Update app.py

app.py

@@ -1,10 +1,6 @@
 """
 RadiologyScan AI – X-ray & Report analyser
 Author : <you>
-▶ requirements.txt needs:
-    torch torchvision torchxrayvision==1.2.0
-    pillow gradio pymupdf torchcam==0.4.0
-    transformers>=4.40.0 accelerate
 """
 
 import os, re, logging, tempfile
@@ -13,20 +9,18 @@ from PIL import Image
 import torch
 import torch.nn.functional as F
 from torchvision import transforms
-import torchxrayvision as xrv                    # CheXNet-style models
-import fitz                                       # PyMuPDF
-from torchcam.methods import SmoothGradCAMpp      # visual explainability
+import torchxrayvision as xrv
+import fitz  # PyMuPDF
+from torchcam.methods import SmoothGradCAMpp
 from transformers import pipeline
 
 logging.basicConfig(level=logging.INFO)
 log = logging.getLogger(__name__)
 
-# ------------------------------------------------------------------
-# 1. Load model – 18-label denseNet trained on multiple X-ray sets
-# ------------------------------------------------------------------
+# Load model
 DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 MODEL  = xrv.models.get_model("densenet121-res224-all").to(DEVICE).eval()
-LABELS = MODEL.pathologies                       # 18 canonical labels
+LABELS = MODEL.pathologies
 
 TRANSFORM = transforms.Compose([
     transforms.Resize(224),
@@ -35,15 +29,12 @@ TRANSFORM = transforms.Compose([
     transforms.Normalize([0.485,0.456,0.406],[0.229,0.224,0.225])
 ])
 
-# ------------------------ helper ----------------------------------
 def preprocess(pil_img: Image.Image) -> torch.Tensor:
     if pil_img.mode != "RGB":
         pil_img = pil_img.convert("RGB")
     return TRANSFORM(pil_img).unsqueeze(0).to(DEVICE)
 
-# ------------------------------------------------------------------
-# 2. X-ray prediction with Grad-CAM + textual advice
-# ------------------------------------------------------------------
+# X-ray prediction with Grad-CAM
 cam_extractor = SmoothGradCAMpp(MODEL)
 
 def analyse_xray(img: Image.Image):
@@ -52,12 +43,12 @@ def analyse_xray(img: Image.Image):
     x = preprocess(img)
     with torch.no_grad():
         logits = MODEL(x)
-        probs  = torch.sigmoid(logits)[0] * 100   # multi-label %
-    topk = torch.topk(probs, 3)                   # show best 3
+        probs  = torch.sigmoid(logits)[0] * 100
+    topk = torch.topk(probs, 3)
 
-    # Grad-CAM heat-map for the highest score
+    # Grad-CAM heat-map
     target = topk.indices[0].item()
-    activation_map = cam_extractor(target, logits)[0]   # H×W
+    activation_map = cam_extractor(target, logits)[0]
     heatmap = cam_extractor.overlay(torch.squeeze(x).cpu(), activation_map)
 
     # Build HTML summary
@@ -74,7 +65,7 @@ def analyse_xray(img: Image.Image):
 
     return html, Image.fromarray(heatmap)
 
-# simple rule-based advice (extend or swap for knowledge-graph)
+# Medical advice
 ADVICE = {
     "Pneumonia": "Consult a pulmonologist; antibiotics or antivirals as indicated.",
     "Cardiomegaly": "Recommend echocardiography; refer to cardiology.",
@@ -82,10 +73,7 @@ ADVICE = {
 }
 def medical_advice(label): return ADVICE.get(label, "Discuss with a radiologist for next steps.")
 
-# ------------------------------------------------------------------
-# 3. PDF report summariser (LLM pipeline fallback)
-# ------------------------------------------------------------------
-# Regex first → else call an LLM summariser (small DistilBART)
+# PDF report summariser
 summariser = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
 
 def analyse_report(file):
@@ -100,7 +88,6 @@ def analyse_report(file):
 
     disease = regex_find_disease(text)
     if not disease:
-        # fallback LLM summary
         short = summariser(text[:4000], max_length=120, min_length=30, do_sample=False)[0]["summary_text"]
         return f"<h3>Report summary</h3><p>{short}</p>"
 
@@ -120,9 +107,7 @@ def regex_find_disease(t:str):
         if re.search(v, t, flags=re.I): return k
     return None
 
-# ------------------------------------------------------------------
-# 4. Gradio UI
-# ------------------------------------------------------------------
+# Gradio UI
 with gr.Blocks(title="🩻 RadiologyScan AI") as demo:
     gr.Markdown("## 🩻 RadiologyScan AI – Chest X-ray & Report Analyser")