A shape-based approach to the segmentation of medical imagery using level sets

By Andy Tsai, Anthony J. Yezzi Jr., William M. Wells, Clare M. Tempany, Dewey Tucker, Ayres C. Fan, W. Grimson, Alan S. Willsky. IEEE Transactions on Medical Imaging, 2003

1,034 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/6c1dd6093f172f02c36015fa3bc20f7579551bc4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Edge and line oriented contour detection: State of the art (2011, methodology): “The easiest way to face this problem is by PCA or ICA, but the assumption of linearity is often too simplistic (see also the discussion in [217]).”
Simultaneous Monocular 2D Segmentation, 3D Pose Recovery and 3D Reconstruction (2012, methodology): “In [8] for example, principal component analysis (PCA) is used to capture the variance in the space of shapes.”
Medical Image Segmentation Using Deep Learning: A Survey (2020, methodology): “[16] proposed a shape based approach using horizontal sets for 2D segmentation of cardiac MRI images and 3D segmentation of prostate MRI images.”
A survey on level set methods for inverse problems and optimal design (2005, methodology): “The segmentation of medical images by level set methods has been investigated by several authors [50, 75, 94, 111, 139].”
A Bayesian model for joint segmentation and registration (2006, neutral): “www.elsevier.com/locate/ynimg NeuroImage 31 (2006) 228 – 239”
A Review of Statistical Approaches to Level Set Segmentation: Integrating Color, Texture, Motion and Shape (2007, background): “[86, 88] proposed a very efficient implementation of shape-driven level set segmentation by directly optimizing in the linear subspace spanned by the principal components.”
Approaches for automated detection and classification of masses in mammograms (2006, neutral): “The level set approach is widely used in medical image analysis [200].”
A review of segmentation methods in short axis cardiac MR images (2011, methodology): “An alternative to the use of a PDE is proposed in (Tsai et al., 2003; Kaus et al., 2004), with the advantage of being fast and direct, based on a preliminary PCA on the training data.”
A fast learning algorithm for image segmentation with max-pooling convolutional networks (2013, methodology): “by enforcing smooth boundaries through filtering and thresholding, or by using techniques such as graph cuts [1] or level sets [2]).”
Segmentation by transduction (2008, methodology): “It includes completely automated methods [8, 10, 22, 25], semi-supervised methods [4, 12, 11, 9, 13, 17, 23, 1], and model-driven approaches [18, 20, 26], among many others.”
Customized Segment Anything Model for Medical Image Segmentation (2023, methodology): “Early medical image segmentation methods empirically adopt explicit contour features [32] or Markov random field [11] to obtain decent performance.”
CE-Net: Context Encoder Network for 2D Medical Image Segmentation (2019, methodology): “The shape-based method using level sets [25] has been proposed for two-dimensional segmentation of cardiac MRI images and three-dimensional segmentation of prostate MRI images.”
Image Segmentation Using Active Contours Driven by the Bhattacharyya Gradient Flow (2007, methodology): “Thus, for example, the object may be associated with a diseased organ in medical imaging [1], [2], an intruder in surveillance video [3], [4], a moving part of a machine in robotics [5], [6], a maneuvering vehicle in trafﬁc control [7], [8], or a target in navigation and military applications [9],…”
TouchCut: Fast image and video segmentation using single-touch interaction (2014, methodology): “Finally, our proposed model also utilizes the geometric cue implied in single-touch input, that users typically touch image in close vicinity to the geometric center of the desired object.”
A Nonrigid Kernel-Based Framework for 2D-3D Pose Estimation and 2D Image Segmentation (2011, positive): “This has resulted in the proposed use of a shape prior to restrict the evolution of the active contour [26], [12], [10], [14], [47].”
Dense Reconstruction Using 3D Object Shape Priors (2013, methodology): “1Though the trimaps could be learned from good segmentations of training data, in practice we crafted these trimaps manually such as PCA [24] or kPCA [6].”
Comparison of quantitative methods for cell‐shape analysis (2007, methodology): “…applied to 2-and 3D data sets of the shapes of various anatomical structures (represented as either signed distance maps (Leventon et al. , 2000; Tsai et al. , 2003) or sets of ‘landmark’ points known to correspond to one another (Cootes et al. , 1993; Baumberg & Hogg, 1995)) to for the purpose…”