Two tree-based methods for the waterfall

Golodetz, Stuart; Nicholls, Christopher; Voiculescu, Irina; Cameron, Stephen

doi:10.1016/j.patcog.2014.04.017

Cited by 10 publications

(11 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Nor do we believe it would significantly increase the processing time of the semi‐automated method. The addition of these features is something we intend to establish as part of our methodology in further work to optimize our semi‐automated segmentation technique . This would allow the biochemical and morphological analysis of specific areas of cartilage between patients and within patients over time.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Segmentation of hip cartilage in compositional magnetic resonance imaging: A fast, accurate, reproducible, and clinically viable semi‐automated methodology

Fernquest

Park

Marčan

et al. 2018

Journal Orthopaedic Research

View full text Add to dashboard Cite

Manual segmentation is a significant obstacle in the analysis of compositional MRI for clinical decision-making and research. Our aim was to produce a fast, accurate, reproducible, and clinically viable semi-automated method for segmentation of hip MRI. We produced a semi-automated segmentation method for cartilage segmentation of hip MRI sequences consisting of a two step process: (i) fully automated hierarchical partitioning of the data volume generated using a bespoke segmentation approach applied recursively, followed by (ii) user selection of the regions of interest using a region editor. This was applied to dGEMRIC scans at 3T taken from a prospective longitudinal study of individuals considered at high-risk of developing osteoarthritis (SibKids) which were also manually segmented for comparison. Fourteen hips were segmented both manually and using our semi-automated method. Per hip, processing time for semi-automated and manual segmentation was 10-15, and 60-120 min, respectively. Accuracy and Dice similarity coefficient (DSC) for the comparison of semi-automated and manual segmentations was 0.9886 and 0.8803, respectively. Intra-observer and inter-observer reproducibility of the semi-automated segmentation method gave an accuracy of 0.9997 and 0.9991, and DSC of 0.9726 and 0.9354, respectively. We have proposed a fast, accurate, reproducible, and clinically viable semi-automated method for segmentation of hip MRI sequences. This enables accurate anatomical and biochemical measurements to be obtained quickly and reproducibly. This is the first such method that shows clinical applicability, and could have large ramifications for the use of compositional MRI in research and clinically. ß

show abstract

Section: Discussionmentioning

confidence: 99%

“…). The selection of an anatomical region of interest, in this case the cartilage, can span across several layers of the hierarchy …”

Section: Methodsmentioning

confidence: 99%

Segmentation of hip cartilage in compositional magnetic resonance imaging: A fast, accurate, reproducible, and clinically viable semi‐automated methodology

Fernquest

Park

Marčan

et al. 2018

Journal Orthopaedic Research

View full text Add to dashboard Cite

show abstract

“…the nodes in the lowest level of the tree) are the actual pixels/voxels of the image. 8,9 The IPF consists of several levels of nodes with each higher level containing fewer regions than the previous one. In the scope of the graphical user interface designed to facilitate the running of the algorithm the levels of regions are called layers.…”

Section: Materials and Methods Image Partition Forestmentioning

confidence: 99%

“…Voxels are grouped into regions of similar intensity value; then groups are re-grouped into larger regions, thus creating a hierarchical structure that we have named Image Partition Forest (IPF), the construction of which we have described elsewhere. 8 The IPF is then analysed in order to identify relevant features (such as bones, organs or blood vessels). This method has previously been thoroughly tested on abdominal CT images, with good results.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised segmentation of MRI knees using image partition forests

Marčan

Voiculescu

2016

SPIE Proceedings

View full text Add to dashboard Cite

Nowadays many people are affected by arthritis, a condition of the joints with limited prevention measures, but with various options of treatment the most radical of which is surgical. In order for surgery to be successful, it can make use of careful analysis of patient-based models generated from medical images, usually by manual segmentation. In this work we show how to automate the segmentation of a crucial and complex joint -the knee. To achieve this goal we rely on our novel way of representing a 3D voxel volume as a hierarchical structure of partitions which we have named Image Partition Forest (IPF). The IPF contains several partition layers of increasing coarseness, with partitions nested across layers in the form of adjacency graphs. On the basis of a set of properties (size, mean intensity, coordinates) of each node in the IPF we classify nodes into different features. Values indicating whether or not any particular node belongs to the femur or tibia are assigned through node filtering and node-based region growing. So far we have evaluated our method on 15 MRI knee images. Our unsupervised segmentation compared against a hand-segmented gold standard has achieved an average Dice similarity coefficient of 0.95 for femur and 0.93 for tibia, and an average symmetric surface distance of 0.98 mm for femur and 0.73 mm for tibia. The paper also discusses ways to introduce stricter morphological and spatial conditioning in the bone labelling process.

show abstract

“…It is because such decision should be made after considering all the weights of the edges of the graph, but it is computationally expensive. We propose a simplified merging approach in which a graph is transformed into a tree as suggested in [35]. By using the tree, the process to find nodes to be merged can be simplified.…”

Section: Depth First Seearch Based Region Mergingmentioning

confidence: 99%

Depth-First-Search Based Region Merging for the Waterfall

Jun

2015

2015 11th International Conference on Signal-Image Technology &Amp; Internet-Based Systems (SITIS)

View full text Add to dashboard Cite

Watershed transformation is a popular method to segment regions in an image. After being proposed in 70's, it has been evolved in various ways. However, the problem of over-segmentation still remains because the existing approaches are computationally expensive; they apply a waterfall technique to the result of the watershed transformation, merging similar regions. The merging requires navigating the graph representing regions and their neighboring relationship. In this paper, we propose to improve navigation and merging process by transforming the graph into a tree and using the depth-first-search. The proposed method was able to simplify the region merging process while producing similar results.

show abstract

Two tree-based methods for the waterfall

Cited by 10 publications

References 37 publications

Segmentation of hip cartilage in compositional magnetic resonance imaging: A fast, accurate, reproducible, and clinically viable semi‐automated methodology

Segmentation of hip cartilage in compositional magnetic resonance imaging: A fast, accurate, reproducible, and clinically viable semi‐automated methodology

Unsupervised segmentation of MRI knees using image partition forests

Depth-First-Search Based Region Merging for the Waterfall

Contact Info

Product

Resources

About