m

app.py

@@ -8,6 +8,10 @@ import streamlit as st
 from PIL import Image
 import io
 import zipfile
+import pandas as pd
+from datetime import datetime
+import os
+import tempfile
 
 # --- GlaucomaModel Class ---
 class GlaucomaModel(object):
@@ -108,6 +112,73 @@ def get_confidence_level(confidence):
     else:
         return "Very Low"
 
+def process_batch(model, images_data, progress_bar=None):
+    results = []
+    for idx, (file_name, image) in enumerate(images_data):
+        try:
+            disease_idx, disc_cup_image, vcdr, cls_conf, cup_conf, disc_conf, cropped_image = model.process(image)
+            results.append({
+                'file_name': file_name,
+                'diagnosis': model.cls_id2label[disease_idx],
+                'confidence': cls_conf,
+                'vcdr': vcdr,
+                'cup_conf': cup_conf,
+                'disc_conf': disc_conf,
+                'processed_image': disc_cup_image,
+                'cropped_image': cropped_image
+            })
+            if progress_bar:
+                progress_bar.progress((idx + 1) / len(images_data))
+        except Exception as e:
+            st.error(f"Error processing {file_name}: {str(e)}")
+    return results
+
+def save_results(results, original_images):
+    # Create temporary directory for results
+    with tempfile.TemporaryDirectory() as temp_dir:
+        # Save report as CSV
+        df = pd.DataFrame([{
+            'File': r['file_name'],
+            'Diagnosis': r['diagnosis'],
+            'Confidence (%)': f"{r['confidence']:.1f}",
+            'VCDR': f"{r['vcdr']:.3f}",
+            'Cup Confidence (%)': f"{r['cup_conf']:.1f}",
+            'Disc Confidence (%)': f"{r['disc_conf']:.1f}"
+        } for r in results])
+        
+        report_path = os.path.join(temp_dir, 'report.csv')
+        df.to_csv(report_path, index=False)
+        
+        # Save processed images
+        for result, orig_img in zip(results, original_images):
+            img_name = result['file_name']
+            base_name = os.path.splitext(img_name)[0]
+            
+            # Save original
+            orig_path = os.path.join(temp_dir, f"{base_name}_original.jpg")
+            Image.fromarray(orig_img).save(orig_path)
+            
+            # Save segmentation
+            seg_path = os.path.join(temp_dir, f"{base_name}_segmentation.jpg")
+            Image.fromarray(result['processed_image']).save(seg_path)
+            
+            # Save ROI
+            roi_path = os.path.join(temp_dir, f"{base_name}_roi.jpg")
+            Image.fromarray(result['cropped_image']).save(roi_path)
+        
+        # Create ZIP file
+        zip_path = os.path.join(temp_dir, 'results.zip')
+        with zipfile.ZipFile(zip_path, 'w') as zipf:
+            for root, _, files in os.walk(temp_dir):
+                for file in files:
+                    if file != 'results.zip':
+                        file_path = os.path.join(root, file)
+                        arcname = os.path.basename(file_path)
+                        zipf.write(file_path, arcname)
+        
+        with open(zip_path, 'rb') as f:
+            return f.read()
+
 # --- Streamlit Interface ---
 def main():
     st.set_page_config(layout="wide", page_title="Glaucoma Screening Tool")
@@ -132,63 +203,54 @@ def main():
         help="Images with confidence above this threshold will be marked as reliable predictions")
     
     if uploaded_files:
-        for uploaded_file in uploaded_files:
-            image = Image.open(uploaded_file).convert('RGB')
-            image_np = np.array(image).astype(np.uint8)
+        st.markdown("## 📊 Batch Analysis Results")
+        
+        # Initialize model once for all images
+        model = GlaucomaModel(device=torch.device("cuda:0" if torch.cuda.is_available() else "cpu"))
+        
+        # Prepare images data
+        images_data = []
+        original_images = []
+        for file in uploaded_files:
+            try:
+                image = Image.open(file).convert('RGB')
+                image_np = np.array(image)
+                images_data.append((file.name, image_np))
+                original_images.append(image_np)
+            except Exception as e:
+                st.error(f"Error loading {file.name}: {str(e)}")
+                continue
+        
+        progress_bar = st.progress(0)
+        st.write(f"Processing {len(images_data)} images...")
+        
+        # Process all images
+        results = process_batch(model, images_data, progress_bar)
+        
+        if results:
+            # Generate ZIP with results
+            zip_data = save_results(results, original_images)
             
-            st.markdown(f"## 📊 Analysis Results: {uploaded_file.name}")
+            # Download button for ZIP
+            st.download_button(
+                label="📥 Download All Results",
+                data=zip_data,
+                file_name=f"glaucoma_screening_{datetime.now().strftime('%Y%m%d_%H%M%S')}.zip",
+                mime="application/zip"
+            )
             
-            with st.spinner(f'🔄 Processing {uploaded_file.name}...'):
-                model = GlaucomaModel(device=torch.device("cuda:0" if torch.cuda.is_available() else "cpu"))
-                disease_idx, disc_cup_image, vcdr, cls_conf, cup_conf, disc_conf, cropped_image = model.process(image_np)
-                
-                # Image display section
-                st.subheader("Original Image")
-                st.image(image_np, use_column_width=True)
-                st.subheader("Segmentation Overlay")
-                st.image(disc_cup_image, use_column_width=True)
-                st.subheader("Region of Interest")
-                st.image(cropped_image, use_column_width=True)
-                
-                st.markdown("---")
-                
-                # Classification Results
-                st.markdown("### 🔍 Classification")
-                diagnosis = model.cls_id2label[disease_idx]
-                is_confident = cls_conf >= confidence_threshold
-                
-                if diagnosis == "Glaucoma":
-                    st.markdown(f"<div style='padding: 10px; background-color: #ffebee; border-radius: 5px;'>"
-                              f"<h4 style='color: #c62828;'>Diagnosis: {diagnosis}</h4></div>", 
-                              unsafe_allow_html=True)
-                else:
-                    st.markdown(f"<div style='padding: 10px; background-color: #e8f5e9; border-radius: 5px;'>"
-                              f"<h4 style='color: #2e7d32;'>Diagnosis: {diagnosis}</h4></div>", 
-                              unsafe_allow_html=True)
-                
-                st.write(f"Classification Confidence: {cls_conf:.1f}%")
-                if not is_confident:
-                    st.warning("⚠️ Below confidence threshold")
-                
-                # Segmentation Results
-                st.markdown("### 🎯 Segmentation Quality")
-                st.write(f"Optic Cup Confidence: {cup_conf:.1f}%")
-                st.write(f"Optic Disc Confidence: {disc_conf:.1f}%")
-                
-                cup_level = get_confidence_level(cup_conf)
-                disc_level = get_confidence_level(disc_conf)
-                st.info(f"Cup Detection: {cup_level}\nDisc Detection: {disc_level}")
-                
-                # Clinical Metrics
-                st.markdown("### 📏 Clinical Metrics")
-                st.write(f"Cup-to-Disc Ratio (CDR): {vcdr:.3f}")
-                
-                if vcdr > 0.7:
-                    st.warning("⚠️ Elevated CDR (>0.7)")
-                elif vcdr > 0.5:
-                    st.info("ℹ️ Borderline CDR (0.5-0.7)")
-                else:
-                    st.success("✅ Normal CDR (<0.5)")
-                
-                st.markdown("---")
-# ... rest of the code remains the same ...
+            # Display results
+            for result in results:
+                with st.expander(f"Results for {result['file_name']}"):
+                    cols = st.columns(3)
+                    with cols[0]:
+                        st.image(result['processed_image'], caption="Segmentation", use_column_width=True)
+                    with cols[1]:
+                        st.image(result['cropped_image'], caption="ROI", use_column_width=True)
+                    with cols[2]:
+                        st.write("### Metrics")
+                        st.write(f"Diagnosis: {result['diagnosis']}")
+                        st.write(f"Confidence: {result['confidence']:.1f}%")
+                        st.write(f"VCDR: {result['vcdr']:.3f}")
+                        st.write(f"Cup Confidence: {result['cup_conf']:.1f}%")
+                        st.write(f"Disc Confidence: {result['disc_conf']:.1f}%")