Cerebrovascular Network Segmentation on MRA Images with Deep Learning
This work addresses segmentation of complex cerebrovascular structures for medical imaging applications, but it appears incremental as it builds on existing U-net and Inception modules.
The paper tackled the challenging problem of segmenting cerebrovascular networks from MRA images by proposing a new convolutional neural network called Uception, which outperformed state-of-the-art models in this specific context.
Deep learning has been shown to produce state of the art results in many tasks in biomedical imaging, especially in segmentation. Moreover, segmentation of the cerebrovascular structure from magnetic resonance angiography is a challenging problem because its complex geometry and topology have a large inter-patient variability. Therefore, in this work, we present a convolutional neural network approach for this problem. Particularly, a new network topology inspired by the U-net 3D and by the Inception modules, entitled Uception. In addition, a discussion about the best objective function for sparse data also guided most choices during the project. State of the art models are also implemented for a comparison purpose and final results show that the proposed architecture has the best performance in this particular context.