Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/71253
Título: | Adaptive feature recombination and recalibration for semantic segmentation: application to brain tumor segmentation in MRI |
Autor(es): | Pereira, Sergio Alves, Victor Silva, Carlos A. |
Data: | 2018 |
Editora: | Springer |
Revista: | Lecture Notes in Computer Science |
Citação: | Pereira S., Alves V., Silva C.A. (2018) Adaptive Feature Recombination and Recalibration for Semantic Segmentation: Application to Brain Tumor Segmentation in MRI. In: Frangi A., Schnabel J., Davatzikos C., Alberola-López C., Fichtinger G. (eds) Medical Image Computing and Computer Assisted Intervention – MICCAI 2018. MICCAI 2018. Lecture Notes in Computer Science, vol 11072. Springer, Cham. https://doi.org/10.1007/978-3-030-00931-1_81 |
Resumo(s): | Convolutional neural networks (CNNs) have been successfully used for brain tumor segmentation, specifically, fully convolutional networks (FCNs). FCNs can segment a set of voxels at once, having a direct spatial correspondence between units in feature maps (FMs) at a given location and the corresponding classified voxels. In convolutional layers, FMs are merged to create new FMs, so, channel combination is crucial. However, not all FMs have the same relevance for a given class. Recently, in classification problems, Squeeze-and-Excitation (SE) blocks have been proposed to re-calibrate FMs as a whole, and suppress the less informative ones. However, this is not optimal in FCN due to the spatial correspondence between units and voxels. In this article, we propose feature recombination through linear expansion and compression to create more complex features for semantic segmentation. Additionally, we propose a segmentation SE (SegSE) block for feature recalibration that collects contextual information, while maintaining the spatial meaning. Finally, we evaluate the proposed methods in brain tumor segmentation, using publicly available data. |
Tipo: | Artigo em ata de conferência |
URI: | https://hdl.handle.net/1822/71253 |
ISBN: | 978-3-030-00930-4 |
e-ISBN: | 978-3-030-00931-1 |
DOI: | 10.1007/978-3-030-00931-1_81 |
ISSN: | 0302-9743 |
Versão da editora: | https://link.springer.com/chapter/10.1007%2F978-3-030-00931-1_81 |
Arbitragem científica: | yes |
Acesso: | Acesso restrito UMinho |
Aparece nas coleções: | CMEMS - Artigos em livros de atas/Papers in proceedings |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
Pereira_Alves_Silva@2018.pdf Acesso restrito! | 208,67 kB | Adobe PDF | Ver/Abrir |