Binary segmentation of medical images using implicit spline representations and deep learning
Barrowclough, Oliver Joseph David; Muntingh, Agnar Georg Peder; Nainamalai, Varatharajan; Stangeby, Ivar Haugaløkken
Peer reviewed, Journal article
Published version
Permanent lenke
https://hdl.handle.net/11250/2995695Utgivelsesdato
2021Metadata
Vis full innførselSamlinger
- Publikasjoner fra CRIStin - SINTEF AS [5638]
- SINTEF Digital [2381]
Sammendrag
We propose a novel approach to image segmentation based on combining implicit spline representations with deep convolutional neural networks. This is done by predicting the control points of a bivariate spline function whose zero-set represents the segmentation boundary. We adapt several existing neural network architectures and design novel loss functions that are tailored towards providing implicit spline curve approximations. The method is evaluated on a congenital heart disease computed tomography medical imaging dataset. Experiments are carried out by measuring performance in various standard metrics for different networks and loss functions. We determine that splines of bidegree (1, 1) with 128 × 128 coefficient resolution performed optimally for 512 × 512 resolution CT images. For our best network, we achieve an average volumetric test Dice score of close to 92%, which reaches the state of the art for this congenital heart disease dataset.