Knee bone segmentation from MRI: A classification and literature review

Aprovitola, Andrea; Gallo, Luigi

doi:10.1016/j.bbe.2015.12.007

Cited by 37 publications

(38 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Automatic and semiautomatic segmentation algorithms provide more consistent labels of the knee structures in a shorter time than manual segmentation . For segmenting the knee bones and cartilages, many advanced techniques have been proposed, including but not limited to, deformable models, graph‐based methods, and voxel classification approaches . In fact, successful approaches often combine several of these techniques into rather complex systems.…”

mentioning

confidence: 99%

“…25 For segmenting the knee bones and cartilages, many advanced techniques have been proposed, including but not limited to, deformable models, graph-based methods, and voxel classification approaches. 25,26 In fact, successful approaches often combine several of these techniques into rather complex systems. More recently, deep-learning techniques 27,28 have reduced the complexity by rendering many preprocessing steps unnecessary, but for accurate and robust segmentation they require large training databases.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Quantification of patellofemoral cartilage deformation and contact area changes in response to static loading via high‐resolution MRI with prospective motion correction

Lange

Taghizadeh

Knowles

et al. 2019

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Background Higher‐resolution MRI of the patellofemoral cartilage under loading is hampered by subject motion since knee flexion is required during the scan. Purpose To demonstrate robust quantification of cartilage compression and contact area changes in response to in situ loading by means of MRI with prospective motion correction and regularized image postprocessing. Study Type Cohort study. Subjects Fifteen healthy male subjects. Field Strength 3 T. Sequence Spoiled 3D gradient‐echo sequence augmented with prospective motion correction based on optical tracking. Measurements were performed with three different loads (0/200/400 N). Assessment Bone and cartilage segmentation was performed manually and regularized with a deep‐learning approach. Average patellar and femoral cartilage thickness and contact area were calculated for the three loading situations. Reproducibility was assessed via repeated measurements in one subject. Statistical Tests Comparison of the three loading situations was performed by Wilcoxon signed‐rank tests. Results Regularization using a deep convolutional neural network reduced the variance of the quantified relative load‐induced changes of cartilage thickness and contact area compared to purely manual segmentation (average reduction of standard deviation by ∼50%) and repeated measurements performed on the same subject demonstrated high reproducibility of the method. For the three loading situations (0/200/400 N), the patellofemoral cartilage contact area as well as the mean patellar and femoral cartilage thickness were significantly different from each other (P < 0.05). While the patellofemoral cartilage contact area increased under loading (by 14.5/19.0% for loads of 200/400 N), patellar and femoral cartilage thickness exhibited a load‐dependent thickness decrease (patella: –4.4/–7.4%, femur: –3.4/–7.1% for loads of 200/400 N). Data Conclusion MRI with prospective motion correction enables quantitative evaluation of patellofemoral cartilage deformation and contact area changes in response to in situ loading. Regularizing the manual segmentations using a neural network enables robust quantification of the load‐induced changes. Level of Evidence: 2 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;50:1561–1570.

show abstract

mentioning

confidence: 99%

mentioning

confidence: 99%

Quantification of patellofemoral cartilage deformation and contact area changes in response to static loading via high‐resolution MRI with prospective motion correction

Lange

Taghizadeh

Knowles

et al. 2019

Magnetic Resonance Imaging

View full text Add to dashboard Cite

show abstract

“…4.1. Analytical representation of 2D-sinusoidal grating and its first and second partial deriavtives The empirical analysis is performed here to approximate the partial derivatives of the discrete image f by means of staggered-forward third order derivative matrix 3,128 and centralized fourth order derivative matrix ∂ 4 f /∂x 4 ≈ f D T 4,128 . The tap-length polynomial to construct the fullband differential matrices is l = 11.…”

Section: Numerical Validationmentioning

confidence: 99%

Finite Differences in Forward and Inverse Imaging Problems: MaxPol Design

Hosseini¹,

Plataniotis²

2017

SIAM J. Imaging Sci.

View full text Add to dashboard Cite

Abstract. A systematic and comprehensive framework for finite impulse response (FIR) lowpass/fullband derivative kernels is introduced in this paper. Closed form solutions of a number of derivative filters are obtained using the maximally flat technique to regulate the Fourier response of undetermined coefficients. The framework includes arbitrary parameter control methods that afford solutions for numerous differential orders, variable polynomial accuracy, centralized/staggered schemes, and arbitrary side-shift nodes for boundary formulation. Using the proposed framework four different derivative matrix operators are introduced and their numerical stability is analyzed by studying their eigenvalues distribution in the complex plane. Their utility is studied by considering two important image processing problems, namely gradient surface reconstruction and image stitching. Experimentation indicates that the new derivative matrices not only outperform commonly used method but provide useful insights to the numerical issues in these two applications.Key words. numerical differentiation, boundary condition, derivative matrix, fullband/lowpass FIR differentiation, maxflat technique, inverse Vandermonde, gradient surface recovery, image stitching 1. Introduction. Finite difference (FD) methods are used extensively in variety of image processing tasks. For example, they are used in digital approximation of order moments such as gradients, Hessian, and high-order tensor. They find numerous applications in either forward imaging problems to encode certain features such as edge and corner [11,44,60,61,64,69,78], or discretizing the differential operators used in inverse problems for image restoration [1,8,23,33,59,67,76,77]. Despite extensive applications, the problem of numerical differentiation suffers from several deficiencies such as the lack of estimation accuracy, sensitivity over perturbing artifacts, and improper formulation of boundary condition (BC). Such deficiencies can easily make the overall imaging applications highly complicated (ill-posed) and sometimes turn the whole exercise to be useless. Recent works highlight the need for a systematic and comprehensive framework of numerical differentiation to overcome these issues by reducing the complexities of error propagation in the system design and furthermore prevent computational burdens. Applications can be found in gradient surface reconstruction [30,33], edge detection [2,3,5,10], edge synthesis [22,35,81], feature extraction [16,17,30], and many more. This article concerns with the main question of what is the best numerical approach to approximate derivatives in an image processing related task? With this question in mind we present a comprehensive framework for differentiation applied in forward and inverse imaging problems. The "forward" here is referred to find a solution of direct approximation in a measurement system A(X) = Y where A is an operator and X is a given signal/image to find Y . While, the "inverse" is referred to inferring X from a simi...

show abstract

“…Segmentation of the articular cartilage is regarded as an essential and primary step in osteoarthritis (OA) quantitative analysis, and can also help clinicians assess the progress of OA treatment [1]. However, articular cartilage segmentation from magnetic resonance images (MRI) is still a challenging task due to the thinness of the cartilage, low contrast to surrounding tissues, and the tiny gaps between two cartilage elements of the same articular structure [2].…”

Section: Introductionmentioning

confidence: 99%