Draft Status
Draft - team will hold off on page creation
Category
Segmentation / Classification / Landmarking
Key Investigators
- Kalysta Makimota (Brigham and Women's Hospital, United States)
- Axel Masquelin (Brigham and Women's Hospital, United States)
- Raúl San José Estépar (Brigham and Women's Hospital, United States)
Project Description
The Chest Imaging Platform (CIP) is an open-source software suite developed by the Applied Chest Imaging Laboratory (ACIL) at Brigham and Women's Hospital (Harvard Medical School). CIP is designed for quantitative chest CT analysis, helping researchers identify and measure phenotypes for Chronic Obstructive Pulmonary Disease (COPD), Interstitial Lung Disease (ILD), Acute Lung Injury (ALI), and pulmonary vascular pruning, and hopefully by the end of this Lung Cancer.
Objective
This relaunch a modern, deep-learning-centric Chest Imaging Platform within 3D Slicer that simplifies model deployment and optimizes inference, while maintaining core functionalities that are being used for tasks such as lung volume estimation.
Approach and Plan
We address two major historical pain points:
Model Dispersion: Previously, integrating new deep learning models required custom scripting or manual installation. We will introduce a unified, user-friendly Model Hub. Further Details pending
Pre-processing Discrepancies: Variations in voxel spacing, orientation, and Intensity (Hounsfield Unit) ranges often degrade model performance. We will provide a standardized, automated preprocessing pipeline that ensures input scans are automatically optimized before running inference.
🛠️ System Architecture & Workflow
The new Slicer-CIP architecture separates the interactive visualization layer (3D Slicer) from the processing layer, allowing users to pull models from our central repository and execute standardized preprocessing on-the-fly.
Progress and Next Steps
- Reviewing current CIP-Slicer integration and getting feedback and development notes from Rubén San José Estépar.
Illustrations
No response
Background and References
- Chest Imaging Platform
- LobTE
Draft Status
Draft - team will hold off on page creation
Category
Segmentation / Classification / Landmarking
Key Investigators
Project Description
The Chest Imaging Platform (CIP)is an open-source software suite developed by theApplied Chest Imaging Laboratory (ACIL)at Brigham and Women's Hospital (Harvard Medical School). CIP is designed for quantitative chest CT analysis, helping researchers identify and measure phenotypes for Chronic Obstructive Pulmonary Disease (COPD), Interstitial Lung Disease (ILD), Acute Lung Injury (ALI), and pulmonary vascular pruning, and hopefully by the end of this Lung Cancer.Objective
This relaunch a modern, deep-learning-centric Chest Imaging Platform within 3D Slicer that simplifies model deployment and optimizes inference, while maintaining core functionalities that are being used for tasks such as lung volume estimation.
Approach and Plan
We address two major historical pain points:
Model Dispersion: Previously, integrating new deep learning models required custom scripting or manual installation. We will introduce a unified, user-friendly Model Hub. Further Details pendingPre-processing Discrepancies: Variations in voxel spacing, orientation, and Intensity (Hounsfield Unit) ranges often degrade model performance. We will provide a standardized, automated preprocessing pipeline that ensures input scans are automatically optimized before running inference.🛠️ System Architecture & Workflow
The new Slicer-CIP architecture separates the interactive visualization layer (3D Slicer) from the processing layer, allowing users to pull models from our central repository and execute standardized preprocessing on-the-fly.
Progress and Next Steps
Illustrations
No response
Background and References