Fully automatic and fast segmentation of the femur bone from 3D-CT images with no shape prior

Krčah, Marcel; Székely, Gábor; Blanc, Rémi

doi:10.1109/isbi.2011.5872823

Cited by 67 publications

(73 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The CT bone models were constructed using an automated graph-cut segmentation method [15,16]. The reconstructed bone models included approximately 15 cm of both the distal femur and proximal tibia.…”

Section: Ct Bone Modelmentioning

confidence: 99%

Reconstructing the anterolateral ligament does not decrease rotational knee laxity in ACL-reconstructed knees

Stentz-Olesen

Nielsen

Raedt

et al. 2017

Knee Surg Sports Traumatol Arthrosc

View full text Add to dashboard Cite

show abstract

Section: Ct Bone Modelmentioning

confidence: 99%

Reconstructing the anterolateral ligament does not decrease rotational knee laxity in ACL-reconstructed knees

Stentz-Olesen

Nielsen

Raedt

et al. 2017

Knee Surg Sports Traumatol Arthrosc

View full text Add to dashboard Cite

show abstract

“…Due to the absence of the source code for the state of the art methods such as [6] and [7] a fair comparison would be difficult specially with variety of parameter choices available. The Dice coefficient of each sample of 9 volumetric images has been calculated.…”

Section: Feature Extraction Using the Pressure Analogymentioning

confidence: 99%

“…Other methods relied on initial parameters chosen by an operator to refine boundary information between the acetabulum and the femoral bone [5]. There are two automated approaches to bone segmentation in the literature, one is based on the graphcut method using statistical analysis and morphology [6] and the other one hinged on local adaptive thresholding conditioned on Bayesian rules [7].…”

Section: Introductionmentioning

confidence: 99%

Femur Bone Segmentation Using a Pressure Analogy

Alathari

Nixon

Bah

2014

2014 22nd International Conference on Pattern Recognition

View full text Add to dashboard Cite

Abstract-It has been recently shown that preclinical analysis of computed tomography 3D image volumes can provide essential information to find the optimal position of an implant in hip replacement procedures. In order to extract such data, proper segmentation is crucial. Many of the currently-available methods depend on manually segmented data as the first step. Inherent difficulties concern the similar density of adjacent structures, and that physically-separated structures appear to touch in scanned imagery. In this study, we describe a new technique based on pressure analogy that depends on the local features of the image to accurately and automatically segment and visualize the femur bone and separate it from the acetabulum. The Dice coefficient was employed to study the similarity between the surface area of the segmentations compared with the manually segmented data, and a high value has been achieved. The same method also showed promising results in segmenting other limbs such as the pelvis, tibia and fibula bones.

show abstract

“…In this context, we focus in this paper on the rib cage segmentation, required to study car crash-induced thoracic injuries, which are life threatening and remain among occupant safety priorities for car manufacturers. Regarding bone segmentation on CT images, a variety of approaches have been derived to extract large bones such as the tibia or the femur [1,2,3] and small bones such as vertebrae [4,5]. However, ribs turn out to be particularly challenging for existing automatic segmentation techniques.…”

Section: Introductionmentioning

confidence: 99%

Accurate and robust shape descriptors for the identification of RIB cage structures in CT-images with Random Forests

Gargouri

Tierny

Jolivet

et al. 2013

2013 IEEE 10th International Symposium on Biomedical Imaging

View full text Add to dashboard Cite

This paper presents a new automatic technique for the segmentation of the rib cage on CT images. Motivated by a usage scenario in the context of large, heterogeneous databases of CT-images, we introduce two shape descriptors to be used in conjunction with a Random Forests (RF) classifier. These descriptors were specifically designed to address the challenges of rib identification under various acquisition conditions affecting subject's orientation and image quality. Extensive experiments demonstrate the superiority of our proposed shape descriptors in nominal configurations. Robustness with respect to subject's orientation variation and additive noise is also demonstrated, with an improvement of classification performance of up to 25%, comparing to intensity-based descriptors, without neither pre-registration nor pre-smoothing.

show abstract

Fully automatic and fast segmentation of the femur bone from 3D-CT images with no shape prior

Cited by 67 publications

References 9 publications

Reconstructing the anterolateral ligament does not decrease rotational knee laxity in ACL-reconstructed knees

Reconstructing the anterolateral ligament does not decrease rotational knee laxity in ACL-reconstructed knees

Femur Bone Segmentation Using a Pressure Analogy

Accurate and robust shape descriptors for the identification of RIB cage structures in CT-images with Random Forests

Contact Info

Product

Resources

About