Update app.py

app.py

@@ -4,10 +4,6 @@ from PIL import Image
 import os
 from typing import Tuple, Optional
 import logging
-import numpy as np
-from skimage import filters, morphology, measure, segmentation, color
-import matplotlib.pyplot as plt
-from io import BytesIO
 
 # Configure logging
 logging.basicConfig(level=logging.INFO)
@@ -115,48 +111,6 @@ Follow the structure below:
             logger.error(f"Analysis failed: {str(e)}")
             return None, None
 
-    def segment_image(self, img: Image.Image) -> Tuple[Optional[Image.Image], Optional[Image.Image]]:
-        """
-        Segment the MRI scan using open-source scikit-image algorithms.
-        Returns a tuple of (segmentation_mask, labeled_image) if successful.
-        """
-        try:
-            # Convert PIL Image to numpy array
-            img_array = np.array(img.convert('L'))  # Convert to grayscale
-            
-            # Apply threshold using Otsu's method
-            threshold = filters.threshold_otsu(img_array)
-            binary = img_array > threshold
-            
-            # Clean up binary image
-            binary = morphology.remove_small_objects(binary, min_size=50)
-            binary = morphology.remove_small_holes(binary, area_threshold=50)
-            
-            # Optional: Apply watershed for better segmentation
-            distance = morphology.distance_transform_edt(binary)
-            local_max = filters.rank.local_max(distance, morphology.disk(5))
-            markers = measure.label(local_max)
-            labels = segmentation.watershed(-distance, markers, mask=binary)
-            
-            # Generate labeled image
-            label_rgb = color.label2rgb(labels, bg_label=0)
-            
-            # Create contour overlay on original image
-            contours = segmentation.find_boundaries(labels, mode='thick')
-            contour_overlay = np.copy(img_array)
-            contour_overlay[contours] = 255
-            
-            # Convert numpy arrays back to PIL Images
-            mask_img = Image.fromarray((binary * 255).astype(np.uint8))
-            label_img = Image.fromarray((label_rgb * 255).astype(np.uint8))
-            contour_img = Image.fromarray(contour_overlay.astype(np.uint8))
-            
-            return mask_img, contour_img
-            
-        except Exception as e:
-            logger.error(f"Segmentation failed: {str(e)}")
-            return None, None
-
     def run(self):
         """Run the Streamlit MRI scan analysis application."""
         st.title("🧠 MRI Scan Analytics")
@@ -171,8 +125,6 @@ Follow the structure below:
         with col2:
             if uploaded_file:
                 self.process_analysis(uploaded_file)
-                st.markdown("---")
-                self.process_segmentation(uploaded_file)
             else:
                 self.show_instructions()
 
@@ -220,36 +172,6 @@ Follow the structure below:
                 else:
                     st.error("Analysis failed. Please try again.")
 
-    def process_segmentation(self, uploaded_file: object) -> None:
-        """Process the uploaded MRI image and display the segmentation results."""
-        if st.button("🔍 Segment MRI Scan", key="segment_button"):
-            with st.spinner("Segmenting MRI scan using open-source algorithms..."):
-                img = Image.open(uploaded_file)
-                seg_mask, seg_contours = self.segment_image(img)
-                
-                if seg_mask and seg_contours:
-                    col1, col2 = st.columns(2)
-                    with col1:
-                        st.image(seg_mask, caption="Binary Segmentation Mask", use_container_width=True)
-                    with col2:
-                        st.image(seg_contours, caption="Region Contours", use_container_width=True)
-                        
-                    with st.expander("Segmentation Details"):
-                        st.markdown("""
-                            ### Segmentation Methodology
-                            
-                            This segmentation uses a pipeline of open-source algorithms:
-                            
-                            1. **Otsu Thresholding**: Automatically determines optimal threshold value
-                            2. **Morphological Operations**: Removes small objects and fills holes
-                            3. **Watershed Transform**: Separates connected regions
-                            4. **Boundary Detection**: Identifies region boundaries
-                            
-                            For medical diagnosis, these results should be reviewed by a qualified professional.
-                        """)
-                else:
-                    st.error("Segmentation failed. Please try again with a clearer image.")
-
     @staticmethod
     def show_instructions() -> None:
         """Display instructions when no image is uploaded."""
@@ -259,7 +181,6 @@ Follow the structure below:
             st.markdown("""
                 1. *Upload* your MRI scan image.
                 2. Click *Analyze MRI Scan* to get analysis reports for medical professionals and patients.
-                3. Click *Segment MRI Scan* to view the segmentation results using open-source algorithms.
             """)
 
     @staticmethod