app.py

import streamlit as st
import tensorflow as tf
import cv2
import numpy as np
from PIL import Image

# Load the trained model
model = tf.keras.models.load_model('braintumor.h5')

# Define labels for the classes
labels = ['glioma_tumor', 'meningioma_tumor', 'no_tumor', 'pituitary_tumor']

# Define a function to make predictions
def predict_tumor_type(image):
    # Preprocess the image
    img = cv2.resize(image, (150, 150))
    img_array = np.array(img)
    img_array = img_array.reshape(1, 150, 150, 3)
    
    # Make prediction
    prediction = model.predict(img_array)
    predicted_class = labels[np.argmax(prediction)]
    confidence = np.max(prediction)
    
    return predicted_class, confidence

# Streamlit UI
st.title("Brain Tumor Classification")
st.write("Upload an image for brain tumor classification.")

uploaded_image = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])

if uploaded_image is not None:
    # Display the uploaded image
    image = Image.open(uploaded_image)
    st.image(image, caption="Uploaded Image", use_column_width=True)
    
    # Make prediction
    prediction, confidence = predict_tumor_type(np.array(image))
    
    st.write("Prediction:", prediction)
    st.write(f"Confidence: {confidence * 100:.2f}%")

st.write("DISCLAIMER:")
st.write("0 - glioma_tumor")
st.write("1 - meningioma_tumor")
st.write("2 - No_tumor")
st.write("3 - pituitary_tumor")