cyd0806's picture
Upload NeuroScan AI code
c2d8817 verified
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>NeuroScan AI - Learn2Reg Real Data Test Report</title>
<style>
* { margin: 0; padding: 0; box-sizing: border-box; }
body {
font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
background: linear-gradient(135deg, #0a192f 0%, #112240 50%, #1d3557 100%);
color: #ccd6f6;
min-height: 100vh;
padding: 20px;
}
.container { max-width: 1400px; margin: 0 auto; }
header {
text-align: center;
padding: 40px 20px;
background: linear-gradient(135deg, #112240 0%, #1d3557 100%);
border-radius: 20px;
margin-bottom: 30px;
box-shadow: 0 10px 40px rgba(0,0,0,0.4);
border: 1px solid rgba(100, 255, 218, 0.1);
}
header h1 {
font-size: 2.8em;
background: linear-gradient(90deg, #64ffda, #00d9ff, #bd93f9);
-webkit-background-clip: text;
-webkit-text-fill-color: transparent;
margin-bottom: 15px;
}
.subtitle { color: #8892b0; font-size: 1.2em; }
.badge {
display: inline-block;
padding: 8px 20px;
border-radius: 25px;
font-weight: bold;
font-size: 0.95em;
margin: 5px;
}
.badge.success { background: linear-gradient(90deg, #64ffda, #00d9ff); color: #0a192f; }
.badge.info { background: rgba(100, 255, 218, 0.1); color: #64ffda; border: 1px solid #64ffda; }
.stats {
display: grid;
grid-template-columns: repeat(auto-fit, minmax(200px, 1fr));
gap: 20px;
margin-bottom: 30px;
}
.stat-card {
background: rgba(255,255,255,0.03);
padding: 25px;
border-radius: 15px;
text-align: center;
border: 1px solid rgba(100, 255, 218, 0.1);
transition: all 0.3s ease;
}
.stat-card:hover {
transform: translateY(-5px);
border-color: #64ffda;
}
.stat-card h3 { font-size: 2.2em; color: #64ffda; margin-bottom: 10px; }
.stat-card p { color: #8892b0; }
.section {
background: rgba(255,255,255,0.02);
border-radius: 20px;
padding: 30px;
margin-bottom: 30px;
border: 1px solid rgba(100, 255, 218, 0.1);
}
.section h2 {
color: #64ffda;
margin-bottom: 20px;
padding-bottom: 10px;
border-bottom: 2px solid rgba(100, 255, 218, 0.2);
}
.visualization { text-align: center; margin: 20px 0; }
.visualization img {
max-width: 100%;
border-radius: 10px;
box-shadow: 0 5px 25px rgba(0,0,0,0.4);
transition: transform 0.3s ease;
}
.visualization img:hover { transform: scale(1.01); }
.description {
background: rgba(100, 255, 218, 0.05);
padding: 15px 20px;
border-radius: 10px;
margin-top: 15px;
border-left: 4px solid #64ffda;
}
footer {
text-align: center;
padding: 30px;
color: #8892b0;
}
</style>
</head>
<body>
<div class="container">
<header>
<h1>🫁 NeuroScan AI</h1>
<p class="subtitle">Learn2Reg Real Lung CT Data - Registration Test Report</p>
<div style="margin-top: 20px;">
<span class="badge success">REAL DATA</span>
<span class="badge info">Learn2Reg Task02</span>
<span class="badge info">Inspiration-Expiration Pair</span>
</div>
</header>
<div class="stats">
<div class="stat-card">
<h3>192x192x208</h3>
<p>Volume Dimensions</p>
</div>
<div class="stat-card">
<h3>10.9%</h3>
<p>Registration Improvement</p>
</div>
<div class="stat-card">
<h3>385.5</h3>
<p>MAE After Registration (HU)</p>
</div>
<div class="stat-card">
<h3>REAL</h3>
<p>Clinical CT Data</p>
</div>
</div>
<div class="section">
<h2>📊 CT Comparison: Inspiration vs Expiration</h2>
<div class="visualization">
<img src="real_ct_comparison.png" alt="Real CT Comparison">
</div>
<div class="description">
<p><strong>Description:</strong> Comparison of real lung CT scans from the Learn2Reg Challenge.
The baseline shows the lungs at end-inspiration (maximum volume), while the followup shows
end-expiration (minimum volume). The significant anatomical deformation is visible,
especially around the diaphragm.</p>
</div>
</div>
<div class="section">
<h2>🔄 Registration Test Results</h2>
<div class="visualization">
<img src="registration_test.png" alt="Registration Test">
</div>
<div class="description">
<p><strong>Description:</strong> Registration test using real breathing motion data.
The algorithm attempts to align the inspiration and expiration scans.
<br><br>
<strong>Results:</strong>
<br>• MAE Before Registration: 432.47 HU
<br>• MAE After Registration: 385.49 HU
<br>• Improvement: 10.9%
<br><br>
<strong>Note:</strong> Large residual differences around the diaphragm are expected
due to the significant breathing motion (typically 2-4 cm displacement).</p>
</div>
</div>
<div class="section">
<h2>🖼️ Multiplanar Views</h2>
<div class="visualization">
<img src="multiplanar_view.png" alt="Multiplanar Views">
</div>
<div class="description">
<p><strong>Description:</strong> Three orthogonal views (axial, coronal, sagittal)
showing the lung anatomy during inspiration and expiration phases.</p>
</div>
</div>
<div class="section">
<h2>📏 Lung Volume Analysis</h2>
<div class="visualization">
<img src="lung_volume_analysis.png" alt="Lung Volume Analysis">
</div>
<div class="description">
<p><strong>Description:</strong> Quantitative analysis of lung volume change during breathing.
The cyan contour represents inspiration (larger volume), while the green contour represents
expiration (smaller volume). This demonstrates the physiological lung volume change
that our registration algorithm must handle.</p>
</div>
</div>
<footer>
<p>NeuroScan AI - Intelligent Medical Imaging Longitudinal Diagnosis System</p>
<p style="margin-top: 10px;">Generated: 2026-01-24 23:17:14</p>
<p style="margin-top: 10px; font-size: 0.9em;">
Data Source: Learn2Reg Challenge Task02 (Zenodo) | Powered by MONAI | SimpleITK
</p>
</footer>
</div>
</body>
</html>