Skip to content
Other

Aschoplex - precise choroid plexus segmentation in brain MRIs

2 min read

A tool for automated extraction and quantitative analysis of the choroid plexus (ChP) on 3D T1-weighted brain MRI scans. The model is built on an ensemble of five AI models (three DynUNet and two UNETR) using the MONAI framework. The solution was trained on data from the COMPASS-ND cohort for neurodegenerative disease research (including Alzheimer's and Parkinson's diseases). It helps researchers quickly obtain segmentation masks and evaluate choroid plexus volume in millimeters.

Key features

  • Model ensemble: a combination of DynUNet and UNETR architectures for more accurate prediction.
  • Volume estimation: calculation of choroid plexus volume in cubic millimeters and milliliters.
  • MONAI ecosystem: full integration with the PyTorch-based medical deep learning ecosystem.
  • Local execution: inference scripts for running on hardware with CUDA support.

What you can do

  • MRI analysis: run automated segmentation of 3D T1-weighted scans in NIfTI format.
  • Research: use for large-scale phenotyping of structural MRIs in Alzheimer's or Parkinson's disease.
  • Integration: set up a medical image processing pipeline in a research laboratory.

Example

Running the full model ensemble for inference:

python run_inference.py \
    --input /data/subject001.nii.gz \
    --output ./predictions
Read moreDetails
Requirements: Linux, GPU with CUDA (for example, RTX A6000), Python 3.9, PyTorch 1.13.1, MONAI 1.0.1.
Input data: 3D T1-weighted MRIs in NIfTI format.
Limitations: for research purposes only, CPU inference is not supported.
License: Apache-2.0.
Discuss Telegram 0

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 0.3 GB · ready files0.9 GB
  • FP8 / INT8recommendedweights 0.2 GB0.7 GB
  • 4-bitweights 0.1 GB0.6 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · BF16 — from RTX 2060

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # manisggn/Aschoplex_compassnd_chp_finetuned
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download manisggn/Aschoplex_compassnd_chp_finetuned --local-dir ~/models/Aschoplex_compassnd_chp_finetuned
    # The model is in ~/models. How to run it is in the model card (link above).
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of Aschoplex_compassnd_chp_finetuned (quants, finetunes, LoRAs) will show up under the bell.

No known relatives of this model yet. All derivatives on Hugging Face

About the model

manisggn/Aschoplex_compassnd_chp_finetuned
Author
manisggn
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

00

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments