An Inception Inspired Deep Network to Analyse Fundus Images
This work addresses vessel segmentation for medical imaging analysis, but it appears incremental as it adapts existing inception modules without major breakthroughs.
The authors tackled vessel segmentation in fundus images by proposing a deep network inspired by inception modules, achieving performance better than or comparable to previous methods on DRIVE and IOSTAR datasets.
A fundus image usually contains the optic disc, pathologies and other structures in addition to vessels to be segmented. This study proposes a deep network for vessel segmentation, whose architecture is inspired by inception modules. The network contains three sub-networks, each with a different filter size, which are connected in the last layer of the proposed network. According to experiments conducted in the DRIVE and IOSTAR, the performance of our network is found to be better than or comparable to that of the previous methods. We also observe that the sub-networks pay attention to different parts of an input image when producing an output map in the last layer of the proposed network; though, training of the proposed network is not constrained for this purpose.