Summary of Building a Synthetic Vascular Model: Evaluation in An Intracranial Aneurysms Detection Scenario, by Rafic Nader and Florent Autrusseau and Vincent L’allinec and Romain Bourcier
Building a Synthetic Vascular Model: Evaluation in an Intracranial Aneurysms Detection Scenario
by Rafic Nader, Florent Autrusseau, Vincent L’Allinec, Romain Bourcier
First submitted to arxiv on: 4 Nov 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed full synthetic 3D model mimics the cerebral vascular tree, including arteries, bifurcations, and intracranial aneurysms. The goal is to provide a dataset for efficient detection of Intra-Cranial Aneurysms using 3D convolutional neural networks. The model focuses on the Circle of Willis structure where aneurysms commonly occur. Deep learning-based studies have shown high performance in detecting and monitoring aneurysms. This work proposes a full synthetic 3D model that mimics brain vasculature as acquired by Magnetic Resonance Angiography (MRA) with Time Of Flight principle, which provides good blood vessel rendering and is non-invasive. The model combines geometry modeling using 3D Spline functions and statistical property reproduction from angiography acquisitions to simulate arteries’ geometry, aneurysm shape, and background noise. A neural network is designed for aneurysm segmentation and detection, and the performance gap achieved through synthetic model data augmentation is evaluated. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper creates a fake brain blood vessel model that helps doctors detect aneurysms better using special computer programs called neural networks. The model makes it look like real MRI scans of the brain, which is useful because it’s hard to get good pictures of tiny blood vessels inside the brain. This could help doctors find aneurysms earlier and prevent them from getting worse. |
Keywords
» Artificial intelligence » Data augmentation » Deep learning » Neural network
