Knee Cartilage Thickness Differs Alongside Ages: A 3-T Magnetic Resonance Research Upon 2,481 Subjects via Deep Learning

Abstract

Background: It was difficult to distinguish the cartilage thinning of an entire knee joint and to track the evolution of cartilage morphology alongside ages in the general population, which was of great significance for studying osteoarthritis until big imaging data and artificial intelligence are fused. The purposes of our study are (1) to explore the cartilage thickness in anatomical regions of the knee joint among a large collection of healthy knees, and (2) to investigate the relationship between the thinning pattern of the cartilages and the increasing ages.Methods: In this retrospective study, 2,481 healthy knees (subjects ranging from 15 to 64 years old, mean age: 35 ± 10 years) were recruited. With magnetic resonance images of knees acquired on a 3-T superconducting scanner, we automatically and precisely segmented the cartilage via deep learning and calculated the cartilage thickness in 14 anatomical regions. The thickness readings were compared using ANOVA by considering the factors of age, sex, and side. We further tracked the relationship between the thinning pattern of the cartilage thickness and the increasing ages by regression analysis.Results: The cartilage thickness was always thicker in the femur than corresponding regions in the tibia (p < 0.05). Regression analysis suggested cartilage thinning alongside ages in all regions (p < 0.05) except for medial and lateral anterior tibia in both females and males (p > 0.05). The thinning speed of men was faster than women in medial anterior and lateral anterior femur, yet slower in the medial patella (p < 0.05).Conclusion: We established the calculation method of cartilage thickness using big data and deep learning. We demonstrated that cartilage thickness differed across individual regions in the knee joint. Cartilage thinning alongside ages was identified, and the thinning pattern was consistent in the tibia while inconsistent in patellar and femoral between sexes. These findings provide a potential reference to detect cartilage anomaly.

The Presence of Cartilage Affects Femoral Rotational Alignment in Total Knee Arthroplasty

“…However, both studies enrolled arthritic subjects where pathological cartilage wear or defects were expected. A similar trend was reported by Si et al, who reported 1.75 ± 0.12 mm for the medial distal femoral cartilage and 1.77 ± 0.13 mm for the lateral, and 1.59 ± 0.16 mm for the medial posterior femoral cartilage and 1.61 ± 0.22 mm for the lateral ( 18 ). The thickness difference could be explained by the subjects we recruited, who were involved in high-intensity physical activities ( 19 ).…”

Emergence of Deep Learning in Knee Osteoarthritis Diagnosis

“…Similar to Norman et al [ 46 ], Si et al [ 47 ] decided to use 2D U-Net to segment the bones and articular cartilages of the knee from MR images which are femur, tibia, patellar, and each of their corresponding cartilages. The cartilages are segmented to obtain the cartilage thickness in 14 anatomical regions.…”

“…Wirth et al [ 31 ] also used 2D U-Net for segmenting femorotibial cartilages to test the cartilage morphometry longitudinal test-retest reproducibility and had demonstrated high DSC for both coronal FLASH and sagittal DESS images. For both studies by Si et al [ 47 ] and Wirth et al [ 31 ], only subjects without OA were included.…”

Getting Cartilage Thickness Measurements Right: A Systematic Inter-Method Comparison Using MRI Data from the Osteoarthritis Initiative

“…7 The problem can be addressed by fully automated approaches, which typically require segmenting cartilage in the MR images, defining joint regions and subregions, and calculating mean cartilage thickness per region and subregion. Different approaches for cartilage thickness measurements have been developed previously, for example, (1) finding the minimum distance between opposite cartilage surfaces, [8][9][10][11][12] (2) measuring the lengths of surface normals between 3D meshes that approximate the cartilage surfaces, 6,8,11,13 (3) combining surface normals with offset maps, 14 (4) analyzing shape models fitted to the cartilage volume, 15 or (5) computing curved potential field lines between the cartilage surfaces. 11 Commercially available techniques also rely on the calculation of surface normals between meshes, 6 which may thus be considered the most established method to date.…”