Update app.py

app.py

@@ -214,63 +214,38 @@ def run_nnunet_predict(nifti_file):
     except subprocess.CalledProcessError as e:
         return f"Error: {e}"
 
-# Define the interface
-interface = gr.Interface(
-    fn=run_nnunet_predict,
-    inputs=[
-        gr.File(label="Upload FLAIR Image (.nii.gz)")
-    ],
-    outputs=[
-        gr.File(label="Download Segmentation Mask"),
-        gr.Image(label="Input: FLAIR image"),
-        gr.Image(label="Output: Lesion Mask")
-    ],
-    title="FLAMeS: Multiple Sclerosis Lesion Segmentation",
-    description="Upload a skull-stripped FLAIR image (.nii.gz) to generate a binary segmentation of multiple sclerosis lesions.",
-)
-
-# Markdown content as a string
-# Markdown content as a string
-markdown_content = """
-**If you find this tool useful, please consider citing:**
-
-1. A Deep Learning-Based Pipeline for Longitudinal White Matter Lesion Segmentation Using Diverse FLAIR Images  
-   F. La Rosa, J. Dos Santos Silva, W. A. Mullins, H. Greenspan, J. F. Sumowski, D. S. Reich, & E. S. Beck.  
-   *ACTRIMS Forum 2023 - Poster Presentations. Multiple Sclerosis Journal.* 2023;29(2_suppl):18-242.  
-   DOI: [10.1177/13524585231169437](https://doi.org/10.1177/13524585231169437)
-
-2. nnU-Net: A Self-Configuring Method for Deep Learning-Based Biomedical Image Segmentation  
-   F. Isensee, P. F. Jaeger, S. A. Kohl, J. Petersen, & K. H. Maier-Hein.  
-   *Nature Methods.* 2021;18(2):203-211.  
-   DOI: [10.1038/s41592-020-01008-z](https://www.nature.com/articles/s41592-020-01008-z)
-"""
-
-# Use Gradio Blocks for a clean layout
+# Gradio interface with adjusted layout
 with gr.Blocks() as demo:
-    # Title and Description
     gr.Markdown("""
     # FLAMeS: Multiple Sclerosis Lesion Segmentation
 
     Upload a skull-stripped FLAIR image (.nii.gz) to generate a binary segmentation of multiple sclerosis lesions.
     """)
-    
-    # Layout for Inputs and Outputs
+
     with gr.Row():
-        with gr.Column(scale=1):  # Input column
+        with gr.Column(scale=1):
             flair_input = gr.File(label="Upload FLAIR Image (.nii.gz)")
             submit_button = gr.Button("Submit")
-        with gr.Column(scale=2):  # Output column
+        with gr.Column(scale=2):
             seg_output = gr.File(label="Download Segmentation Mask")
             input_img = gr.Image(label="Input: FLAIR image")
             output_img = gr.Image(label="Output: Lesion Mask")
-    
-    # References
-    gr.Markdown(markdown_content)
 
-    # Link submit button to the function
+    gr.Markdown("""
+    **If you find this tool useful, please consider citing:**
+
+    1. A Deep Learning-Based Pipeline for Longitudinal White Matter Lesion Segmentation Using Diverse FLAIR Images  
+       F. La Rosa, J. Dos Santos Silva, et al.  
+       *Multiple Sclerosis Journal.* DOI: [10.1177/13524585231169437](https://doi.org/10.1177/13524585231169437)
+
+    2. nnU-Net: A Self-Configuring Method for Deep Learning-Based Biomedical Image Segmentation  
+       F. Isensee, et al.  
+       *Nature Methods.* DOI: [10.1038/s41592-020-01008-z](https://www.nature.com/articles/s41592-020-01008-z)
+    """)
+
     submit_button.click(
-        fn=run_nnunet_predict, 
-        inputs=[flair_input], 
+        fn=run_nnunet_predict,
+        inputs=[flair_input],
         outputs=[seg_output, input_img, output_img]
     )
 
@@ -279,8 +254,9 @@ if torch.cuda.is_available():
     print(f"GPU is available: {torch.cuda.get_device_name(0)}")
 else:
     print("No GPU available. Falling back to CPU.")
-    os.system("nvidia-smi")  # Check if NVIDIA tools are available
+    os.system("nvidia-smi")
+
+download_model()
 
-# Launch the app
 if __name__ == "__main__":
     demo.launch(share=True)