Wall Stress Estimation of Cerebral Aneurysm based on Zernike Convolutional Neural Networks
This work addresses a critical clinical problem for medical imaging and aneurysm treatment by enabling more accurate stress estimation on arbitrary-shaped manifolds, representing an incremental improvement over existing geometric ConvNet methods.
The paper tackled the problem of estimating cerebral aneurysm wall stress, which is clinically important but challenging due to the manifold structure of the data that traditional and state-of-the-art geometric convolutional neural networks (ConvNets) cannot handle effectively. The proposed ZerNet method, based on a novel mathematical generalization of convolution and pooling on manifolds, outperformed other geometric ConvNets in accuracy.
Convolutional neural networks (ConvNets) have demonstrated an exceptional capacity to discern visual patterns from digital images and signals. Unfortunately, such powerful ConvNets do not generalize well to arbitrary-shaped manifolds, where data representation does not fit into a tensor-like grid. Hence, many fields of science and engineering, where data points possess some manifold structure, cannot enjoy the full benefits of the recent advances in ConvNets. The aneurysm wall stress estimation problem introduced in this paper is one of many such problems. The problem is well-known to be of a paramount clinical importance, but yet, traditional ConvNets cannot be applied due to the manifold structure of the data, neither does the state-of-the-art geometric ConvNets perform well. Motivated by this, we propose a new geometric ConvNet method named ZerNet, which builds upon our novel mathematical generalization of convolution and pooling operations on manifolds. Our study shows that the ZerNet outperforms the other state-of-the-art geometric ConvNets in terms of accuracy.