Measurement and visualisation of focal cartilage thickness change by MRI in a study of knee osteoarthritis using a novel image analysis tool

Williams, T.G.; Holmes, Andrew P.; Bowes, M.A.; Groenhuis, Vincent; Hutchinson, Charles E.; Waterton, John C.; Maciewicz, Rose A.; Taylor, Chris

doi:10.1259/bjr/68875123

Cited by 41 publications

(31 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We did not observe similar associations between lateral cartilage thickness loss or the dGEMRIC index with weight loss. The differential change in the medial compared with the lateral compartment is not unexpected as previous studies have found that the medial compartment generally exhibits higher rates of cartilage loss in people with knee OA 31 34 35. This finding is likely to be attributable to the greater proportion of ground reaction forces borne by the medial tibiofemoral compartment, even in normally aligned knees 36.…”

Section: Discussionmentioning

confidence: 70%

Weight loss in obese people has structure-modifying effects on medial but not on lateral knee articular cartilage

et al. 2011

View full text Add to dashboard Cite

Background Obesity is an important risk factor for knee osteoarthritis (OA), Weight loss can reduce the symptoms of knee OA. No prospective studies assessing the impact of weight loss on knee cartilage structure and composition have been performed. Objectives To assess the impact of weight loss on knee cartilage thickness and composition. Methods 111 obese adults were recruited from either laparoscopic adjustable gastric banding or exercise and diet weight loss programmes from two tertiary centres. MRI was performed at baseline and 12-month follow-up to assess cartilage thickness. 78 eligible subjects also underwent delayed gadolinium-enhanced MRI of cartilage (dGEMRIC), an estimate of proteoglycan content. The associations between cartilage outcomes (cartilage thickness and dGEMRIC index) and weight loss were adjusted for age, gender, body mass index (BMI) and presence of clinical knee OA. Results Mean age was 51.7±11.8 years and mean BMI was 36.6±5.8 kg/m 2 ; 32% had clinical knee OA. Mean weight loss was 9.3±11.9%. Percentage weight loss was negatively associated with cartilage thickness loss in the medial femoral compartment in multiple regression analysis (β=0.006, r 2 =0.19, p=0.029). This association was not detected in the lateral compartment (r 2 =0.12, p=0.745). Percentage weight loss was associated with an increase in medial dGEMRIC in multiple regression analysis (β=3.9, r 2 =0.26; p=0.008) but not the lateral compartment (r 2 =0.14, p=0.34). For every 10% weight loss there was a gain in the medial dGEMRIC index of 39 ms (r 2 =0.28; p=0.014). The lowest weight loss cut-off associated with reduced medial femoral cartilage thickness loss and improved medial dGEMRIC index was 7%. Conclusions Weight loss is associated with improvements in the quality (increased proteoglycan content) and quantity (reduced cartilage thickness losses) of medial articular cartilage. This was not observed in the lateral compartment. This could ultimately lead to a reduced need for total joint replacements and is thus a fi nding with important public health implications.

show abstract

Section: Discussionmentioning

confidence: 70%

Weight loss in obese people has structure-modifying effects on medial but not on lateral knee articular cartilage

et al. 2011

View full text Add to dashboard Cite

show abstract

“…The semi-automated approach used the following method. First, the user selected start and end sagittal images for each major cartilage region (femoral, medial tibial, lateral tibial and patellar), as well as seed points in the subchondral bone midway between the two slices 25 26. Initial boundary finding for the bone–cartilage interface was performed by an active contour approach.…”

Section: Methodsmentioning

confidence: 99%

Cross-sectional and longitudinal associations between systemic, subchondral bone mineral density and knee cartilage thickness in older adults with or without radiographic osteoarthritis

et al. 2013

View full text Add to dashboard Cite

show abstract

“…A total of 176 sagittal 3D double‐echo steady state (DESS) MR images from 2 scans of 88 knees (baseline and 12‐month follow‐up visits) in the Osteoarthritis Initiative (OAI) database were used in this study. All knees had manual segmentations of cartilage and menisci supplied by Imorphics . The relevant scan parameters for DESS were as follows: field of view = 14 cm, matrix = 384 × 307 (zero‐filled to 384 × 384), echo time = 5 ms, repetition time = 16 ms, 160 slices with a thickness of 0.7 mm.…”

Section: Methodsmentioning

confidence: 99%

Automated cartilage and meniscus segmentation of knee MRI with conditional generative adversarial networks

Gaj

Yang

Nakamura

et al. 2019

Magnetic Resonance in Med

View full text Add to dashboard Cite

Purpose Fully automatic tissue segmentation is an essential step to translate quantitative MRI techniques to clinical setting. The goal of this study was to develop a novel approach based on the generative adversarial networks for fully automatic segmentation of knee cartilage and meniscus. Theory and Methods Defining proper loss function for semantic segmentation to enforce the learning of multiscale spatial constraints in an end‐to‐end training process is an open problem. In this work, we have used the conditional generative adversarial networks to improve segmentation performance of convolutional neural network, such as UNet alone by overcoming the problems caused by pixel‐wise mapping based objective functions, and to capture cartilage features during the training of the network. Furthermore, the Dice coefficient and cross entropy losses were incorporated to the loss functions to improve the model performance. The model was trained and tested on 176, 3D DESS (double‐echo steady‐state) knee images from the Osteoarthritis Initiative data set. Results The proposed model provided excellent segmentation performance for cartilages with Dice coefficients ranging from 0.84 in patellar cartilage to 0.91 in lateral tibial cartilage, with an average Dice coefficient of 0.88. For meniscus segmentation, the model achieves 0.89 Dice coefficient for lateral meniscus and 0.87 Dice coefficient for medial meniscus. The results are superior to previously published automatic cartilage and meniscus segmentation methods based on deep learning models such as convolutional neural network. Conclusion The proposed UNet‐conditional generative adversarial networks based model demonstrated a fully automated segmentation method with high accuracy for knee cartilage and meniscus.

show abstract

Measurement and visualisation of focal cartilage thickness change by MRI in a study of knee osteoarthritis using a novel image analysis tool

Cited by 41 publications

References 24 publications

Weight loss in obese people has structure-modifying effects on medial but not on lateral knee articular cartilage

Weight loss in obese people has structure-modifying effects on medial but not on lateral knee articular cartilage

Cross-sectional and longitudinal associations between systemic, subchondral bone mineral density and knee cartilage thickness in older adults with or without radiographic osteoarthritis

Automated cartilage and meniscus segmentation of knee MRI with conditional generative adversarial networks

Contact Info

Product

Resources

About