Update app.py

app.py

@@ -2,88 +2,75 @@ import gradio as gr
 from PIL import Image
 import torch
 from torchvision import models, transforms
-import PyPDF2  # For reading patient reports (PDFs)
+import PyPDF2
 
-# Load a more specialized pre-trained model (DenseNet, similar to CheXNet)
-model = models.densenet121(pretrained=True)  # DenseNet is good for image classification tasks like chest X-rays
-model.eval()  # Set the model to evaluation mode
+model = models.densenet121(pretrained=True)
+model.eval()
 
-# Define image preprocessing function
 def preprocess_image(image):
     transform = transforms.Compose([
-        transforms.Resize((224, 224)),  # Resize to fit the model input size
+        transforms.Resize((224, 224)),
         transforms.ToTensor(),
     ])
     return transform(image).unsqueeze(0)
 
-# Define a prediction function for X-ray images with detailed output
 def predict_xray(image):
     image_tensor = preprocess_image(image)
     with torch.no_grad():
         outputs = model(image_tensor)
     probs = torch.nn.functional.softmax(outputs[0], dim=0)
-    
-    # Define the conditions (replace these with the actual conditions your model predicts)
+
     conditions = ["Normal", "Pneumonia", "Cancer", "TB", "Other"]
     results = {conditions[i]: float(probs[i]) for i in range(len(conditions))}
-    
-    # Identify the most likely condition and calculate the confidence
+
     most_likely_condition = max(results, key=results.get)
-    confidence = results[most_likely_condition] * 100  # Convert to percentage
-    
-    # Provide a more detailed summary of the results
+    confidence = results[most_likely_condition] * 100
+
     summary = f"**Summary**: Based on the X-ray analysis, the most likely diagnosis is: <b>{most_likely_condition}</b> with a confidence of <b>{confidence:.2f}%</b>."
-    
-    # Additional detailed descriptions and recommendations for each condition
+
     condition_details = {
         "Normal": {
             "description": "The X-ray shows no abnormal signs, and the lungs appear healthy.",
             "recommendation": "No further tests are required. Continue with regular health check-ups."
         },
         "Pneumonia": {
-            "description": "Pneumonia is an infection that causes inflammation in the lungs. It can be caused by bacteria, viruses, or fungi.",
-            "recommendation": "Consult a healthcare provider immediately for possible antibiotics and further treatment."
+            "description": "Pneumonia is an infection that causes inflammation in the lungs.",
+            "recommendation": "Consult a healthcare provider for treatment."
         },
         "Cancer": {
-            "description": "Lung cancer can manifest in the form of abnormal growths in the lungs. It may require more advanced diagnostic tools like biopsies.",
-            "recommendation": "Consult an oncologist for further tests and treatment options."
+            "description": "Lung cancer may appear as abnormal growths in the lungs.",
+            "recommendation": "Consult an oncologist for further diagnostic procedures."
         },
         "TB": {
-            "description": "Tuberculosis (TB) is a serious bacterial infection that mainly affects the lungs. It is treatable but requires proper care.",
-            "recommendation": "Seek immediate medical attention for a proper treatment plan, which may include antibiotics."
+            "description": "Tuberculosis is a bacterial infection that affects the lungs.",
+            "recommendation": "Seek immediate medical attention for treatment."
         },
         "Other": {
-            "description": "The X-ray may show signs of other possible conditions that need further investigation.",
-            "recommendation": "Consult with a doctor to rule out any other serious conditions."
+            "description": "There may be other conditions requiring investigation.",
+            "recommendation": "Consult a radiologist for further analysis."
         }
     }
-    
-    # Displaying the results in a structured way (bullet points)
+
     detailed_results = "<ul>"
     for condition, prob in results.items():
         detailed_results += f"<li><b>{condition}:</b> {prob*100:.2f}%</li>"
     detailed_results += "</ul>"
-    
-    # Additional feedback for the most likely condition
-    additional_feedback = condition_details.get(most_likely_condition, "Please consult with a doctor for further details.")
-    
+
+    additional_feedback = condition_details.get(most_likely_condition, "Consult a doctor for more details.")
+
     return summary, detailed_results, additional_feedback
 
-# Define a function to read and analyze patient reports (PDFs)
 def analyze_report(file):
     text = ""
     if file.name.endswith(".pdf"):
         pdf_reader = PyPDF2.PdfReader(file)
         for page in pdf_reader.pages:
             text += page.extract_text()
-    # For simplicity, we are just summarizing the first 300 characters
     report_summary = f"Patient Report (Preview): {text[:300]}..."
     return report_summary
 
-# Gradio Interface with enhanced UI
 def create_interface():
     with gr.Blocks() as demo:
-        # Custom CSS for UI
         custom_css = """
         .gradio-container {
             background-color: #f4f6f9;
@@ -110,42 +97,38 @@ def create_interface():
             box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);
             margin-top: 20px;
         }
-        .result-list {
-            padding-left: 20px;
-        }
-        .result-summary {
-            font-size: 18px;
-            color: #2F4F4F;
-        }
         """
-        
-        # Title section
+
         gr.Markdown("<h1 class='title'>RadiologyScan AI</h1>")
-        
-        # Upload X-ray image section
+        gr.Markdown("""
+        <h3>🩻 Radiology Areas Covered:</h3>
+        <table style='width:100%; border: 1px solid #ccc;'>
+          <tr><th>Area</th><th>Common Tools</th><th>Focused Problems</th></tr>
+          <tr><td>Lungs</td><td>X-ray, CT</td><td>Pneumonia, TB, Lung cancer</td></tr>
+          <tr><td>Brain</td><td>MRI, CT</td><td>Stroke, Tumors</td></tr>
+          <tr><td>Bones/Joints</td><td>X-ray, CT, MRI</td><td>Fractures, Arthritis</td></tr>
+          <tr><td>Abdomen/Pelvis</td><td>Ultrasound, CT</td><td>Liver/kidney issues, tumors, appendicitis</td></tr>
+          <tr><td>Cancer Anywhere</td><td>MRI, CT, PET</td><td>Tumors, cancer spread, biopsy guidance</td></tr>
+        </table>
+        """)
+
         with gr.Row():
             xray_input = gr.Image(label="Upload Chest X-ray", type="pil")
             report_input = gr.File(label="Upload Patient Report (PDF)", file_count="single")
-        
-        # Buttons for analysis
+
         with gr.Row():
             predict_button = gr.Button("Analyze X-ray", elem_classes="gradio-button")
             report_button = gr.Button("Analyze Report", elem_classes="gradio-button")
-        
-        # Results section for the X-ray image
-        xray_output = gr.HTML(label="X-ray Diagnosis Summary", elem_classes="result-box")  # Removed interactive=False
-        xray_result = gr.HTML(label="Detailed X-ray Results", elem_classes="result-box")  # Removed interactive=False
+
+        xray_output = gr.HTML(label="X-ray Diagnosis Summary", elem_classes="result-box")
+        xray_result = gr.HTML(label="Detailed X-ray Results", elem_classes="result-box")
         additional_feedback = gr.Textbox(label="Additional Feedback", interactive=False, elem_classes="result-box")
-        
-        # Results section for the patient report
         report_output = gr.Textbox(label="Report Summary", interactive=False, elem_classes="result-box")
-        
-        # Event handlers for buttons
+
         predict_button.click(predict_xray, inputs=xray_input, outputs=[xray_output, xray_result, additional_feedback])
         report_button.click(analyze_report, inputs=report_input, outputs=report_output)
-    
+
     return demo
 
-# Launch the Gradio interface
 demo = create_interface()
-demo.launch(share=True)
+demo.launch(share=True)