Update app.py

app.py

@@ -1,4 +1,4 @@
-import json 
+import json
 import numpy as np
 import gradio as gr
 from PIL import Image
@@ -16,44 +16,54 @@ MODEL = xrv.models.DenseNet(weights="densenet121-res224-all").to(DEVICE)
 MODEL.eval()
 PATHOLOGIES = MODEL.pathologies
 
-# TorchXRayVision transforms (keep separate, not in torchvision.Compose)
-center_crop = xrv.datasets.XRayCenterCrop()
-resize = xrv.datasets.XRayResizer(224)
-
 def imaging_agent(image_path: str):
     if not image_path:
         return "No image provided.", None
     try:
+        # Load grayscale X-ray
         img = Image.open(image_path).convert("L")
         arr = np.array(img).astype(np.float32)
+
+        # Normalize to [0,1]
         if arr.max() > 1:
             arr /= 255.0
+
+        # TorchXRayVision normalization
         arr = xrv.datasets.normalize(arr, 4096)
 
-        # TorchXRayVision expects dict
+        # Wrap in dict for TorchXRayVision
         sample = {"img": arr}
-        sample = center_crop(sample)
-        sample = resize(sample)
-        arr = sample["img"]
 
+        # Apply transforms step by step
+        sample = xrv.datasets.XRayCenterCrop()(sample)
+        sample = xrv.datasets.XRayResizer(224)(sample)
+
+        arr = sample["img"]  # Unpack back to array
+
+        # Convert to torch tensor
         arr = torch.from_numpy(arr).unsqueeze(0).unsqueeze(0).to(DEVICE)
 
+        # Inference
         with torch.no_grad():
             preds = MODEL(arr)[0]
             probs = torch.sigmoid(preds).cpu().numpy().tolist()
 
-        # Focus on lung pathologies relevant to cancer
+        # Focus only on cancer-relevant lung pathologies
         focus_labels = ["Lung Opacity", "Mass", "Nodule"]
         focus = [(l, probs[PATHOLOGIES.index(l)]) for l in focus_labels if l in PATHOLOGIES]
 
+        # Format outputs
         lines = [f"{name}: {p*100:.1f}%" for name, p in sorted(focus, key=lambda x: x[1], reverse=True)]
         table = {name: round(p, 4) for name, p in focus}
+
         return "🖼️ Imaging Agent (Chest X-ray for cancer risk)\n" + "\n".join(lines), json.dumps(table, indent=2)
+
     except Exception as e:
         return f"Imaging agent error: {e}", None
 
+
 # -----------------------------
-# Lab Agent (tumor markers, stub thresholds)
+# Lab Agent (tumor markers, thresholds stub)
 # -----------------------------
 CANCER_MARKERS = {
     "psa": {"unit": "ng/mL", "high": 4},
@@ -80,6 +90,7 @@ def lab_agent(text: str):
         return "Could not parse tumor markers."
     return "🧪 Lab Agent (Tumor Markers)\n" + "\n".join(results) + ("\nFlags: " + ", ".join(flags) if flags else "\nFlags: none")
 
+
 # -----------------------------
 # Coordinator
 # -----------------------------
@@ -90,6 +101,7 @@ def coordinator(imaging_txt, lab_txt):
     summary += "\n\n⚠️ Disclaimer: Research demo only. Not for clinical use."
     return summary
 
+
 # -----------------------------
 # Demo samples
 # -----------------------------
@@ -99,6 +111,7 @@ SAMPLES = {
 }
 SAMPLE_LABS = "PSA: 8 ng/mL\nCA125: 20 U/mL\nAFP: 15 ng/mL"
 
+
 # -----------------------------
 # Runner
 # -----------------------------
@@ -108,6 +121,7 @@ def run_all(image, labs):
     coord = coordinator(txt, lab)
     return txt, raw, lab, coord
 
+
 # -----------------------------
 # Gradio UI
 # -----------------------------
@@ -147,3 +161,4 @@ demo.launch()
 
 
 
+