Commit
•
880bb40
1
Parent(s):
9436e9a
Update README.md
Browse files
README.md
CHANGED
@@ -12,13 +12,13 @@ widget:
|
|
12 |
---
|
13 |
# Model Card for PubMedCLIP
|
14 |
|
15 |
-
PubMedCLIP is a fine-tuned version of [CLIP](https://huggingface.co/
|
16 |
image–text pairs obtained from [PubMed](https://pubmed.ncbi.nlm.nih.gov/) articles.
|
17 |
|
18 |
## Model Details
|
19 |
PubMedCLIP was trained on the [Radiology Objects in COntext (ROCO)](https://link.springer.com/chapter/10.1007/978-3-030-01364-6_20) dataset, which provides
|
20 |
-
over 80,000 samples including diverse imaging modalities (
|
21 |
-
captured from PubMed articles.
|
22 |
|
23 |
### Model Description
|
24 |
<!-- Provide a longer summary of what this model is. -->
|
|
|
12 |
---
|
13 |
# Model Card for PubMedCLIP
|
14 |
|
15 |
+
PubMedCLIP is a fine-tuned version of [CLIP](https://huggingface.co/docs/transformers/model_doc/clip) for the medical domain trained on a large number of medical
|
16 |
image–text pairs obtained from [PubMed](https://pubmed.ncbi.nlm.nih.gov/) articles.
|
17 |
|
18 |
## Model Details
|
19 |
PubMedCLIP was trained on the [Radiology Objects in COntext (ROCO)](https://link.springer.com/chapter/10.1007/978-3-030-01364-6_20) dataset, which provides
|
20 |
+
over 80,000 samples including diverse imaging modalities (such as ultrasound, X-Ray, MRI, etc.) from various human body regions (such as head, neck, spine, etc.)
|
21 |
+
captured from PubMed articles. The texts used for training were taken from the short captions (average length of 20 words) associated with images in the articles.
|
22 |
|
23 |
### Model Description
|
24 |
<!-- Provide a longer summary of what this model is. -->
|