🏥 MPR Neural Viewer

Advanced Multi-Planar Reconstruction System for Medical Imaging

Features • Installation • Usage • Architecture • Screenshots

---

✨ Features

Feature	Description
📁 Multi-Format Support	Load DICOM series, NIfTI (.nii, .nii.gz), and NumPy (.npy) volumes
🔄 Multi-Planar Views	Axial, Sagittal, Coronal, and Oblique reconstructions
🎯 Interactive Navigation	Click to recenter, scroll to slice, drag to pan
🔍 Zoom Controls	Ctrl+scroll or buttons for precise zoom
📐 Oblique Slicing	Drag yellow handles to rotate the cutting plane
🤖 AI Organ Detection	TotalSegmentator integration for automatic organ segmentation
📊 Contour Mode	Visualize segmentation contours with label selection
🎬 Cine Playback	Animate through slices in any view
💾 Export Options	Save slices (PNG/NPY) or ROI volumes (NIfTI/NPY)
🌙 Cyberpunk Theme	Modern dark UI with neon accents

---

📦 Installation

Prerequisites

# Required
pip install PyQt5 numpy matplotlib scipy

# Optional (for full functionality)
pip install pydicom          # DICOM support
pip install nibabel          # NIfTI support
pip install scikit-image     # Contour detection
pip install totalsegmentator # AI organ detection (requires GPU)

Quick Start

# Clone or download the project
cd d:\study\imaging\tasks\task2

# Run the application
python main.py

---

🚀 Usage

Loading Data

1. DICOM: Click "Load DICOM" → Select folder containing DICOM files
2. NIfTI/NumPy: Click "Load NIfTI/NumPy" → Select .nii, .nii.gz, or .npy file

Navigation

Action	Control
Change slice	Scroll wheel or slider
Recenter views	Click on any view
Pan	Drag with left mouse button
Zoom	Ctrl + scroll wheel
Rotate oblique plane	Drag yellow handles on crosshair

AI Features

• Detect Organ: Runs TotalSegmentator to identify the main organ
• Run AI: Detects volume orientation (Axial/Sagittal/Coronal)

Contour Mode

1. Load segmentation file with "Load Seg (Contour)"
2. Select label from dropdown
3. Click "Enter Contour Mode"
4. Navigate through contour slices

---

🏗️ Architecture

MPR-Viewer/
├── main.py                 # Application entry point
├── config/
│   ├── __init__.py
│   └── theme.py            # Dark theme stylesheet & palette
├── core/
│   ├── __init__.py
│   ├── reslice.py          # Oblique slice interpolation
│   └── segmentation.py     # TotalSegmentator thread
├── ui/
│   ├── __init__.py
│   ├── view_panel.py       # Single view panel container
│   ├── info_dialog.py      # Startup splash dialog
│   └── main_window.py      # Main MPRApp window
└── utils/
    ├── __init__.py
    └── math_utils.py       # Rotation matrices & plane calculations

Module Responsibilities

Module	Purpose
config.theme	CSS styling and color palette
core.reslice	3D volume oblique resampling
core.segmentation	Background AI segmentation
ui.view_panel	Matplotlib canvas + slider + crosshair state
ui.info_dialog	Animated startup screen
ui.main_window	All UI logic, events, and rendering
utils.math_utils	3D rotation and plane normal calculations

---

📸 Screenshots

Main Interface

The application features a 2×2 grid layout with:

• Top-left: Axial view
• Top-right: Sagittal view
• Bottom-left: Coronal view
• Bottom-right: Oblique view (interactive)

Cyberpunk Theme

• Dark background (#0a0f1a)
• Neon cyan accents (#00ffcc)
• Terminal-style fonts (Consolas)
• Glowing button effects

---

⚙️ Technical Details

Volume Coordinate System

• Shape: (Z, Y, X) or (Slices, Rows, Columns)
• Axial: vol[:, :, z] - horizontal slices
• Sagittal: vol[x, :, :] - left-right slices
• Coronal: vol[:, y, :] - front-back slices

Oblique Slicing Algorithm

Uses trilinear interpolation via scipy.ndimage.map_coordinates:

1. Compute plane normal from crosshair rotation angles
2. Build orthonormal basis (u, v, n)
3. Sample points on the plane grid
4. Interpolate volume values

---

📄 License

MIT License - Feel free to use and modify for your projects.

---

🤝 Contributing

Contributions are welcome! Please feel free to submit issues or pull requests.

---

Made with ❤️ for Medical Imaging