---
license: cc-by-nc-sa-4.0
---

# FastGlioma: foundation models for fast, label-free detection of glioma infiltration

[**Paper**](https://www.nature.com/articles/s41586-024-08169-3) /
[**Interactive Demo**](https://fastglioma.mlins.org) /
[**GitHub**](https://github.com/MLNeurosurg/fastglioma) /
[**MLiNS Lab**](https://mlins.org)

Model card for our paper 'Foundation models for fast, label-free detection of glioma infiltration.' We employ a foundational model training strategy to predict the degree of diffuse glioma infiltration intraoperatively using stimulated Raman histology and deep learning.

## Model Details

* **Patch Encoder**: ResNet-34 (21.4M parameters). Batch size of 512 distributed over 4x Nvidia A40s for 800 epochs with the self-supervised hierarchical discriminative (HiDisc) objective, base learn rate was 0.001.
* **WSI Encoder, Foundation Model**: Transformer (6.6M parameters). Batch size of 256 with 1 Nvidia Titan V100 for 100 epochs with the self-supervised VICReg objective, base learn rate was 0.0003.
* **WSI Encoder, Supervised Finetuning**: Batch size of 16 with 1 Nvidia Titan V100 for 100 epochs with the supervised ordinal metric learning objective, base learn rate was 0.0000188.

Learn rate scheduler was cosine decay with 10% warmup for all stages. Mixed precision and data parallelism were used when applicable.

## Model Checkpoints

The checkpoints provided are designed to work with our [**inference package**](https://github.com/MLNeurosurg/fastglioma/tree/main/fastglioma/inference) on the [**OpenSRH dataset**](https://opensrh.mlins.org). Note that FastGlioma was only designed for patients with adult-type diffuse gliomas. Please refer [here](https://github.com/MLNeurosurg/fastglioma/tree/main?tab=readme-ov-file#intended-use) for an in-depth description on FastGlioma's intended use.

``fastglioma_highres_model.ckpt`` takes in **FullSRH images** (3 channels, no skipped rows) and has the best performance, whereas ``fastglioma_lowres_model.ckpt`` takes in **FastSRH images** (1 channel, every 5th row selected; >10x faster).

## License Information

FastGlioma models and the OpenSRH dataset are licensed under the CC-BY-NC-SA 4.0 License. The associated code, found in our GitHub repository, is licensed under the MIT License.