Accurate Bone Segmentation in 2D Radiographs Using Fully Automatic Shape Model Matching Based On Regression-Voting

Lindner, Claudia; Thiagarajah, S; Wilkinson, J. Mark; Wallis, Gillian A.; Cootes, Timothy F.

doi:10.1007/978-3-642-40763-5_23

Cited by 21 publications

(34 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [10], we demonstrated that the proposed method generalises well across medical application areas, achieving what we believe to be the best published results for proximal femur and knee joint segmentation. For facial feature point detection, we would like to point out that although the approach was demonstrated on frontal faces, it would be equally applicable to non-frontal faces, given a suitable training set. "…”

Section: Discussionsupporting

confidence: 53%

“…Preliminary outputs of this work were presented in [9] for introducing RFRV in the CLM framework and in [10] for analysing what properties of RFRV contribute to its highly accurate and robust performance. This paper expands on the latter in various ways: (i) We provide a more detailed description of RFRV and how it is used in the CLM framework.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robust and Accurate Shape Model Matching Using Random Forest Regression-Voting

Lindner

Bromiley

Ionita

et al. 2015

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

208

113

View full text Add to dashboard Cite

A widely used approach for locating points on deformable objects in images is to generate feature response images for each point, and then to fit a shape model to these response images. We demonstrate that Random Forest regression-voting can be used to generate high quality response images quickly. Rather than using a generative or a discriminative model to evaluate each pixel, a regressor is used to cast votes for the optimal position of each point. We show that this leads to fast and accurate shape model matching when applied in the Constrained Local Model framework. We evaluate the technique in detail, and compare it with a range of commonly used alternatives across application areas: the annotation of the joints of the hands in radiographs and the detection of feature points in facial images. We show that our approach outperforms alternative techniques, achieving what we believe to be the most accurate results yet published for hand joint annotation and state-of-the-art performance for facial feature point detection.

show abstract

Section: Discussionsupporting

confidence: 53%

Section: Introductionmentioning

confidence: 99%

Robust and Accurate Shape Model Matching Using Random Forest Regression-Voting

Lindner

Bromiley

Ionita

et al. 2015

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

208

113

View full text Add to dashboard Cite

show abstract

“…Each model uses regression-voting trees to predict point displacements from patches of image texture and constrains the points using a shape model. The algorithm has been used previously to find hips and knees 16 from radiographs.…”

Section: Object Detection and Shape Model Matchingmentioning

confidence: 99%

Combination of lateral and PA view radiographs to study development of knee OA and associated pain

2017

View full text Add to dashboard Cite

Knee Osteoarthritis (OA) is the most common form of arthritis, affecting millions of people around the world. The effects of the disease have been studied using the shape and texture features of bones in PosteriorAnterior (PA) and Lateral radiographs separately. In this work we compare the utility of features from each view, and evaluate whether combining features from both is advantageous. We built a fully automated system to independently locate landmark points in both radiographic images using Random Forest Constrained Local Models. We extracted discriminative features from the two bony outlines using Appearance Models. The features were used to train Random Forest classifiers to solve three specific tasks: (i) OA classification, distinguishing patients with structural signs of OA from the others; (ii) predicting future onset of the disease and (iii) predicting which patients with no current pain will have a positive pain score later in a follow-up visit. Using a subset of the MOST dataset we show that the PA view has more discriminative features to classify and predict OA, while the lateral view contains features that achieve better performance in predicting pain, and that combining the features from both views gives a small improvement in accuracy of the classification compared to the individual views.

show abstract

“…A key first step in such analysis is often locating the outlines of the structures of interest. Recently, it has been shown that robust and accurate annotations can be automatically obtained using shape-based model matching algorithms [2,4,8,9]. Unfortunately, building such models requires accurate annotation of large numbers of points on several hundred images.…”

Section: Introductionmentioning

confidence: 99%

“…It was shown that RFRV-CLMs can successfully be applied as part of a fully automatic segmentation system to accurately and robustly segment bone shapes in 2D radiographs [8,9]. In this paper, we explore the effect of different annotation schemes on RFRV-CLM performance.…”

Section: Introductionmentioning

confidence: 99%

Learning-Based Shape Model Matching: Training Accurate Models with Minimal Manual Input

Lindner

Thomson

Cootes

2015

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. Recent work has shown that statistical model-based methods lead to accurate and robust results when applied to the segmentation of bone shapes from radiographs. To achieve good performance, modelbased matching systems require large numbers of annotations, which can be very time-consuming to obtain. Non-rigid registration can be applied to unlabelled images to obtain correspondences from which models can be built. However, such models are rarely as effective as those built from careful manual annotations, and the accuracy of the registration is hard to measure. In this paper, we show that small numbers of manually annotated points can be used to guide the registration, leading to significant improvements in performance of the resulting model matching system, and achieving results close to those of a model built from dense manual annotations. Placing such sparse points manually is much less time-consuming than a full dense annotation, allowing good models to be built for new bone shapes more quickly than before. We describe detailed experiments on varying the number of sparse points, and demonstrate that manually annotating fewer than 30% of the points is sufficient to create robust and accurate models for segmenting hip and knee bones in radiographs. The proposed method includes a very effective and novel way of estimating registration accuracy in the absence of ground truth.

show abstract

Accurate Bone Segmentation in 2D Radiographs Using Fully Automatic Shape Model Matching Based On Regression-Voting

Cited by 21 publications

References 13 publications

Robust and Accurate Shape Model Matching Using Random Forest Regression-Voting

Robust and Accurate Shape Model Matching Using Random Forest Regression-Voting

Combination of lateral and PA view radiographs to study development of knee OA and associated pain

Learning-Based Shape Model Matching: Training Accurate Models with Minimal Manual Input

Contact Info

Product

Resources

About