Improve model card and add metadata

README.md

@@ -1,5 +1,6 @@
 ---
 license: cc-by-nc-nd-4.0
+pipeline_tag: image-feature-extraction
 tags:
 - medical-imaging
 - ct
@@ -9,9 +10,16 @@ tags:
 
 # FlexiCT
 
-FlexiCT is a CT foundation model family trained through agglomerative continual pretraining from 2D slice-level anatomy to 3D volumetric reasoning and report-aligned vision-language understanding.
+FlexiCT is a CT foundation model family trained through agglomerative continual pretraining, progressing from 2D slice-level anatomy to 3D volumetric reasoning and report-aligned vision-language understanding.
 
-This family page links three child repos:
+The models were presented in the paper [Universal CT Representations from Anatomy to Disease Phenotype through Agglomerative Pretraining](https://huggingface.co/papers/2605.21906).
+
+- **Project Page:** [https://ricklisz.github.io/flexict.github.io](https://ricklisz.github.io/flexict.github.io)
+- **GitHub Repository:** [https://github.com/ricklisz/FlexiCT](https://github.com/ricklisz/FlexiCT)
+
+## Model Family
+
+This family page links three child repositories:
 
 | Repo | Input | Output | Recommended use |
 |---|---|---|---|
@@ -19,6 +27,17 @@ This family page links three child repos:
 | `ricklisz/FlexiCT-3D` | `[B, 1, 160, 160, 160]` CT volumes | CLS and patch tokens | Whole-volume feature extraction and downstream 3D workflows |
 | `ricklisz/FlexiCT-3D-VLM` | CT volumes plus text | Image/text embeddings and similarity scores | Report-aligned retrieval and zero-shot text-image scoring |
 
+## Sample Usage
+
+To use the models, you can follow the installation instructions in the [GitHub repository](https://github.com/ricklisz/FlexiCT). Once installed, you can load a model as follows:
+
+```python
+from flexi_ct import Flexi_CT_3D
+
+# Pass a checkpoint path when constructing a model
+model = Flexi_CT_3D(checkpoint_path="/path/to/ct_3d_teacher.pth")
+```
+
 ## Preprocessing presets
 
 `default` is recommended for whole-volume 3D and 3D-VLM inference. It orients/resamples path inputs to LPS at 2 mm spacing when spacing is available, clips HU to `[-1000, 1000]`, z-score normalizes, pads with the tensor minimum to at least `160^3`, then center crops to `160^3`. This best matches the released VLM evaluation path because it preserves physical scale better than globally resizing the anatomy.
@@ -48,4 +67,4 @@ The released checkpoints are made available under the Creative Commons Attributi
 
 ## Medical disclaimer
 
-FlexiCT is for research use only. It is not a medical device and is not a substitute for professional medical judgment.
+FlexiCT is for research use only. It is not a medical device and is not a substitute for professional medical judgment.