Update app.py

app.py

@@ -1,4 +1,13 @@
 import streamlit as st
+
+# ⚡️ Page config must be FIRST
+st.set_page_config(
+    page_title="Chest X-ray Disease Classifier",
+    page_icon="🩺",
+    layout="centered"
+)
+
+# Imports
 import torch
 import torch.nn as nn
 import torchvision.transforms as transforms
@@ -6,7 +15,7 @@ from efficientnet_pytorch import EfficientNet
 from PIL import Image
 from datetime import datetime
 
-# Define HardSwish activation
+# --- Define HardSwish activation ---
 class HardSwish(nn.Module):
     def __init__(self):
         super(HardSwish, self).__init__()
@@ -14,7 +23,7 @@ class HardSwish(nn.Module):
     def forward(self, x):
         return x * (torch.clamp(x + 3, 0, 6) / 6)
 
-# Define custom EfficientNet model
+# --- Define Custom EfficientNet model ---
 class CustomEfficientNet(nn.Module):
     def __init__(self, num_classes):
         super(CustomEfficientNet, self).__init__()
@@ -30,17 +39,17 @@ class CustomEfficientNet(nn.Module):
     def forward(self, x):
         return self.model(x)
 
-# Class names
+# Disease class labels
 class_names = [
     'No Finding', 'Enlarged Cardiomediastinum', 'Cardiomegaly', 'Lung Opacity',
     'Lung Lesion', 'Edema', 'Consolidation', 'Pneumonia', 'Atelectasis', 'Pneumothorax',
     'Pleural Effusion', 'Pleural Other', 'Fracture', 'Support Devices'
 ]
 
-# Device configuration
+# --- Device configuration ---
 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 
-# Load model
+# --- Load model ---
 @st.cache_resource
 def load_model():
     model = CustomEfficientNet(num_classes=14)
@@ -55,14 +64,14 @@ def load_model():
 
 model = load_model()
 
-# Transformations
+# --- Transformations ---
 transform = transforms.Compose([
     transforms.Resize((300, 300)),
     transforms.ToTensor(),
     transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
 ])
 
-# Prediction function
+# --- Prediction function ---
 def predict(image):
     if image.mode != 'RGB':
         image = image.convert('RGB')
@@ -74,45 +83,55 @@ def predict(image):
 
     results = {class_names[i]: float(probs[i]) for i in range(len(class_names))}
     sorted_results = dict(sorted(results.items(), key=lambda item: item[1], reverse=True))
-    top5 = {k: f"{v*100:.2f}%" for k, v in list(sorted_results.items())[:5]}
+    top5 = {k: v for k, v in list(sorted_results.items())[:5]}
 
     return top5
 
-# ---------------- Streamlit App -----------------
-
-st.set_page_config(page_title="Chest X-ray Disease Classifier", page_icon="🩺", layout="centered")
-
+# --- Streamlit UI ---
 st.markdown(
     """
-    <h1 style="text-align:center;">🩺 Chest X-ray Disease Classifier</h1>
-    <p style="text-align:center;">Upload a chest X-ray image to get disease predictions.</p>
+    <h1 style="text-align: center;">🩺 Chest X-ray Disease Classifier</h1>
+    <p style="text-align: center;">Upload a chest X-ray image to get disease predictions.<br>Top 5 diseases shown with probability scores.</p>
     """,
     unsafe_allow_html=True
 )
 
-# Input form
-with st.form("input_form"):
-    patient_name = st.text_input("Patient Name", placeholder="Enter full name...")
-    scan_date = st.date_input("Scan Date", value=datetime.today())
-    uploaded_file = st.file_uploader("Upload Chest X-ray Image", type=["png", "jpg", "jpeg", "bmp", "tiff"])
-    submitted = st.form_submit_button("🔍 Predict")
+st.write("")  # small space
+
+with st.form("prediction_form"):
+    patient_name = st.text_input("👤 Patient Name", placeholder="Enter patient's full name...")
+    scan_date = st.date_input("📅 Scan Date", value=datetime.today())
+    uploaded_file = st.file_uploader("📤 Upload Chest X-ray Image", type=["png", "jpg", "jpeg", "bmp", "tiff"])
 
-if submitted:
-    if uploaded_file is not None and patient_name:
+    submit_button = st.form_submit_button("🔍 Analyze X-ray")
+
+# Handle submission
+if submit_button:
+    if not uploaded_file:
+        st.error("⚠️ Please upload a chest X-ray image.")
+    elif not patient_name.strip():
+        st.error("⚠️ Please enter the patient's name.")
+    else:
         image = Image.open(uploaded_file)
 
-        with st.spinner('Analyzing the X-ray...'):
+        with st.spinner('🔎 Analyzing the X-ray...'):
             top5_predictions = predict(image)
 
-        st.success('✅ Prediction completed!')
+        st.success('✅ Analysis Completed!')
 
+        # --- Show results ---
         st.markdown("---")
-        st.markdown(f"**📋 Patient Name:** {patient_name}")
-        st.markdown(f"**📅 Scan Date:** {scan_date.strftime('%Y-%m-%d')}")
-        st.markdown("### 🧪 Top 5 Predictions:")
-        for disease, probability in top5_predictions.items():
-            st.write(f"🔹 **{disease}**: {probability}")
+        st.subheader("📋 Patient Information")
+        st.write(f"**Name:** {patient_name}")
+        st.write(f"**Scan Date:** {scan_date.strftime('%Y-%m-%d')}")
 
-        st.image(image, caption="Uploaded Chest X-ray", use_column_width=True)
-    else:
-        st.error("⚠️ Please fill all fields and upload an image.")
+        st.markdown("---")
+        st.subheader("🧪 Top 5 Predicted Diseases")
+        
+        for disease, prob in top5_predictions.items():
+            st.progress(prob)  # show progress bar
+            st.write(f"🔹 **{disease}** — {prob*100:.2f}%")
+
+        st.markdown("---")
+        st.subheader("🖼️ Uploaded X-ray Image")
+        st.image(image, use_column_width=True)