TRELLIS-Enhanced Surface Features for Comprehensive Intracranial Aneurysm Analysis
This work addresses the difficulty of intracranial aneurysm analysis for medical applications, representing an incremental advance by applying an existing generative model to a new domain.
The paper tackled the problem of detecting, delineating, and modeling intracranial aneurysms by proposing a cross-domain feature-transfer approach using TRELLIS surface features, which improved classification, segmentation, and blood-flow prediction tasks, reducing simulation error by 15%.
Intracranial aneurysms pose a significant clinical risk yet are difficult to detect, delineate and model due to limited annotated 3D data. We propose a cross-domain feature-transfer approach that leverages the latent geometric embeddings learned by TRELLIS, a generative model trained on large-scale non-medical 3D datasets, to augment neural networks for aneurysm analysis. By replacing conventional point normals or mesh descriptors with TRELLIS surface features, we systematically enhance three downstream tasks: (i) classifying aneurysms versus healthy vessels in the Intra3D dataset, (ii) segmenting aneurysm and vessel regions on 3D meshes, and (iii) predicting time-evolving blood-flow fields using a graph neural network on the AnXplore dataset. Our experiments show that the inclusion of these features yields strong gains in accuracy, F1-score and segmentation quality over state-of-the-art baselines, and reduces simulation error by 15\%. These results illustrate the broader potential of transferring 3D representations from general-purpose generative models to specialized medical tasks.