custom models are institution-private. Your training data never leaves your environment and is never used to train other customers' models.

Clinical Workflow

From CT to TPS in five steps.

Orcrist ContourOAI fits into your existing DICOM workflow — no new hardware, no TPS plugin, no disruption.

1
Upload CT
Send directly from your PACS, contour station, or TPS via DICOMweb — then import the resulting RT Struct files directly back into your system.
2
AI Contours
Deep learning generates OAR and lymph node contours in under 3 minutes.
3
Annotate & Edit
Clinician reviews, corrects, adds structures, or manually contours where needed.
4
Approve
Mandatory review gate: explicit structure-by-structure sign-off before export.
5
RT Struct to TPS
Approved contours delivered to Eclipse, RayStation, Monaco, or any DICOM-compatible TPS.

Structure Coverage

317+ structures.

Orcrist ContourOAI has been validated across 225+ structures spanning 10 model groups. A further 92+ structures across 16 groups are on the active testing and validation pipeline.

225+
Structures available
92+
Structures under testing
17
Model groups total
Available
Total Body (Torso) 117 structures
Lymph Nodes (Head & Neck) 20 levels
Head Glands & Cavities 19 structures
Head & Neck Muscles 23 structures
Head Muscles (Masticatory) 11 structures
Head & Neck Bones & Vessels 12 structures
Oculomotor Muscles 19 structures
Lung Vessels 2 structures
Body Trunk 2 structures
Under Testing & Validation
Brain Structures 16 structures
Heart Chambers 7 structures
Abdominal Muscles 22 structures
Thigh & Shoulder Muscles 18 structures
Appendicular Bones 11 structures
Craniofacial Structures 7 structures
Liver Segments 8 segments
Tissue Types 3 structures

Structure counts derived from model group definitions. Bilateral structures counted individually. Roadmap subject to change.