Step 1 · Data

What are you working on today, Dr. Chen?

Drop a labeled dataset — we'll handle the rest. No code. No config files. No DevOps.

Drop DICOM / NIfTI / CSV folder here

or browse your files

HIPAA / BAA covered Never leaves your environment

or start from a sample:

Step 2 · Task

What kind of model?

Pick the task that best matches your clinical question. You can change this later.

Step 3 · Configure

Smart configuration

Clique analyzed your dataset and hardware. Here's what it chose.

"Clique auto-configures every pipeline to the hardware you have — not the hardware you wish you had."

Why this configuration? Auditable decision tree · nnU-Net-inspired

Every choice below is driven by two things the platform already measured for you — the dataset fingerprint and the available hardware. No manual guessing. Every decision is logged and reproducible.

1 Is the dataset 3D or 2D?

3D — 100 CT volumes, median shape 512×512×220.

→ Picks a volumetric architecture family (UNet3D) over 2D slice-wise baselines.
2 Is the dataset large enough for the full nnU-Net?

No — 100 cases is below the 200-case threshold (heuristic H-3).

→ Downgrades to the UNet3D-small variant to avoid over-parameterization.
3 What batch size fits in available VRAM?

Batch = 2 — solved from 24 GB A100 VRAM minus ~3.1 GB headroom at median shape.

→ Keeps gradient accumulation off the critical path; no OOM at epoch 0.
4 Is mixed-precision safe for this task?

Yes — segmentation on CT + A100 = ~2.1× speedup, <0.1% Dice impact in published benchmarks.

→ Enables Mixed FP16 by default; falls back to FP32 automatically if NaN losses are detected.
5 Which augmentation policy?

Elastic + intensity jitter — small 3D CT dataset, single modality.

→ Matches nnU-Net's default 3D CT policy. Skips color / mixup (not meaningful on CT).
6 How to validate?

5-fold CV — because N < 200 and we want a variance estimate for the handoff report.

→ Single-split would be misleading at this sample size.

Every branch of this tree is recorded in the audit log with the dataset hash, hardware ID, and resolved value — so IT and compliance can reproduce the run on demand.

Architecture

UNet3D-small

Lightweight 3D variant optimized for a 100-case training set.

Batch size

2

Fits comfortably in 24GB GPU with 3.1GB headroom.

Precision

Mixed FP16

2.1× speedup vs FP32, <0.1% accuracy impact.

Augmentation

Elastic + intensity jitter

Standard for 3D CT with small training sets.

Validation split

5-fold cross-validation

Recommended for datasets < 200 cases.

Estimated runtime

4 h 12 min

On 1× NVIDIA A100 (detected in your cluster).

Advanced options Researchers only — clinicians can safely ignore.

Learning rate Weight decay Epochs Optimizer LR scheduler Seed

We'll provision a container and stream progress below.

Step 3.5 · Train

Training in progress

Container auto-spun-up. You can close this tab — we'll email you when it's done.

"Container spun up in 4.8s. Will shut down automatically when training completes — you only pay for what you use."

Configuring

Container provisioned · image: clique-runner:v4.2
Training

Epoch 0 / 250 · loss: — · val dice: —
Validating

5-fold cross-validation
Exporting

ONNX + versioned artifact
Released

Available in Model Registry

Loss & validation dice

Train loss Val dice

GPU util

0%

Power

0 W

Elapsed

00:00

ETA

—

Live log clique-runner:v4.2

Step 4 · Deploy

Your model is ready

Review the artifact, hand it to IT, or deploy it yourself — with every step audited.

pneumonia-seg-v1

Trained from chest-ct-100cases.zip · moments ago

Ready to deploy

Sensitivity

0.932

Specificity

0.908

AUC

0.961

Val Dice

0.891

Artifact

148 MB · ONNX

SHA-256

a7f4c2…e9b1

Lab book

Recent experiments

Every experiment is a container in some stage of its lifecycle — configured, trained, validated, exported, released, or archived.

Name	Task	State	Dataset	GPU-hours	Accuracy	Updated