The image foresting transform: theory, algorithms, and applications

Falcão, Alexandre X.; Stolfi, Jorge; Lotufo, Roberto de Alencar

doi:10.1109/tpami.2004.1261076

Cited by 529 publications

(492 citation statements)

References 45 publications

(104 reference statements)

Supporting

Mentioning

374

Contrasting

Unclassified

Order By: Relevance

“…Axial images were uploaded for sliceby-slice segmentation performed using inhouse software developed at our institution. The software uses a graphbased technique to identify the endosteal boundary of the radius (29). The area inside the endosteal perimeter (i.e., cortical bone excluded) served as the region of interest for each slice.…”

Section: Mrimentioning

confidence: 99%

Association of larger holes in the trabecular bone at the distal radius in postmenopausal women with type 2 diabetes mellitus compared to controls

Pritchard¹,

Giangregorio²,

Atkinson³

et al. 2011

Arthritis Care & Research

View full text Add to dashboard Cite

Objective. Adults with type 2 diabetes mellitus (DM) have an elevated fracture risk despite normal areal bone mineral density (aBMD). The study objective was to compare trabecular bone microarchitecture of postmenopausal women with type 2 DM and women without type 2 DM.Methods. An extremity 1T magnetic resonance imaging system was used to acquire axial images (195 ؋ 195 ؋ 1,000 m 3 voxel size) of the distal radius of women recruited from outpatient clinics or by community advertisement. Image segmentation yielded geometric, topologic, and stereologic outcomes, i.e., number and size of trabecular bone network holes (marrow spaces), endosteal area, trabecular bone volume fraction, nodal and branch density, and apparent trabecular thickness, separation, and number. Lumbar spine (LS) and proximal femur BMD were measured with dual x-ray absorptiometry. Microarchitectural differences were assessed using linear regression and adjusted for percent body fat, ethnicity, timed up-and-go test, Charlson Index, and calcium and vitamin D intake; aBMD differences were adjusted for body mass index (BMI). Results. Women with type 2 DM (n ‫؍‬ 30, mean ؎ SD age 71.0 ؎ 4.8 years) had larger holes (؉13.3%; P ‫؍‬ 0.001) within the trabecular bone network than women without type 2 DM (n ‫؍‬ 30, mean ؎ SD age 70.7 ؎ 4.9 years). LS aBMD was greater in women with type 2 DM; however, after adjustment for BMI, LS aBMD did not differ between groups. Conclusion. In women with type 2 DM, the average hole size within the trabecular bone network at the distal radius is greater compared to controls. This may explain the elevated fracture risk in this population.

show abstract

Section: Mrimentioning

confidence: 99%

Association of larger holes in the trabecular bone at the distal radius in postmenopausal women with type 2 diabetes mellitus compared to controls

Pritchard¹,

Giangregorio²,

Atkinson³

et al. 2011

Arthritis Care & Research

View full text Add to dashboard Cite

show abstract

“…The training forest becomes a classifier which can assign to any new sample the label of its most strongly connected root. Essentially, this methodology extends a previous approach, called Image Foresting Transform [8], for the design of image processing operators from the image domain to the feature space.…”

Section: Pattern Recognition By Optimum-path Forestmentioning

confidence: 93%

Precipitates Segmentation from Scanning Electron Microscope Images through Machine Learning Techniques

Papa

Pereira

Albuquerque

et al. 2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. The presence of precipitates in metallic materials affects its durability, resistance and mechanical properties. Hence, its automatic identification by image processing and machine learning techniques may lead to reliable and efficient assessments on the materials. In this paper, we introduce four widely used supervised pattern recognition techniques to accomplish metallic precipitates segmentation in scanning electron microscope images from dissimilar welding on a Hastelloy C-276 alloy: Support Vector Machines, Optimum-Path Forest, Self Organizing Maps and a Bayesian classifier. Experimental results demonstrated that all classifiers achieved similar recognition rates with good results validated by an expert in metallographic image analysis.

show abstract

“…The prototypes are marked as the connected samples from different classes in a minimum spanning tree (MST) computed over the training set; as the arc-weights encode the distance between samples, the MST algorithm enforces the edges with lowest weights to be part of it, thus connecting samples with minimum distance. Therefore, after computing the prototypes, we can start the competition process using some smooth path-cost function, that is a function that obeys some properties [6]. The path-cost function adopted by the OPF version used in this work is the same as used by Papa et al [29,28], which computes the maximum arc-weight along a path between two samples.…”

Section: Optimum-path Forestmentioning

confidence: 99%

Swarm-based Descriptor Combination and its Application for Image Classification

Mansano¹,

Matsuoka²,

Abiuzzi³

et al. 2014

ELCVIA

View full text Add to dashboard Cite

In this paper, we deal with the descriptor combination problem in image classification tasks. This problem refers to the definition of an appropriate combination of image content descriptors that characterize different visual properties, such as color, shape and texture. In this paper, we propose to model the descriptor combination as a swarm-based optimization problem, which finds out the set of parameters that maximizes the classification accuracy of the Optimum-Path Forest (OPF) classifier. In our model, a descriptor is seen as a pair composed of a feature extraction algorithm and a suitable distance function. Our strategy here is to combine distance scores defined by different descriptors, as well as to employ them to weight OPF edges, which connect samples in the feature space. An extensive evaluation of several swarm-based optimization techniques was performed. Experimental results have demonstrated the robustness of the proposed combination approach.

show abstract

The image foresting transform: theory, algorithms, and applications

Cited by 529 publications

References 45 publications

Association of larger holes in the trabecular bone at the distal radius in postmenopausal women with type 2 diabetes mellitus compared to controls

Association of larger holes in the trabecular bone at the distal radius in postmenopausal women with type 2 diabetes mellitus compared to controls

Precipitates Segmentation from Scanning Electron Microscope Images through Machine Learning Techniques

Swarm-based Descriptor Combination and its Application for Image Classification

Contact Info

Product

Resources

About