app.py

import streamlit as st
from PIL import Image
import numpy as np
from tensorflow.keras.models import load_model
from tensorflow.keras.preprocessing import image
from tensorflow.keras.applications.vgg16 import preprocess_input

# Load your trained model
model = load_model('BT(Deploy).h5')  # Replace with your model's path

# Set Streamlit page config for a better layout
st.set_page_config(page_title="Brain Tumor Detection", page_icon="🧠", layout="centered")

# Add a title and description
st.title("Brain Tumor Detection 🧠")
st.markdown("""
    Upload a brain MRI scan to detect whether it contains a brain tumor or not. 
    Our model uses advanced deep learning to analyze your scan and provide a prediction.
    """)

# File uploader with custom styling
uploaded_file = st.file_uploader("Upload a Brain MRI Scan", type=["jpg", "png", "jpeg"], label_visibility="collapsed")


# Function to preprocess the image
def preprocess_image(img):
    img = img.resize((224, 224))  # Resize to 224x224
    img_array = np.array(img)  # Convert image to numpy array
    img_array = np.expand_dims(img_array, axis=0)  # Add batch dimension
    img_array = preprocess_input(img_array)  # Preprocess image for VGG16
    return img_array


if uploaded_file is not None:
    # Display the uploaded image
    img = Image.open(uploaded_file)
    st.image(img, caption="Uploaded MRI Scan", use_container_width=True)

    # Preprocess and predict
    try:
        processed_image = preprocess_image(img)
        st.write("Image successfully preprocessed!")

        # Model prediction
        prediction = model.predict(processed_image)

        # Display prediction result with styling
        st.subheader("Prediction Results")
        if prediction[0][0] > 0.5:
            st.markdown('<p style="font-size:18px;color:red;">⚠️ Brain Tumor Detected</p>', unsafe_allow_html=True)
        else:
            st.markdown('<p style="font-size:18px;color:green;">✅ No Brain Tumor Detected</p>', unsafe_allow_html=True)

    except Exception as e:
        st.error(f"Error in preprocessing or prediction: {e}")

# Add footer and additional information
st.markdown("""
    ---
    **Developed with 💙 by [Abhinav]**  
    This project is aimed at helping doctors detect brain tumors from MRI scans using deep learning models.
    """)

# Custom styling for Streamlit components
st.markdown("""
    <style>
        .css-1v0mbdj {
            font-size: 20px;
            font-weight: bold;
        }
        .css-5wyi5j {
            background-color: #f0f0f5;
        }
    </style>
""", unsafe_allow_html=True)