Add brain tumor segmentation model (LFS) and app files

Dockerfile

@@ -0,0 +1,32 @@
+FROM python:3.9-slim
+
+WORKDIR /app
+
+# Install system dependencies for OpenCV
+RUN apt-get update && apt-get install -y \
+    libglib2.0-0 \
+    libsm6 \
+    libxext6 \
+    libxrender-dev \
+    libgomp1 \
+    libgl1 \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements first for better caching
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy application files
+COPY app.py .
+COPY brain1.h5 .
+COPY templates/ templates/
+COPY image/ image/
+
+# Create uploads directory with proper permissions
+RUN mkdir -p uploads && chmod 777 uploads
+
+# Expose port
+EXPOSE 7860
+
+# Run the application
+CMD ["python", "app.py"]

app.py

@@ -0,0 +1,209 @@
+import os
+import cv2
+import numpy as np
+from flask import Flask, request, render_template, jsonify, send_from_directory
+from werkzeug.utils import secure_filename
+from datetime import datetime
+import base64
+from io import BytesIO
+from PIL import Image
+
+# Suppress TensorFlow warnings
+os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
+
+import tensorflow as tf
+from tensorflow.keras.models import load_model
+
+app = Flask(__name__)
+app.config['MAX_CONTENT_LENGTH'] = 16 * 1024 * 1024  # 16MB max
+app.config['UPLOAD_FOLDER'] = 'uploads'
+app.config['ALLOWED_EXTENSIONS'] = {'png', 'jpg', 'jpeg', 'mha'}
+
+# Create uploads folder with proper permissions
+os.makedirs(app.config['UPLOAD_FOLDER'], mode=0o777, exist_ok=True)
+
+# Load the brain segmentation model
+print("Loading Brain Segmentation Model...")
+import warnings
+warnings.filterwarnings('ignore')
+
+try:
+    model = load_model('brain1.h5', compile=False)
+    print("✓ Model loaded successfully!")
+except Exception as e:
+    print(f"❌ Error loading model: {e}")
+    import traceback
+    traceback.print_exc()
+    raise
+
+def allowed_file(filename):
+    """Check if file extension is allowed"""
+    return '.' in filename and \
+           filename.rsplit('.', 1)[1].lower() in app.config['ALLOWED_EXTENSIONS']
+
+def preprocess_image(image_path):
+    """Preprocess image for brain segmentation"""
+    # Read image in grayscale
+    img = cv2.imread(image_path, cv2.IMREAD_GRAYSCALE)
+    
+    if img is None:
+        raise ValueError("Could not read image")
+    
+    # Get original shape
+    original_shape = img.shape
+    
+    # Resize to model input size (assuming 256x256)
+    img_resized = cv2.resize(img, (256, 256))
+    
+    # Normalize to [0, 1]
+    img_normalized = img_resized.astype(np.float32) / 255.0
+    
+    # Add batch and channel dimensions
+    img_input = np.expand_dims(img_normalized, axis=0)
+    img_input = np.expand_dims(img_input, axis=-1)
+    
+    return img_input, original_shape
+
+def postprocess_mask(mask, original_shape):
+    """Postprocess segmentation mask"""
+    # Remove batch dimension
+    mask = np.squeeze(mask)
+    
+    # Resize back to original shape
+    mask_resized = cv2.resize(mask, (original_shape[1], original_shape[0]))
+    
+    # Threshold
+    mask_binary = (mask_resized > 0.5).astype(np.uint8) * 255
+    
+    return mask_binary
+
+def create_overlay(original, mask):
+    """Create overlay of mask on original image"""
+    # Ensure original is RGB
+    if len(original.shape) == 2:
+        original_rgb = cv2.cvtColor(original, cv2.COLOR_GRAY2RGB)
+    else:
+        original_rgb = original.copy()
+    
+    # Create colored mask (red for tumor)
+    colored_mask = np.zeros_like(original_rgb)
+    colored_mask[:, :, 2] = mask  # Red channel
+    
+    # Blend
+    overlay = cv2.addWeighted(original_rgb, 0.7, colored_mask, 0.3, 0)
+    
+    return overlay
+
+def img_to_base64(img_array):
+    """Convert numpy array to base64 string"""
+    # Ensure uint8
+    if img_array.dtype != np.uint8:
+        img_array = (img_array * 255).astype(np.uint8)
+    
+    # Convert to PIL Image
+    if len(img_array.shape) == 2:
+        img = Image.fromarray(img_array, mode='L')
+    else:
+        img = Image.fromarray(img_array, mode='RGB')
+    
+    # Save to buffer
+    buffer = BytesIO()
+    img.save(buffer, format='PNG')
+    buffer.seek(0)
+    
+    # Encode to base64
+    img_base64 = base64.b64encode(buffer.getvalue()).decode('utf-8')
+    
+    return f"data:image/png;base64,{img_base64}"
+
+@app.route('/')
+def index():
+    """Render main page"""
+    return render_template('index.html')
+
+@app.route('/predict', methods=['POST'])
+def predict():
+    """Handle image upload and prediction"""
+    try:
+        # Check if file was uploaded
+        if 'file' not in request.files:
+            return jsonify({'error': 'No file uploaded'}), 400
+        
+        file = request.files['file']
+        
+        if file.filename == '':
+            return jsonify({'error': 'No file selected'}), 400
+        
+        if not allowed_file(file.filename):
+            return jsonify({'error': 'Invalid file type. Please upload PNG, JPG, or JPEG'}), 400
+        
+        # Save uploaded file
+        timestamp = datetime.now().strftime('%Y%m%d_%Hh%Mm%Ss')
+        filename = secure_filename(f"{timestamp}_{file.filename}")
+        filepath = os.path.join(app.config['UPLOAD_FOLDER'], filename)
+        file.save(filepath)
+        
+        # Read original image
+        original_img = cv2.imread(filepath, cv2.IMREAD_GRAYSCALE)
+        
+        # Preprocess
+        img_input, original_shape = preprocess_image(filepath)
+        
+        # Predict
+        print("Making prediction...")
+        prediction = model.predict(img_input, verbose=0)
+        
+        # Postprocess
+        mask = postprocess_mask(prediction[0], original_shape)
+        
+        # Create overlay
+        overlay = create_overlay(original_img, mask)
+        
+        # Convert to base64
+        original_base64 = img_to_base64(original_img)
+        mask_base64 = img_to_base64(mask)
+        overlay_base64 = img_to_base64(overlay)
+        
+        # Calculate statistics
+        tumor_pixels = np.sum(mask > 127)
+        total_pixels = mask.shape[0] * mask.shape[1]
+        tumor_percentage = (tumor_pixels / total_pixels) * 100
+        
+        result = {
+            'original': original_base64,
+            'mask': mask_base64,
+            'overlay': overlay_base64,
+            'tumor_percentage': float(tumor_percentage),
+            'image_size': f"{original_shape[1]}x{original_shape[0]}"
+        }
+        
+        print(f"✓ Prediction completed: {tumor_percentage:.2f}% tumor detected")
+        
+        return jsonify(result)
+        
+    except Exception as e:
+        print(f"Error during prediction: {e}")
+        import traceback
+        traceback.print_exc()
+        return jsonify({'error': str(e)}), 500
+
+@app.route('/example')
+def example():
+    """Get example image"""
+    example_path = 'image/20251012_09h06m52s_grim.png'
+    if os.path.exists(example_path):
+        with open(example_path, 'rb') as f:
+            img_data = f.read()
+        img_base64 = base64.b64encode(img_data).decode('utf-8')
+        return jsonify({'image': f"data:image/png;base64,{img_base64}"})
+    return jsonify({'error': 'Example image not found'}), 404
+
+if __name__ == '__main__':
+    print("\n" + "="*60)
+    print("🧠 Brain Tumor Segmentation App")
+    print("="*60)
+    print("✓ Model loaded and ready!")
+    print("✓ Server starting on port 7860...")
+    print("="*60 + "\n")
+    
+    app.run(host='0.0.0.0', port=7860, debug=False)

brain1.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d11bf3e0889b75fb7e68103dd531b392dba0d5583eaa6fb413c4e7f8dd6bdcf
+size 372892632

requirements.txt

@@ -0,0 +1,7 @@
+Flask==3.0.0
+tensorflow==2.16.1
+opencv-python-headless==4.9.0.80
+numpy==1.26.4
+Pillow==10.2.0
+Werkzeug==3.0.1
+h5py==3.11.0

templates/index.html

@@ -0,0 +1,507 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Brain Tumor Segmentation</title>
+    <style>
+        * {
+            margin: 0;
+            padding: 0;
+            box-sizing: border-box;
+        }
+
+        body {
+            font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
+            background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
+            min-height: 100vh;
+            padding: 20px;
+            display: flex;
+            flex-direction: column;
+            align-items: center;
+        }
+
+        .container {
+            max-width: 1400px;
+            width: 100%;
+            background: rgba(255, 255, 255, 0.95);
+            border-radius: 20px;
+            box-shadow: 0 20px 60px rgba(0, 0, 0, 0.3);
+            overflow: hidden;
+        }
+
+        .header {
+            background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
+            color: white;
+            padding: 40px;
+            text-align: center;
+        }
+
+        .header h1 {
+            font-size: 2.5em;
+            margin-bottom: 10px;
+            display: flex;
+            align-items: center;
+            justify-content: center;
+            gap: 15px;
+        }
+
+        .header p {
+            font-size: 1.1em;
+            opacity: 0.95;
+        }
+
+        .content {
+            padding: 40px;
+        }
+
+        .upload-section {
+            background: #f8f9fa;
+            border-radius: 15px;
+            padding: 40px;
+            text-align: center;
+            margin-bottom: 30px;
+            border: 3px dashed #667eea;
+            transition: all 0.3s;
+        }
+
+        .upload-section:hover {
+            border-color: #764ba2;
+            background: #f0f1f5;
+        }
+
+        .upload-section.dragover {
+            background: #e3e8ff;
+            border-color: #764ba2;
+        }
+
+        .upload-icon {
+            font-size: 4em;
+            margin-bottom: 20px;
+            color: #667eea;
+        }
+
+        .file-input-wrapper {
+            position: relative;
+            display: inline-block;
+            margin: 20px 0;
+        }
+
+        input[type="file"] {
+            display: none;
+        }
+
+        .file-input-label {
+            background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
+            color: white;
+            padding: 15px 40px;
+            border-radius: 50px;
+            cursor: pointer;
+            font-size: 1.1em;
+            font-weight: 600;
+            transition: all 0.3s;
+            display: inline-block;
+            box-shadow: 0 4px 15px rgba(102, 126, 234, 0.4);
+        }
+
+        .file-input-label:hover {
+            transform: translateY(-2px);
+            box-shadow: 0 6px 20px rgba(102, 126, 234, 0.6);
+        }
+
+        .example-btn {
+            background: #6c757d;
+            color: white;
+            padding: 12px 30px;
+            border: none;
+            border-radius: 50px;
+            cursor: pointer;
+            font-size: 1em;
+            margin-left: 15px;
+            transition: all 0.3s;
+        }
+
+        .example-btn:hover {
+            background: #5a6268;
+            transform: translateY(-2px);
+        }
+
+        .selected-file {
+            margin-top: 20px;
+            color: #667eea;
+            font-weight: 600;
+            font-size: 1.1em;
+        }
+
+        .analyze-btn {
+            background: linear-gradient(135deg, #11998e 0%, #38ef7d 100%);
+            color: white;
+            padding: 15px 50px;
+            border: none;
+            border-radius: 50px;
+            cursor: pointer;
+            font-size: 1.2em;
+            font-weight: 600;
+            margin-top: 20px;
+            transition: all 0.3s;
+            box-shadow: 0 4px 15px rgba(17, 153, 142, 0.4);
+        }
+
+        .analyze-btn:hover:not(:disabled) {
+            transform: translateY(-2px);
+            box-shadow: 0 6px 20px rgba(17, 153, 142, 0.6);
+        }
+
+        .analyze-btn:disabled {
+            background: #ccc;
+            cursor: not-allowed;
+            box-shadow: none;
+        }
+
+        .loading {
+            display: none;
+            margin: 30px 0;
+            text-align: center;
+        }
+
+        .spinner {
+            border: 4px solid #f3f3f3;
+            border-top: 4px solid #667eea;
+            border-radius: 50%;
+            width: 50px;
+            height: 50px;
+            animation: spin 1s linear infinite;
+            margin: 0 auto 20px;
+        }
+
+        @keyframes spin {
+            0% { transform: rotate(0deg); }
+            100% { transform: rotate(360deg); }
+        }
+
+        .results {
+            display: none;
+            margin-top: 40px;
+        }
+
+        .results-grid {
+            display: grid;
+            grid-template-columns: repeat(auto-fit, minmax(350px, 1fr));
+            gap: 25px;
+            margin-top: 25px;
+        }
+
+        .result-card {
+            background: white;
+            border-radius: 15px;
+            padding: 20px;
+            box-shadow: 0 4px 20px rgba(0, 0, 0, 0.1);
+            transition: all 0.3s;
+        }
+
+        .result-card:hover {
+            transform: translateY(-5px);
+            box-shadow: 0 6px 30px rgba(0, 0, 0, 0.15);
+        }
+
+        .result-card h3 {
+            color: #667eea;
+            margin-bottom: 15px;
+            font-size: 1.3em;
+        }
+
+        .result-card img {
+            width: 100%;
+            border-radius: 10px;
+            margin-bottom: 15px;
+        }
+
+        .stats {
+            background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
+            color: white;
+            border-radius: 15px;
+            padding: 30px;
+            margin-top: 25px;
+            text-align: center;
+        }
+
+        .stats h3 {
+            font-size: 1.5em;
+            margin-bottom: 20px;
+        }
+
+        .stats-grid {
+            display: grid;
+            grid-template-columns: repeat(auto-fit, minmax(200px, 1fr));
+            gap: 20px;
+        }
+
+        .stat-item {
+            background: rgba(255, 255, 255, 0.2);
+            padding: 20px;
+            border-radius: 10px;
+        }
+
+        .stat-value {
+            font-size: 2em;
+            font-weight: bold;
+            margin: 10px 0;
+        }
+
+        .stat-label {
+            font-size: 0.9em;
+            opacity: 0.9;
+        }
+
+        .error {
+            background: #f8d7da;
+            color: #721c24;
+            padding: 20px;
+            border-radius: 10px;
+            margin: 20px 0;
+            display: none;
+        }
+
+        .footer {
+            background: #f8f9fa;
+            padding: 30px;
+            text-align: center;
+            color: #6c757d;
+            margin-top: 40px;
+        }
+
+        @media (max-width: 768px) {
+            .header h1 {
+                font-size: 1.8em;
+            }
+            
+            .results-grid {
+                grid-template-columns: 1fr;
+            }
+            
+            .content {
+                padding: 20px;
+            }
+        }
+    </style>
+</head>
+<body>
+    <div class="container">
+        <div class="header">
+            <h1>
+                <span>🧠</span>
+                Brain Tumor Segmentation
+                <span>🔬</span>
+            </h1>
+            <p>AI-Powered Medical Image Analysis for Brain MRI Scans</p>
+        </div>
+
+        <div class="content">
+            <div class="upload-section" id="dropZone">
+                <div class="upload-icon">📤</div>
+                <h2 style="color: #667eea; margin-bottom: 15px;">Upload Brain MRI Scan</h2>
+                <p style="color: #6c757d; margin-bottom: 20px;">
+                    Drag and drop your MRI image here or click to browse
+                </p>
+                
+                <div class="file-input-wrapper">
+                    <input type="file" id="fileInput" accept="image/*">
+                    <label for="fileInput" class="file-input-label">
+                        Choose File
+                    </label>
+                    <button class="example-btn" onclick="loadExample()">
+                        Load Example
+                    </button>
+                </div>
+                
+                <div class="selected-file" id="selectedFile"></div>
+                
+                <button class="analyze-btn" id="analyzeBtn" onclick="analyzeBrain()" disabled>
+                    Analyze Brain Scan
+                </button>
+            </div>
+
+            <div class="loading" id="loading">
+                <div class="spinner"></div>
+                <p style="color: #667eea; font-size: 1.2em;">Analyzing brain scan...</p>
+            </div>
+
+            <div class="error" id="error"></div>
+
+            <div class="results" id="results">
+                <h2 style="color: #667eea; margin-bottom: 20px;">Segmentation Results</h2>
+                
+                <div class="results-grid">
+                    <div class="result-card">
+                        <h3>🖼️ Original MRI</h3>
+                        <img id="originalImg" src="" alt="Original">
+                    </div>
+                    
+                    <div class="result-card">
+                        <h3>🎯 Tumor Mask</h3>
+                        <img id="maskImg" src="" alt="Mask">
+                    </div>
+                    
+                    <div class="result-card">
+                        <h3>🔍 Overlay</h3>
+                        <img id="overlayImg" src="" alt="Overlay">
+                    </div>
+                </div>
+
+                <div class="stats">
+                    <h3>📊 Analysis Statistics</h3>
+                    <div class="stats-grid">
+                        <div class="stat-item">
+                            <div class="stat-label">Tumor Coverage</div>
+                            <div class="stat-value" id="tumorPercentage">-</div>
+                            <div class="stat-label">of brain area</div>
+                        </div>
+                        <div class="stat-item">
+                            <div class="stat-label">Image Resolution</div>
+                            <div class="stat-value" id="imageSize">-</div>
+                            <div class="stat-label">pixels</div>
+                        </div>
+                    </div>
+                </div>
+            </div>
+        </div>
+
+        <div class="footer">
+            <p>⚠️ For research and educational purposes only. Not for clinical diagnosis.</p>
+            <p style="margin-top: 10px;">Powered by Deep Learning | TensorFlow & Keras</p>
+        </div>
+    </div>
+
+    <script>
+        let selectedFile = null;
+
+        // File input change handler
+        document.getElementById('fileInput').addEventListener('change', function(e) {
+            if (e.target.files.length > 0) {
+                selectedFile = e.target.files[0];
+                document.getElementById('selectedFile').textContent = '✓ ' + selectedFile.name;
+                document.getElementById('analyzeBtn').disabled = false;
+                hideResults();
+            }
+        });
+
+        // Drag and drop handlers
+        const dropZone = document.getElementById('dropZone');
+
+        dropZone.addEventListener('dragover', (e) => {
+            e.preventDefault();
+            dropZone.classList.add('dragover');
+        });
+
+        dropZone.addEventListener('dragleave', () => {
+            dropZone.classList.remove('dragover');
+        });
+
+        dropZone.addEventListener('drop', (e) => {
+            e.preventDefault();
+            dropZone.classList.remove('dragover');
+            
+            const files = e.dataTransfer.files;
+            if (files.length > 0) {
+                selectedFile = files[0];
+                document.getElementById('fileInput').files = files;
+                document.getElementById('selectedFile').textContent = '✓ ' + selectedFile.name;
+                document.getElementById('analyzeBtn').disabled = false;
+                hideResults();
+            }
+        });
+
+        // Load example image
+        function loadExample() {
+            fetch('/example')
+                .then(response => response.json())
+                .then(data => {
+                    if (data.image) {
+                        // Convert base64 to blob
+                        fetch(data.image)
+                            .then(res => res.blob())
+                            .then(blob => {
+                                const file = new File([blob], "example.png", { type: "image/png" });
+                                const dataTransfer = new DataTransfer();
+                                dataTransfer.items.add(file);
+                                document.getElementById('fileInput').files = dataTransfer.files;
+                                selectedFile = file;
+                                document.getElementById('selectedFile').textContent = '✓ Example Brain MRI';
+                                document.getElementById('analyzeBtn').disabled = false;
+                                hideResults();
+                            });
+                    }
+                })
+                .catch(error => {
+                    showError('Failed to load example image');
+                });
+        }
+
+        // Analyze brain scan
+        function analyzeBrain() {
+            if (!selectedFile) {
+                showError('Please select a file first');
+                return;
+            }
+
+            const formData = new FormData();
+            formData.append('file', selectedFile);
+
+            // Show loading
+            document.getElementById('loading').style.display = 'block';
+            document.getElementById('results').style.display = 'none';
+            document.getElementById('error').style.display = 'none';
+            document.getElementById('analyzeBtn').disabled = true;
+
+            fetch('/predict', {
+                method: 'POST',
+                body: formData
+            })
+            .then(response => response.json())
+            .then(data => {
+                if (data.error) {
+                    showError(data.error);
+                } else {
+                    showResults(data);
+                }
+            })
+            .catch(error => {
+                showError('Analysis failed: ' + error.message);
+            })
+            .finally(() => {
+                document.getElementById('loading').style.display = 'none';
+                document.getElementById('analyzeBtn').disabled = false;
+            });
+        }
+
+        // Show results
+        function showResults(data) {
+            document.getElementById('originalImg').src = data.original;
+            document.getElementById('maskImg').src = data.mask;
+            document.getElementById('overlayImg').src = data.overlay;
+            document.getElementById('tumorPercentage').textContent = data.tumor_percentage.toFixed(2) + '%';
+            document.getElementById('imageSize').textContent = data.image_size;
+            
+            document.getElementById('results').style.display = 'block';
+            
+            // Scroll to results
+            document.getElementById('results').scrollIntoView({ behavior: 'smooth' });
+        }
+
+        // Show error
+        function showError(message) {
+            document.getElementById('error').textContent = '❌ ' + message;
+            document.getElementById('error').style.display = 'block';
+            setTimeout(() => {
+                document.getElementById('error').style.display = 'none';
+            }, 5000);
+        }
+
+        // Hide results
+        function hideResults() {
+            document.getElementById('results').style.display = 'none';
+            document.getElementById('error').style.display = 'none';
+        }
+    </script>
+</body>
+</html>