Update app.py

app.py

@@ -76,19 +76,62 @@ def extract_features(seg_path, high_risk_threshold_mm=5.0):
 
 def calculate_risk_and_format(mask_path, no_chemo, pd_surgery):
     """Runs extraction, ML prediction, and formats UI output."""
+    # 1. Extract raw metrics
     mac, vev, aev, ttv = extract_features(mask_path)
 
+    # Convert textboxes safely
+    try:
+        chemo_val = int(no_chemo)
+        pd_val = int(pd_surgery)
+    except ValueError:
+        error_msg = "**Error:** Clinical metadata fields must be numbers (1 or 0)."
+        return (gr.update(value=error_msg, visible=True), "", "", "", "", "")
+
+    # 2. Hardcode the Means and Stds from your training data
+    # Extracted from your means/stds arrays based on their index positions
+    TTV_MEAN, TTV_STD = 8980.23827, 8281.19811
+    MAC_MEAN, MAC_STD = 8.53567157, 8.92353600
+    AEV_MEAN, AEV_STD = 155.784393, 367.152035
+    VEV_MEAN, VEV_STD = 576.025386, 559.944824
+
+    # 3. Apply Z-score Normalization
+    scaled_ttv = (ttv - TTV_MEAN) / TTV_STD
+    scaled_mac = (mac - MAC_MEAN) / MAC_STD
+    scaled_aev = (aev - AEV_MEAN) / AEV_STD
+    scaled_vev = (vev - VEV_MEAN) / VEV_STD
+
+    # 4. Predict Risk
     if risk_model is not None:
-        features = np.array([[mac, vev, aev, ttv, int(no_chemo), int(pd_surgery)]])
+        # STRICT ORDER MATCHING your column_order:
+        # ['Chemo_0', 'Surgery_1', 'Total_Tumor_Volume_mm3_arterial', 'Min_Distance_mm_arterial', 'High_Risk_Volume_mm3_5mm_arterial', 'High_Risk_Volume_mm3_5mm_venous']
+        features = np.array([[
+            chemo_val,   # Chemo_0
+            pd_val,      # Surgery_1
+            scaled_ttv,  # Total_Tumor_Volume_mm3_arterial
+            scaled_mac,  # Min_Distance_mm_arterial
+            scaled_aev,  # High_Risk_Volume_mm3_5mm_arterial
+            scaled_vev   # High_Risk_Volume_mm3_5mm_venous
+        ]])
+        
         prob_r1 = risk_model.predict_proba(features)[0][1] 
     else:
         prob_r1 = 0.72 # Fallback dummy
 
+    # 5. Format Outputs
     risk_percentage = prob_r1 * 100
     risk_color = "red" if risk_percentage > 50 else "green"
     risk_display = f"<h2 style='color: {risk_color}; margin-top: 0;'>Predicted probability of R1 resection: {risk_percentage:.1f}%</h2>"
 
-    return (gr.update(value="", visible=False), f"{mac:.1f}", f"{vev:.1f}", f"{aev:.1f}", f"{ttv:.1f}", risk_display)
+    # Notice we still display the RAW un-normalized values to the user in the UI, 
+    # but the model calculates risk using the SCALED values.
+    return (
+        gr.update(value="", visible=False), 
+        f"{mac:.1f}", 
+        f"{vev:.1f}", 
+        f"{aev:.1f}", 
+        f"{ttv:.1f}", 
+        risk_display
+    )
 
 
 # PIPELINE HANDLERS