Improved watershed transform for medical image segmentation using prior information

By Vicente Grau, A. Mewes, Mariano Alcañiz Raya, Ron Kikinis, Simon Keith Warfield. 2004

821 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Medical Imaging

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

In Medical Imaging

Citations in the corpus

Deep Watershed Transform for Instance Segmentation (2016, background): “One of the possible solutions is to estimate the locations of object instance markers, which guide the selection of a subset of these basins [11, 21].”
Multi-spectral brain tissue segmentation using automatically trained k-Nearest-Neighbor classification (2007, neutral): “A number of authors have previously published encouraging results when incorporating spatial information, e.g. Fischl et al. (2002) and Grau et al. (2004).”
COMPARE: Classification of Morphological Patterns Using Adaptive Regional Elements (2007, methodology): “segmentation algorithm is a traditional image segmentation approach, widely utilized in medical image analysis for partitioning images into different regions according to local intensity similarity [22], [25].”
A review of atlas-based segmentation for magnetic resonance brain images (2011, methodology): “Healthy tissue Van Leemput [76] ICBM No Affine No PA Marroquin [84] ICBM No Affine Level set PA Cocosco [91] 53 manual No Affine No PA Grau [97] 29 manual No No Demons PA Ashburner [114] ICBM No Affine Cosine PA Awate [79] ICBM No Affine No PA Vrooman [92] 22 manual No Affine B-Splines PA Bricq [82]”
Medical Image Segmentation Using K-Means Clustering and Improved Watershed Algorithm (2006, background): “Its drawbacks will include over-segmentation and sensitivity to noise [2].”
Color Image Segmentation Based on Mean Shift and Normalized Cuts (2007, background): “Given the importance of edge information, as well as the need to preserve the spatial relationship between the pixels on the image plane, there is a recent tendency to handle images in the spatial domain [11], [28].”
AUTOMATIC SEGMENTATION OF NUCLEI IN 3D MICROSCOPY IMAGES OF C.ELEGANS (2007, methodology): “Watershed algorithm has been demonstrated more suitable for segmenting biological images [2-4].”
Understanding Deep Learning Techniques for Image Segmentation (2019, background): “s [47]. Simulated annealing [124] can be an apt example in this regard as well. These approaches can choose to partition graphs based on their energy. Watershed transformations : Watershed algorithms [73] assumes the gradients of an image as a topographic surface. Analogous to the water ow lines in ”
Significantly Fast and Robust Fuzzy C-Means Clustering Algorithm Based on Morphological Reconstruction and Membership Filtering (2018, methodology): “The technologies of image segmentation involve clustering [7], [8], region growth [9], watershed transform [10], active contour model [11], MeanShift [12], Graph Cut [13], spectral clustering [14], Markov random ﬁeld [15], neural network [16], etc.”
Hierarchical Fully Convolutional Network for Joint Atrophy Localization and Alzheimer’s Disease Diagnosis using Structural MRI (2018, methodology): “Fan et al. [12] adopted the watershed algorithm [44] to group sMRI voxels into an adaptive set of brain regions, from which regional volumetric features were extracted to perform SVM-based AD clas-siﬁcation.”
A review of algorithms for medical image segmentation and their applications to the female pelvic cavity (2010, methodology): “Typical examples are watershed algorithms (Beucher and Lantuéjoul 1979; Vincent and Soille 1991; Grau et al. 2004; Ng et al. 2006; Hamarneh and Li 2009) which combine image intensity with gradient information and use mathematical morphology operations to do the segmentation.”
Image Segmentation Using Active Contours Driven by the Bhattacharyya Gradient Flow (2007, background): “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],…”
Medical image registration: a review (2014, methodology): “Examples of region-based techniques are: thresholding methods (Wellner 1993; Otsu 1979), watershed (Beucher 1991; Grau et al. 2004) and region growing (Adams and Bischof 1994).”
Artificial intelligence in radiology (2018, neutral): “A second generation of algorithms saw the incorporation of statistical learning and optimization methods to improve segmentation precision, such as the watershed algorithm, where images are transformed into topological maps with intensities representing heights 49 .”
Comparison and validation of tissue modelization and statistical classification methods in T1-weighted MR brain images (2005, methodology): “[30] proposed an improved watershed method using prior information and they compare their approach for WM and GM segmentation with the methods of Van Leemput et al.”