app.py

# app.py

import streamlit as st
import tensorflow as tf
from tensorflow.keras.preprocessing import image
import numpy as np
from PIL import Image
import cv2 # OpenCV for easy image processing (Make sure it's in requirements.txt)

# --- CONFIGURATION ---
MODEL_PATH = 'model.keras' # Aapka saved model file
IMAGE_SIZE = (224, 224)
CLASS_NAMES = ['No Tumor', 'Tumor'] # 0: No Tumor, 1: Tumor

# --- Helper Function: Load Model ---
# Streamlit mein model ko sirf ek baar load karna chahiye
@st.cache_resource
def load_model():
    try:
        model = tf.keras.models.load_model(MODEL_PATH)
        return model
    except Exception as e:
        st.error(f"Error loading model: {e}")
        return None

# --- Helper Function: Preprocess Image ---
def preprocess_image(img):
    """Uploaded image ko model input ke liye ready karna."""
    # Convert PIL image to OpenCV format (numpy array)
    img_array = np.array(img.convert('RGB'))
    
    # Resize and Rescale (Jaisa training mein kiya tha)
    img_resized = cv2.resize(img_array, IMAGE_SIZE)
    img_normalized = img_resized / 255.0  # Normalize to 0-1
    
    # Add batch dimension: (224, 224, 3) -> (1, 224, 224, 3)
    img_batch = np.expand_dims(img_normalized, axis=0)
    
    return img_batch

# --- Streamlit UI Start ---

# 1. Page Title (Requirement a)
st.title("🧠 Brain Tumor Detection System (AI Powered)")

# Load the model
model = load_model()

if model is None:
    st.warning("Model file 'model.keras' not found. Please run 'train_model.py' first and place the file here.")
else:
    # 2. Image Upload Section (Requirement b)
    uploaded_file = st.file_uploader(
        "Upload a Brain MRI Image (.jpg, .png) for Classification:",
        type=["jpg", "png", "jpeg"]
    )

    if uploaded_file is not None:
        # Display image preview (Requirement b)
        image_preview = Image.open(uploaded_file)
        st.image(image_preview, caption='Uploaded MRI Image', use_column_width=True)
        st.write("")
        
        # 3. Prediction Button (Requirement c)
        if st.button("🔬 Detect Tumor"):
            st.write("Processing...")

            # --- Prediction Logic ---
            try:
                # 1. Preprocess the image
                processed_img = preprocess_image(image_preview)
                
                # 2. Predict
                prediction = model.predict(processed_img)
                
                # 3. Interpret the result
                # Output is a single value, e.g., [0.98] or [0.02]
                confidence_score = prediction[0][0] * 100 
                
                if confidence_score > 50:
                    # Confidence is high for Tumor (Class 1)
                    result_index = 1 
                else:
                    # Confidence is high for No Tumor (Class 0)
                    result_index = 0
                    # For 'No Tumor', confidence is 100 - (Model's confidence for Tumor)
                    confidence_score = 100 - confidence_score
                
                predicted_class = CLASS_NAMES[result_index]
                
                # 4. Output Section (Requirement d)
                st.subheader("✅ Prediction Results")
                
                if predicted_class == 'Tumor':
                    st.error(f"**Prediction:** **{predicted_class}** - Immediate medical consultation is advised.")
                else:
                    st.success(f"**Prediction:** **{predicted_class}** - Looks clear.")
                
                # Display Confidence Score
                st.info(f"**Confidence Score:** **{confidence_score:.2f}%**")

            except Exception as e:
                st.error(f"An error occurred during prediction: {e}")

    else:
        st.info("Please upload an image file to begin detection.")

# --- End of Streamlit App ---