Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
A 3D segmentation model for detecting papyrus sheet surfaces in micro-CT scans of the Herculaneum scrolls, trained for the Vesuvius Challenge Surface Detection competition on Kaggle.
Model source
Source description
A 3D segmentation model for detecting papyrus sheet surfaces in micro-CT scans of the Herculaneum scrolls, trained for the Vesuvius Challenge Surface Detection competition on Kaggle.
This model uses nnU-Net v2, the self-configuring deep learning framework for biomedical image segmentation. nnU-Net automatically determines the optimal network architecture, preprocessing, and training strategy from the dataset properties.
Sources
1 sourceVerified Sep 27
Model artifacts
2 artifactsSource excerpts
2 excerptsThe model segments 3D micro-CT volumes into three classes:
| Component | Value |
|---|---|
| Network | PlainConvUNet (3D) |
| Stages | 6 |
| Features per stage | [32, 64, 128, 256, 320, 320] |
| Conv op | Conv3d (3×3×3 kernels) |
| Normalization | InstanceNorm3d |
| Activation | LeakyReLU (inplace) |
| Deep supervision | Yes |
| Patch size | 128 × 128 × 128 |
| Batch size | 2 |
| Parameters | ~31M |
| Detail | Value |
|---|---|
| Dataset | Dataset011_Vesuvius (786 training volumes) |
| Epochs | 200 |
| Iterations/epoch | 250 (train), 50 (val) |
| Optimizer | SGD (lr=0.01, momentum=0.99, nesterov=True, weight_decay=3e-5) |
| LR schedule | PolyLR (200 epochs) |
| Loss | Dice + Cross-Entropy with Deep Supervision |
| Normalization | CT Normalization (dataset-level statistics) |
| Foreground oversampling | 33% |
| Mixed precision | Yes (AMP with GradScaler) |
| torch.compile | Yes |
| Hardware | NVIDIA A10G (AWS g5.xlarge) |
| Metric | Value |
|---|---|
| Best EMA pseudo Dice | 0.4676 (epoch 194) |
| Best val loss | 0.3518 (epoch 187) |
| Final train loss | 0.4127 |
| Final val loss | 0.4274 |
| Submission | Post-Processing | Public LB | Private LB |
|---|---|---|---|
| V2 pipeline (best) | 1st-place post-proc | 0.433 | 0.449 |
Note: The Kaggle submission used our V2 pipeline model (custom UNet3D), not this nnU-Net model directly. This nnU-Net model is intended for future ensemble submissions and as a standalone alternative.
The Vesuvius Challenge Surface Detection dataset consists of 3D micro-CT scans of carbonized papyrus scrolls from Herculaneum, buried by the eruption of Mount Vesuvius in 79 AD.
26002| Stat | Value |
|---|---|
| Mean | 87.5 |
| Median | 81.0 |
| Std | 47.7 |
| Min/Max | 0 / 255 |
| 0.5th/99.5th percentile | 0 / 212 |
pip install nnunetv2 torch
from huggingface_hub import snapshot_download
# Download model
model_dir = snapshot_download("bshepp/vesuvius-nnunet-model")
# Set nnU-Net environment variables
import os
os.environ["nnUNet_results"] = model_dir
# Run prediction using nnU-Net CLI
# nnUNetv2_predict -i INPUT_FOLDER -o OUTPUT_FOLDER -d 011 -c 3d_fullres -tr nnUNetTrainer_200epochs -f all
import torch
checkpoint = torch.load("checkpoint_best.pth", map_location="cpu")
# checkpoint contains: network_weights, optimizer_state, epoch, etc.
| File | Description | Size |
|---|---|---|
fold_all/checkpoint_best.pth | Best model weights (EMA pseudo Dice) | 238 MB |
fold_all/checkpoint_final.pth | Final epoch (200) weights | 238 MB |
plans.json | nnU-Net experiment plan (architecture, preprocessing) | 20 KB |
dataset.json | Dataset configuration (channels, labels) | <1 KB |
dataset_fingerprint.json | Dataset statistics | 110 KB |
fold_all/training_log_*.txt | Full training log (200 epochs) | 80 KB |
fold_all/progress.png | Training curves plot | 880 KB |
For best results, apply the 1st-place post-processing pipeline after inference:
binary_fill_holesSee 1st place writeup for details.
If you use this model, please cite nnU-Net:
@article{isensee2021nnu,
title={nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation},
author={Isensee, Fabian and Jaeger, Paul F and Kohl, Simon AA and Petersen, Jens and Maier-Hein, Klaus H},
journal={Nature methods},
volume={18},
number={2},
pages={203--211},
year={2021},
publisher={Nature Publishing Group}
}
MIT
Brian Sheppard (@bshepp)
--- license: mit tags: - nnunet - 3d-segmentation - medical-imaging - micro-ct - surface-detection - vesuvius-challenge - pytorch datasets: - vesuvius-challenge-surface-detection pipeline_tag: image-segmentation library_name: nnunetv2 --- # Vesuvius Challenge — nnU-Net Surface Detection Model A 3D segmentation model for detecting papyrus sheet surfaces in micro-CT scans of the Herculaneum scrolls, trained for the [Vesuvius Challenge Surface Detection](https://www.kaggle.com/competitions/vesuvius-challenge-surface-detection) competition on Kaggle. ## Model Description This model uses [nnU-Net v2](https://github.com/MIC-DKFZ/nnUNet), the self-configuring deep learning framework for biomedical image segmentation. nnU-Net automatically determines the optimal network architecture, preprocessing, and training strategy from the dataset properties. The model segments 3D micro-CT volumes into three classes: - **Background** (0) — empty space / non-papyrus - **Surface** (1) — the outer surface of the papyrus sheet - **Interior** (2) — the interior of the papyrus sheet ### Architecture | Component | Value | |-----------|-------| | **Network** | PlainConvUNet (3D) | | **Stages** | 6 | | **Features per stage** | [32, 64, 128, 256, 320, 320] | | **Conv op** | Conv3d (3×3×3 kernels) | | **Normalization** | InstanceNorm3d | | **Activation** | LeakyReLU (inplace) | | **Deep supervision** | Yes | | **Patch size** | 128 × 128 × 128 | | **Batch size** | 2 | | **Parameters** | ~31M | ### Training Details | Detail | Value | |--------|-------| | **Dataset** | Dataset011_Vesuvius (786 training volumes) | | **Epochs** | 200 | | **Iterations/epoch** | 250 (train), 50 (val) | | **Optimizer** | SGD (lr=0.01, momentum=0.99, nesterov=True, weight_decay=3e-5) | | **LR schedule** | PolyLR (200 epochs) | | **Loss** | Dice + Cross-Entropy with Deep Supervision | | **Normalization** | CT Normalization (dataset-level statistics) | | **Foreground oversampling** | 33% | | **Mixed precision** | Yes (AMP with GradScaler) | | **torch.compile** | Yes | | **Hardware** | NVIDIA A10G (AWS g5.xlarge) | | **Training time** | ~11.5 hours | | **Framework** | nnU-Net v2, PyTorch 2.10.0+cu128, CUDNN 9.1 | ### Training Metrics | Metric | Value | |--------|-------| | **Best EMA pseudo Dice** | 0.4676 (epoch 194) | | **Best val loss** | 0.3518 (...
Source context: 0 downloads · 0 likes · Pipeline image-segmentation · Library nnunetv2 · Repo bshepp/vesuvius-nnunet-model
| ~11.5 hours |
| Framework | nnU-Net v2, PyTorch 2.10.0+cu128, CUDNN 9.1 |
fold_all/debug.json| Debug/config snapshot |
| — |