Ashwin Kumar
commited on
Commit
Β·
f1ecfbe
1
Parent(s):
daf825e
updatd readme
Browse files
README.md
CHANGED
|
@@ -4,3 +4,47 @@ license: mit
|
|
| 4 |
|
| 5 |
# Merlin: Vision Language Foundation Model for 3D Computed Tomography
|
| 6 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
|
| 5 |
# Merlin: Vision Language Foundation Model for 3D Computed Tomography
|
| 6 |
|
| 7 |
+
[](https://arxiv.org/abs/2406.06512) [](https://pypi.org/project/merlin-vlm/)
|
| 8 |
+
|
| 9 |
+
Merlin is a 3D VLM for computed tomography that leverages both structured electronic health records (EHR) and unstructured radiology reports for pretraining.
|
| 10 |
+
|
| 11 |
+
[[π» Github](https://github.com/StanfordMIMI/Merlin)]
|
| 12 |
+
|
| 13 |
+
## β‘οΈ Installation
|
| 14 |
+
|
| 15 |
+
To install Merlin, you can simply run:
|
| 16 |
+
|
| 17 |
+
```python
|
| 18 |
+
pip install merlin-vlm
|
| 19 |
+
```
|
| 20 |
+
|
| 21 |
+
For an editable installation, use the following commands to clone and install this repository.
|
| 22 |
+
```bash
|
| 23 |
+
git clone https://github.com/StanfordMIMI/Merlin.git
|
| 24 |
+
cd merlin
|
| 25 |
+
pip install -e .
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
+
For usage instructions, please visit the github [repository](https://github.com/StanfordMIMI/Merlin).
|
| 29 |
+
|
| 30 |
+
### π Project Structure:
|
| 31 |
+
|
| 32 |
+
```
|
| 33 |
+
.
|
| 34 |
+
βββ README.md
|
| 35 |
+
βββ i3_resnet_clinical_longformer_best_clip_04-02-2024_23-21-36_epoch_99.pt <Merlin weights>
|
| 36 |
+
βββ image1.nii.gz <Sample Image>
|
| 37 |
+
```
|
| 38 |
+
|
| 39 |
+
## π Citation
|
| 40 |
+
If you find this repository useful for your work, please cite the cite the [original paper](https://arxiv.org/abs/2406.06512):
|
| 41 |
+
|
| 42 |
+
```bibtex
|
| 43 |
+
@article{blankemeier2024merlin,
|
| 44 |
+
title={Merlin: A vision language foundation model for 3d computed tomography},
|
| 45 |
+
author={Blankemeier, Louis and Cohen, Joseph Paul and Kumar, Ashwin and Van Veen, Dave and Gardezi, Syed Jamal Safdar and Paschali, Magdalini and Chen, Zhihong and Delbrouck, Jean-Benoit and Reis, Eduardo and Truyts, Cesar and others},
|
| 46 |
+
journal={Research Square},
|
| 47 |
+
pages={rs--3},
|
| 48 |
+
year={2024}
|
| 49 |
+
}
|
| 50 |
+
```
|