app.py

import gradio as gr
import tensorflow as tf
import numpy as np
from tensorflow.keras.preprocessing import image
from PIL import Image
import os
from fpdf import FPDF
import datetime

# Load the trained model
model = tf.keras.models.load_model("my_keras_model.h5")

# Define image size based on the model's input requirement
image_size = (224, 224)

# Function to make predictions
def predict_image(img):
    img = img.resize(image_size)  # Resize image to model's expected size
    img_array = image.img_to_array(img)
    img_array = np.expand_dims(img_array, axis=0) / 255.0  # Normalize
    prediction = model.predict(img_array)

    # Assuming binary classification (fractured or normal)
    class_names = ['Fractured', 'Normal']
    predicted_class = class_names[int(prediction[0] > 0.5)]  # Threshold at 0.5
    confidence = prediction[0][0]

    return predicted_class, confidence

# Function to generate a PDF report
def generate_report(name, age, weight, height, img):
    # Predict result
    predicted_class, confidence = predict_image(img)

    # Create PDF
    pdf = FPDF()
    pdf.set_auto_page_break(auto=True, margin=15)
    pdf.add_page()
    pdf.set_font("Arial", size=12)

    # Add title
    pdf.set_font("Arial", style='B', size=16)
    pdf.cell(200, 10, "Bone Fracture Detection Report", ln=True, align='C')
    pdf.ln(10)

    # Add patient details
    pdf.set_font("Arial", size=12)
    pdf.cell(200, 10, f"Patient Name: {name}", ln=True)
    pdf.cell(200, 10, f"Age: {age}", ln=True)
    pdf.cell(200, 10, f"Weight: {weight} kg", ln=True)
    pdf.cell(200, 10, f"Height: {height} cm", ln=True)
    pdf.cell(200, 10, f"Diagnosis Date: {datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')}", ln=True)
    pdf.ln(10)

    # Add prediction result
    pdf.set_font("Arial", style='B', size=14)
    pdf.cell(200, 10, f"Diagnosis: {predicted_class}", ln=True)
    pdf.set_font("Arial", size=12)
    pdf.cell(200, 10, f"Confidence: {confidence:.2f}", ln=True)

    # Save PDF
    pdf_filename = "patient_report.pdf"
    pdf.output(pdf_filename)

    return pdf_filename

# Define Gradio Interface
interface = gr.Interface(
    fn=generate_report,
    inputs=[
        gr.Textbox(label="Patient Name"),
        gr.Number(label="Age"),
        gr.Number(label="Weight (kg)"),
        gr.Number(label="Height (cm)"),
        gr.Image(type="pil", label="X-ray Image")
    ],
    outputs=gr.File(label="Download Report"),
    title="Bone Fracture Detection & Diagnosis",
    description="Fill in the patient details and upload an X-ray image. The system will analyze the image and generate a PDF report with the diagnosis."
)

# Launch the Gradio app
if __name__ == "__main__":
    interface.launch()