Your browser doesn't support javascript.
loading
Improving cardiac MRI convolutional neural network segmentation on small training datasets and dataset shift: A continuous kernel cut approach.
Guo, Fumin; Ng, Matthew; Goubran, Maged; Petersen, Steffen E; Piechnik, Stefan K; Neubauer, Stefan; Wright, Graham.
Afiliação
  • Guo F; Sunnybrook Research Institute, University of Toronto, Toronto M4N 3M5, Canada; Department of Medical Biophysics, University of Toronto, Toronto, Canada. Electronic address: fumin.guo@sri.utoronto.ca.
  • Ng M; Sunnybrook Research Institute, University of Toronto, Toronto M4N 3M5, Canada; Department of Medical Biophysics, University of Toronto, Toronto, Canada.
  • Goubran M; Sunnybrook Research Institute, University of Toronto, Toronto M4N 3M5, Canada; Department of Medical Biophysics, University of Toronto, Toronto, Canada.
  • Petersen SE; NIHR Biomedical Research Centre at Barts, Queen Mary University of London, London, UK.
  • Piechnik SK; Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford, UK.
  • Neubauer S; Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford, UK.
  • Wright G; Sunnybrook Research Institute, University of Toronto, Toronto M4N 3M5, Canada; Department of Medical Biophysics, University of Toronto, Toronto, Canada.
Med Image Anal ; 61: 101636, 2020 04.
Article em En | MEDLINE | ID: mdl-31972427
Cardiac magnetic resonance imaging (MRI) provides a wealth of imaging biomarkers for cardiovascular disease care and segmentation of cardiac structures is required as a first step in enumerating these biomarkers. Deep convolutional neural networks (CNNs) have demonstrated remarkable success in image segmentation but typically require large training datasets and provide suboptimal results that require further improvements. Here, we developed a way to enhance cardiac MRI multi-class segmentation by combining the strengths of CNN and interpretable machine learning algorithms. We developed a continuous kernel cut segmentation algorithm by integrating normalized cuts and continuous regularization in a unified framework. The high-order formulation was solved through upper bound relaxation and a continuous max-flow algorithm in an iterative manner using CNN predictions as inputs. We applied our approach to two representative cardiac MRI datasets across a wide range of cardiovascular pathologies. We comprehensively evaluated the performance of our approach for two CNNs trained with various small numbers of training cases, tested on the same and different datasets. Experimental results showed that our approach improved baseline CNN segmentation by a large margin, reduced CNN segmentation variability substantially, and achieved excellent segmentation accuracy with minimal extra computational cost. These results suggest that our approach provides a way to enhance the applicability of CNN by enabling the use of smaller training datasets and improving the segmentation accuracy and reproducibility for cardiac MRI segmentation in research and clinical patient care.
Assuntos
Palavras-chave

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Imageamento por Ressonância Magnética / Interpretação de Imagem Assistida por Computador / Doenças Cardiovasculares / Redes Neurais de Computação Idioma: En Ano de publicação: 2020 Tipo de documento: Article

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Imageamento por Ressonância Magnética / Interpretação de Imagem Assistida por Computador / Doenças Cardiovasculares / Redes Neurais de Computação Idioma: En Ano de publicação: 2020 Tipo de documento: Article