| import streamlit as st
|
| import tensorflow as tf
|
| from tensorflow.keras.models import load_model
|
| import numpy as np
|
| from PIL import Image
|
| import os
|
| import requests
|
|
|
|
|
| HF_REPO_ID = "saad1BM/brain-tumor-detection"
|
| MODEL_FILENAME = "brain_tumor_model.keras"
|
| MODEL_PATH = MODEL_FILENAME
|
|
|
| IMAGE_SIZE = (224, 224)
|
| CLASS_NAMES = ['glioma_tumor', 'meningioma_tumor', 'no_tumor', 'pituitary_tumor']
|
|
|
|
|
| @st.cache_resource
|
| def load_trained_model():
|
| """Trained model ko Hugging Face se download aur load karta hai."""
|
|
|
|
|
| MIN_SIZE = 100 * 1024 * 1024
|
|
|
| try:
|
|
|
| if not os.path.exists(MODEL_PATH) or os.path.getsize(MODEL_PATH) < MIN_SIZE:
|
| st.info(f"Downloading model from Hugging Face: {HF_REPO_ID}")
|
|
|
|
|
| model_url = f"https://huggingface.co/{HF_REPO_ID}/resolve/main/{MODEL_FILENAME}"
|
|
|
|
|
| r = requests.get(model_url, allow_redirects=True)
|
|
|
|
|
| r.raise_for_status()
|
|
|
|
|
| with open(MODEL_PATH, 'wb') as f:
|
| f.write(r.content)
|
| st.success("Model download successful!")
|
|
|
|
|
| model = load_model(MODEL_PATH)
|
| return model
|
|
|
| except requests.exceptions.HTTPError as hf_err:
|
| st.error(f"Error 404/401: Model not found on Hugging Face. Please check {HF_REPO_ID}/{MODEL_FILENAME}.")
|
| return None
|
| except Exception as e:
|
| st.error(f"Final Keras Load Error: Model file may be incomplete or corrupted. ({e})")
|
| return None
|
|
|
| model = load_trained_model()
|
|
|
|
|
|
|
| def predict_image(image_file, model):
|
| """Uploaded image par prediction karta hai."""
|
| if model is None:
|
| return "Model Load Failed", 0.0
|
|
|
|
|
| img = Image.open(image_file).convert("RGB")
|
|
|
| img = img.resize(IMAGE_SIZE)
|
| img_array = np.array(img)
|
|
|
| img_array = np.expand_dims(img_array, axis=0)
|
|
|
|
|
| img_array = img_array / 255.0
|
|
|
|
|
| predictions = model.predict(img_array)
|
|
|
|
|
| predicted_index = np.argmax(predictions, axis=1)[0]
|
| confidence_score = np.max(predictions) * 100
|
|
|
| predicted_class = CLASS_NAMES[predicted_index]
|
|
|
| return predicted_class, confidence_score
|
|
|
|
|
|
|
| st.set_page_config(page_title="Brain Tumor Detection", layout="wide")
|
|
|
|
|
| st.title("Brain Tumor Detection System (AI Powered)")
|
| st.write("Upload an MRI image below to classify it as one of the tumor types or no tumor.")
|
| st.markdown("---")
|
|
|
| col1, col2 = st.columns(2)
|
|
|
| with col1:
|
|
|
| uploaded_file = st.file_uploader("Upload MRI Image:", type=["jpg", "jpeg", "png"])
|
|
|
| if uploaded_file is not None:
|
|
|
| st.image(uploaded_file, caption="Uploaded MRI Image", use_column_width=True)
|
| st.markdown("---")
|
|
|
|
|
| if st.button("Detect Tumor"):
|
| st.spinner("Analyzing image and detecting tumor...")
|
|
|
|
|
| predicted_class, confidence_score = predict_image(uploaded_file, model)
|
|
|
|
|
|
|
|
|
| if predicted_class == 'no_tumor':
|
| result_label = f" **Prediction: No Tumor**"
|
| else:
|
| result_label = f" **Prediction: Tumor ({predicted_class.replace('_', ' ').title()})**"
|
|
|
| st.success(" Analysis Complete")
|
| st.subheader(result_label)
|
| st.metric(label="Confidence Score", value=f"{confidence_score:.2f}%")
|
|
|
| st.write("---")
|
|
|
| with col2:
|
| st.header("Results and Interpretation")
|
| st.info("The system uses Transfer Learning (VGG16) to classify the image into four categories: Glioma, Meningioma, Pituitary, or No Tumor.")
|
|
|
|
|
| if uploaded_file is None:
|
| st.warning("Please upload an image and click 'Detect Tumor' to see the results.") |
