Update README.md

README.md

@@ -10,7 +10,7 @@ Paper accepted for [MIDL](https://www.midl.io/) 2025 : [arXiv submission](https:
 
 The CT-Scroll architecture consists of three main components. (1) Axial slices of the volume are grouped into triplets and processed by a ResNet followed by a GAP layer, producing a vector representation per triplet. (2) The Scrolling Block then refines these embedded visual tokens using both global and local attention mechanisms. (3) Finally, the aggregated representations are fed into a classification head to predict anomalies.
 
-<img src="./figures/method_overview.jpg" width="1000">
+<img src="./figures/method_overview.png" width="1000">
 
 ## Clone the Repository
 
@@ -22,7 +22,7 @@ git clone https://huggingface.co/theodp/ct-scroll
 
 ## Code repository
 
-The project source code can be found [here](https://github.com/theodpzz/ct-agrg).
+The project source code can be found [here](https://github.com/theodpzz/ct-scroll).
 
 ## Acknowledgments