Your browser doesn't support javascript.
loading
Automated eloquent cortex localization in brain tumor patients using multi-task graph neural networks.
Nandakumar, Naresh; Manzoor, Komal; Agarwal, Shruti; Pillai, Jay J; Gujar, Sachin K; Sair, Haris I; Venkataraman, Archana.
Afiliação
  • Nandakumar N; Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore MD, USA. Electronic address: nnandak1@jhu.edu.
  • Manzoor K; Division of Neuroradiology, Johns Hopkins University School of Medicine, Baltimore MD, USA.
  • Agarwal S; Division of Neuroradiology, Johns Hopkins University School of Medicine, Baltimore MD, USA.
  • Pillai JJ; Division of Neuroradiology, Johns Hopkins University School of Medicine, Baltimore MD, USA.
  • Gujar SK; Division of Neuroradiology, Johns Hopkins University School of Medicine, Baltimore MD, USA.
  • Sair HI; Division of Neuroradiology, Johns Hopkins University School of Medicine, Baltimore MD, USA.
  • Venkataraman A; Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore MD, USA.
Med Image Anal ; 74: 102203, 2021 12.
Article em En | MEDLINE | ID: mdl-34474216
ABSTRACT
Localizing the eloquent cortex is a crucial part of presurgical planning. While invasive mapping is the gold standard, there is increasing interest in using noninvasive fMRI to shorten and improve the process. However, many surgical patients cannot adequately perform task-based fMRI protocols. Resting-state fMRI has emerged as an alternative modality, but automated eloquent cortex localization remains an open challenge. In this paper, we develop a novel deep learning architecture to simultaneously identify language and primary motor cortex from rs-fMRI connectivity. Our approach uses the representational power of convolutional neural networks alongside the generalization power of multi-task learning to find a shared representation between the eloquent subnetworks. We validate our method on data from the publicly available Human Connectome Project and on a brain tumor dataset acquired at the Johns Hopkins Hospital. We compare our method against feature-based machine learning approaches and a fully-connected deep learning model that does not account for the shared network organization of the data. Our model achieves significantly better performance than competing baselines. We also assess the generalizability and robustness of our method. Our results clearly demonstrate the advantages of our graph convolution architecture combined with multi-task learning and highlight the promise of using rs-fMRI as a presurgical mapping tool.
Assuntos
Palavras-chave

Texto completo: 1 Coleções: 01-internacional Temas: Geral / Tipos_de_cancer / Outros_tipos Base de dados: MEDLINE Assunto principal: Mapeamento Encefálico / Neoplasias Encefálicas Limite: Humans Idioma: En Revista: Med Image Anal Assunto da revista: DIAGNOSTICO POR IMAGEM Ano de publicação: 2021 Tipo de documento: Article

Texto completo: 1 Coleções: 01-internacional Temas: Geral / Tipos_de_cancer / Outros_tipos Base de dados: MEDLINE Assunto principal: Mapeamento Encefálico / Neoplasias Encefálicas Limite: Humans Idioma: En Revista: Med Image Anal Assunto da revista: DIAGNOSTICO POR IMAGEM Ano de publicação: 2021 Tipo de documento: Article