Active shape model based segmentation of bone structures in hip radiographs

Boukala, Nabil; Favier, Eric; Laget, Bernard; Radeva, Petia

doi:10.1109/icit.2004.1490821

Cited by 16 publications

(13 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two specific learning-based algorithms, Active Shape Model (ASM) and Active Appearance Model (AAM), have proven successful in segmenting CT, MRI, and x-ray images [5,11,2]. Boukala [4] successfully applied the ASM algorithm to pelvic x-rays; however, individual structures were not segmented, and the focus was on pathological deformities in hip replacement patients, rather than pelvic fractures sustained in traumatic injury. …”

Section: Prior Workmentioning

confidence: 99%

Automated segmentation of pelvic bone structure in x-ray radiographs using active shape models and directed Hough transform

Smith

Najarian

2008

2008 IEEE International Conference on Bioinformatics and Biomeidcine Workshops

View full text Add to dashboard Cite

Traumatic pelvic injuries are often associated with severe, life-threatening hemorrhage, and immediate medical treatment is therefore vital. However, patient prognosis depends heavily on the type, location and severity of the bone fracture. Detecting these fractures can prove challenging for physicians due to the complexity of the pelvic bone structure, but is vital in identifying the most severe cases. X-ray imaging is fast and requires disruption to the patient, and is an important initial diagnostic step upon a patient's admission. Therefore, automated fracture detection from initial patient x-rays can assist physicians in diagonsis and treatment. However, fractures in different areas of the pelvis display different characteristics in x-ray images. As a first and crucial step, the separate structures within the pelvisin particular, the ilium and left and right acetabulum -must therefore be correctly segmented and identified in the x-ray image. This paper describes a algorithm for segmentation of these structures, using a hierarchical approach that combines directed Hough transform and Active Shape models. Unlike various other x-ray segmentation methods, the algorithm presented here both handles the inconsistencies between x-ray images in a clinical environment, and performs successfully in the presence of fracture.

show abstract

Section: Prior Workmentioning

confidence: 99%

Automated segmentation of pelvic bone structure in x-ray radiographs using active shape models and directed Hough transform

Smith

Najarian

2008

2008 IEEE International Conference on Bioinformatics and Biomeidcine Workshops

View full text Add to dashboard Cite

show abstract

“…Mean contour errors from up to 12 mm [10] down to about 1.5 mm [7], [12] have been reported. Current approaches based on Active Shape Models (ASM) rely on a single image feature for delineation.…”

Section: A Active Shape Modelsmentioning

confidence: 99%

“…Various segmentation techniques to solve this task have been proposed, including template-based registration [6], level-set segmentation [7], geometric approaches [8], Active Contours [9] and Active Shape Models [10], [11], [12]. Mean contour errors from up to 12 mm [10] down to about 1.5 mm [7], [12] have been reported.…”

Section: A Active Shape Modelsmentioning

confidence: 99%

Intelligent feature selection for model-based bone segmentation in digital radiographs

Gooβen

Peters

Gernoth

et al. 2009

2009 9th International Conference on Information Technology and Applications in Biomedicine

View full text Add to dashboard Cite

In the following two subsections we briefly review the segmentation using Active Shape Models (ASM) and some proposed extensions [13], [14], [15]. Afterwards we introduce our proposed intelligent feature selection and finally show how to incorporate it into the segmentation. with x =~L~l Xj denoting the mean shape of the m aligned training shapes and b denoting a weighting of the t eigenvectors. By varying the elements of b we can vary the shape x. To approximate a new target shape y, we have to fit the model parameters to minimize the distance between the target shape y and the fitted shape x. We remove rigid differences between y and x by rotation, translation and scaling and subsequently estimate the parameters b, i.e, To restrict the deformation to plausible shapes, we apply constraints to the parameters, e.g. Ilbkll < 3JXk, k = 1,2, ... ,t.

show abstract

“…• Detecting cancerous bone [8] • Calculating cortical bone mineralization using segmentation of osteons and interstitial tissue [9] • Relating osteon geometry to age, sex, height, and weight [10] • Relating bone mineralization changes to age and sex [11] • Segmenting bone structures in anterior-posterior radiographs on the basis of active shape models [12] • Measuring cartilage tissue using shape-based segmentation for bones [13].…”

Section: Introductionmentioning

confidence: 99%

Geometric-attributes-based segmentation of cortical bone slides using optimized neural networks

Hage

Hamade

2015

J Bone Miner Metab

View full text Add to dashboard Cite

In cortical bone, solid (lamellar and interstitial) matrix occupies space left over by porous microfeatures such as Haversian canals, lacunae, and canaliculi-containing clusters. In this work, pulse-coupled neural networks (PCNN) were used to automatically distinguish the microfeatures present in histology slides of cortical bone. The networks' parameters were optimized using particle swarm optimization (PSO). When forming the fitness functions for the PSO, we considered the microfeatures' geometric attributes-namely, their size (based on measures of elliptical perimeter or area), shape (based on measures of compactness or the ratio of minor axis length to major axis length), and a two-way combination of these two geometric attributes. This hybrid PCNN-PSO method was further enhanced for pulse evaluation by combination with yet another method, adaptive threshold (AT), where the PCNN algorithm is repeated until the best threshold is found corresponding to the maximum variance between two segmented regions. Together, this framework of using PCNN-PSO-AT constitutes, we believe, a novel framework in biomedical imaging. Using this framework and extracting microfeatures from only one training image, we successfully extracted microfeatures from other test images. The high fidelity of all resultant segments was established using quantitative metrics such as precision, specificity, and Dice indices.

show abstract

Active shape model based segmentation of bone structures in hip radiographs

Cited by 16 publications

References 13 publications

Automated segmentation of pelvic bone structure in x-ray radiographs using active shape models and directed Hough transform

Automated segmentation of pelvic bone structure in x-ray radiographs using active shape models and directed Hough transform

Intelligent feature selection for model-based bone segmentation in digital radiographs

Geometric-attributes-based segmentation of cortical bone slides using optimized neural networks

Contact Info

Product

Resources

About