Automatic deformable surface registration for medical applications by radial basis function-based robust point-matching

Kim, Young‐Jun; Na, Yong Hum; Li, Xing; Lee, Rena; Park, Sehyung

doi:10.1016/j.compbiomed.2016.07.013

Cited by 8 publications

(9 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After rigidly aligning the resulting vector displacements and mapping source vertices to the target mesh, non-rigid registration of the source mesh onto the target mesh is applied. In a first step we approximate remaining vector displacements mapping source vertices to the target mesh using a non-rigid transformation, modelled as a sum of N c Gaussian Radial Basis Functions (G-RBF) with variable γ defining the width of the Gaussian function (Carr et al 2001;Chui and Rangarajan 2003;de Boer et al 2007;Kim et al 2016):…”

Section: Dense Landmarking Of Manual Segmentationsmentioning

confidence: 99%

Cascaded statistical shape model based segmentation of the full lower limb in CT

Audenaert

Houcke

Almeida

et al. 2019

Computer Methods in Biomechanics and Biomedical Engineering

View full text Add to dashboard Cite

Image segmentation has become an important tool in orthopedic and biomechanical research. However, it greatly remains a time-consuming and laborious task. In this manuscript, we propose a fully automatic model-based segmentation pipeline for the full lower limb in computed tomography (CT) images. The method relies on prior shape model fitting, followed by a gradientdefined free from deformation. The technique allows for the generation of anatomically corresponding surface meshes, which can subsequently be applied in anatomical and mechanical simulation studies. Starting from an initial, small (n ≤ 10) sample of manual segmentations, the model is continuously updated and refined with newly segmented training samples. Validation of the segmentation pipeline was performed by comparing the automatic segmentations against corresponding manual segmentations. Convergence of the segmentation pipeline was obtained in 250 cases and failed in three samples. The average distance error ranged from 0.53 to 0.76 mm and maximal error ranged from 2.0 to 7.8 mm for the 7 different osteological structures that were investigated. The accuracy of the shape model-based segmentation gradually increased as the number of training shapes in the updated population also increased. When optimized with the free form deformation, however, average segmentation accuracy rapidly plateaued from already as little as 20 training samples on. The maximum segmentation error plateaued from 100 training samples on.

show abstract

Section: Dense Landmarking Of Manual Segmentationsmentioning

confidence: 99%

Cascaded statistical shape model based segmentation of the full lower limb in CT

Audenaert

Houcke

Almeida

et al. 2019

Computer Methods in Biomechanics and Biomedical Engineering

View full text Add to dashboard Cite

show abstract

“…The surface distance is lesser for surfaces registered with proposed algorithm but this can be due to smaller value of stiffness parameter alpha. Other authors using non-rigid ICP, obtaining a distance of the surface, varying within 3 orders of magnitude: from thousandth of a millimeter RMS 0.0037 mm [ 5 ], through a fraction of a millimeter RMS 0.47 mm [ 15 ] to a few millimeters RMS 1.61 mm [ 8 ] and RMS 3.39 mm [ 10 ]. Lack of information on the adopted stiffness factor makes a direct comparison of numerical values unjustified.…”

Section: Discussionmentioning

confidence: 99%

“…First, the corresponding points pairs finding stage was changed. Instead of using the plain Euclidean distance norm presented by [ 2 ], we modified the norm as equation [ 15 ] states. To calculate the correspondents distance weighting matrix , a point localization error is needed in the form of standard deviations on principal axes.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Anisotropic non-rigid Iterative Closest Point Algorithm for respiratory motion abdominal surface matching

Spińczyk

Bas

2019

BioMed Eng OnLine

View full text Add to dashboard Cite

Surface registration is a one of the crucial and actual problems of computer aided surgery. This paper presents the modification of the non-rigid Iterative Closest Point Algorithm which takes into account an anisotropic noise model and landmarks as guided correspondence at the transformation step in every iteration. The presented approach was validated on human abdominal briefing surface data from a time-of-flight camera. We took the median of the resulting measures and the outcome is presented: the median of means of surfaces distance was at the same level for both variants of the ICP algorithm and is comparable with the isotropic variant, the median of mean landmark position errors decreased by 0.93 units (over 20% improvement) and the median of percentage of single correspondences in target point cloud increased by 11.96%. The results showed that the introduction of the anisotropic model of noise for the ToF camera allows for the improvement the percentage of target cloud points which had only one correspondent over 10% impartment and additional weighting of markers also improves the measure of the quality of finding real correspondents over 20% improvement. In the examined dataset, where the average initial distance between the clouds of points in the inspiratory and expiration is equal to approx. 7.5 mm, a more than 10% improvement in the quality of the correspondence improves the accuracy of matching the surface within 1 mm which is a significant value in application of minimally invasive image guided interventions.

show abstract

“…Our study proposal included three ANNs that differed according to the basis function used: product unit neural network (PUNN) [15], sigmoid unit neural network (SUNN) [8], and finally, the radial basis function neural network (RBFNN) [16]. All these methods have been widely used in biomedicine since 1990 and are still in use today: see [17][18][19] for RBFNN, [20][21][22] for MLP or SUNN and [23,24] for PUNN. Finally, all these ANN models have been proven to be universal approximators [8].…”

Section: Introductionmentioning

confidence: 99%

Using machine learning methods to determine a typology of patients with HIV-HCV infection to be treated with antivirals

et al. 2020

View full text Add to dashboard Cite

Several European countries have established criteria for prioritising initiation of treatment in patients infected with the hepatitis C virus (HCV) by grouping patients according to clinical characteristics. Based on neural network techniques, our objective was to identify those factors for HIV/HCV co-infected patients (to which clinicians have given careful consideration before treatment uptake) that have not being included among the prioritisation criteria. This study was based on the Spanish HERACLES cohort (NCT02511496) (April-September 2015, 2940 patients) and involved application of different neural network models with different basis functions (product-unit, sigmoid unit and radial basis function neural networks) for automatic classification of patients for treatment. An evolutionary algorithm was used to determine the architecture and estimate the coefficients of the model. This machine learning methodology found that radial basis neural networks provided a very simple model in terms of the number of patient characteristics to be considered by the classifier (in this case, six), returning a good overall classification accuracy of 0.767 and a minimum sensitivity (for the classification of the minority class, untreated patients) of 0.550. Finally, the area under the ROC curve was 0.802, which proved to be exceptional. The parsimony of the model makes it especially attractive, using just eight connections. The independent variable "recent PWID" is compulsory due to its importance. The simplicity of the model means that it is possible to analyse the relationship between patient characteristics and the probability of belonging to the treated group.

show abstract

Automatic deformable surface registration for medical applications by radial basis function-based robust point-matching

Cited by 8 publications

References 31 publications

Cascaded statistical shape model based segmentation of the full lower limb in CT

Cascaded statistical shape model based segmentation of the full lower limb in CT

Anisotropic non-rigid Iterative Closest Point Algorithm for respiratory motion abdominal surface matching

Using machine learning methods to determine a typology of patients with HIV-HCV infection to be treated with antivirals

Contact Info

Product

Resources

About