Quantitation of articular cartilage dimensions by computer analysis of 3D MR images of human knee joints

Kshirsagar, Ashwini; Watson, P. J.; Herrod, N. J.; Tyler, Jenny A.; Hall, Laurance D.

doi:10.1109/iembs.1997.757746

Cited by 7 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They extended the method to 3D edge detection for automatic delineation of cartilage from 3D MR images of human knee joint. Canny edge detection technique is used recursively to segment the cartilage [5]. The Canny edge detection operator returns a value for the first derivative in the horizontal direction (Gx) and the vertical direction (Gy).…”

Section: Pixel or Intensity Based Segmentation Methodsmentioning

confidence: 99%

“…In earlier method based 2D segmentation [4] the plot of cartilage thickness in mm is plotted against the distance along the femur. Topographical distribution of cartilage thickness on the surface of bones is also obtained and cartilage volume is computed [5]. To avoid local anomalies such as osteophytes, present in images from patients with OA.…”

Section: Quantification Of Cartilage Thickness and Volumementioning

confidence: 99%

See 1 more Smart Citation

Knee Joint Articular Cartilage Segmentation, Visualization and Quantification using Image Processing Techniques: A Review

Swamy¹,

Holi²

2012

IJCA

View full text Add to dashboard Cite

Knee is a complex and articulated joint of the body. Cartilage is a smooth hyaline spongy material between the tibia and femur bones of knee joint. Cartilage morphology change is an important biomarker for the progression of osteoarthritis (OA). Magnetic resonance imaging (MRI) is the modality widely used to image the knee joint because of its hazard free and high resolution soft tissue contrast. Cartilage thickness measurement and visualization is useful for early detection and progression of the disease in case of OA affected patients. A wide variety of algorithms are available for knee joint image segmentation. They are classified as pixel based and model based methods. Based on the human intervention required, segmentation methods are also classified as manual, semi-automatic and fully automatic methods. This paper reviews knee joint articular cartilage segmentation methods, visualization, thickness measurement, volume measurement and validation methods.

show abstract

Section: Pixel or Intensity Based Segmentation Methodsmentioning

confidence: 99%

Section: Quantification Of Cartilage Thickness and Volumementioning

confidence: 99%

Knee Joint Articular Cartilage Segmentation, Visualization and Quantification using Image Processing Techniques: A Review

Swamy¹,

Holi²

2012

IJCA

View full text Add to dashboard Cite

show abstract

“…This approach of using only static information cannot reflect the loads during leg movement, causing the limitation of diagnosis accuracy. To conquer this disadvantage, kinematics approaches [4] which perform the analysis using sequences of image slices taken when the legs are in the moving path, have been recommended. However, complete kinematic analysis requires the challenging work of segmenting knee organs patellar, femur and tibia which often reveal uneven gray distributions due to the degradation of magnetic propagation.…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, soft tissues are adhered around the patellar and femur increasing the segmentation difficulty. Due to all these difficulties, traditional kinematic approaches [4] measure only the caltriage thickness in the moving path as the analysis criterion. As we know, dislocation reveals much more on the changes of relative position and orientation than the tissue thickness.…”

Section: Introductionmentioning

confidence: 99%

An automatic detection algorithm of MR images for knee pain problem

Chung

Chou

Tan

et al. 2007

TENCON 2007 - 2007 IEEE Region 10 Conference

View full text Add to dashboard Cite

Anterior knee pain (AKP) is a common pathological condition. The problem causing knee pain is the abnormal patellar tracking mechanism. Kinematic approaches using MR images have been regarded of more accuracy in knee pain detection than stationary approaches. This paper proposes an automatic diagnosis based kinematic patellar tracking for AKP detection. The kinematic patellar tracking uses a hybrid approach for extracting knee organs, where an edge-constrained wavelet enhancement followed by moment preserving segmentation is employed for conquering the soft tissue adhesion for extracting the femur and tibia from axial MR images, and a sliding window based moment preserving for resolving the segmentation difficulty associated with intensity non-uniformity in saggital MR images. The experiment results demonstrate the prominent of the calculated inclination angles in detecting AKP. Keywords：Automatic diagnosis based kinematic patellar tracking, edge-constrained wavelet enhancement,

show abstract

“…To cope with these problems several computerized methods of analyzing MR images of human knee joint have been proposed. Kshirsagar et al [10] focus on quantitating the cartilage dimensions. Kitney et al [11] propose a set of dedicated functions to segment images.…”

Section: Introductionmentioning

confidence: 99%

Integrating Edge Detection and Thresholding Approaches to Segmenting Femora and Patellae From Magnetic Resonance Images

Lee

Chung

2005

Biomed. Eng. Appl. Basis Commun.

View full text Add to dashboard Cite

Anterior knee pain (AKP) is a common pathological condition. The most obvious problem causing knee pain is the abnormal patellar tracking mechanism. For computerized knee joint analysis, how to successfully segment the knee bones is an import issue. This paper presents a simple while effective algorithm for fully automatic femur and patella segmentation for magnetic resonance (MR) knee images through integrating edge detection and thresholding approaches. Based on consideration of computational complexity and accuracy, we develop a compound approach to segment the MR knee images. The moment preserving thresholding is first utilized to gather the boneoutline information employed to estimate the region of interest (ROI). An ROI based wavelet enhancement is proposed to restrict the contrast improvement only around the bone edges. The restriction makes both the adhesion separation of bone and surrounding tissues and the bone contour conservation become possible and avoid harsh thresholding resulting from the global based wavelet enhancement. Cooperating with the morphology operation, stable initial guess of the bone regions can be achieved. To overwhelm the main drawback of the existing edge based segmentation methods, i.e. the necessity of complicated post-processing, a new approach -FLoG is proposed to provide a feasible solution. It converts the edge detection results using LoG into a region-based format through the flow fill operation. The developed onion-growing algorithm can properly combine the initial guess of bone regions with the FLoG outputs in an efficient way. The experimental study shows our method is superior to the conventional ones in meeting the requirement of physicians. This is because our method can perform well in dealing with the tougher conditions, i.e. the partial volume and the soft tissue adhesion conditions. Because of the integration of the thresholding approach with the FLoG edge detector, our algorithm is even robust to unsatisfactory imaging conditions. Hence, our method lends itself to assisting the clinical diagnosis of knee functions.Biomed Eng Appl Basis Comm, 2005(February); 17: 1-11.

show abstract

Quantitation of articular cartilage dimensions by computer analysis of 3D MR images of human knee joints

Cited by 7 publications

References 7 publications

Knee Joint Articular Cartilage Segmentation, Visualization and Quantification using Image Processing Techniques: A Review

Knee Joint Articular Cartilage Segmentation, Visualization and Quantification using Image Processing Techniques: A Review

An automatic detection algorithm of MR images for knee pain problem

Integrating Edge Detection and Thresholding Approaches to Segmenting Femora and Patellae From Magnetic Resonance Images

Contact Info

Product

Resources

About