METHODS: The proximal tibia was resected as a single osteochondral unit during total knee replacement from patients (N = 10). The osteoarthritic chondrocytes were isolated from the osteochondral units, and characterized using reverse transcriptase-polymerase chain reaction. The isolated osteoarthritic chondrocytes were cultured and embedded in agarose, and then subjected to 10% and 20% uniaxial dynamic compression up to 8-days using a bioreactor. The morphological features and changes in the osteoarthritic chondrocytes upon compression were evaluated using scanning electron microscopy. Safranin O was used to detect the presence of cartilage matrix proteoglycan expression while quantitative analysis was conducted by measuring type VI collagen using an immunohistochemistry and fluorescence intensity assay.
FINDINGS: Gene expression analysis indicated that the isolated osteoarthritic chondrocytes expressed chondrocyte-specific markers, including BGN, CD90 and HSPG-2. Moreover, the compressed osteoarthritic chondrocytes showed a more intense and broader deposition of proteoglycan and type VI collagen than control. The expression of type VI collagen was directly proportional to the duration of compression in which 8-days compression was significantly higher than 4-days compression. The 20% compression showed significantly higher intensity compared to 10% compression in 4- and 8-days.
INTERPRETATION: The biosynthetic activity of human chondrocytes from osteoarthritic joints can be enhanced using selected compression regimes.
METHODS: In this study, we proposed an image feature extraction technique based on image segmentation with the fully convolutional neural network with eight stride pixel (FCN-8). A total of 290 radiographic images including both female and the male subject of age ranging from 0 to 18 were manually segmented and trained using FCN-8.
RESULTS AND CONCLUSION: The results exhibit a high training accuracy value of 99.68% and a loss rate of 0.008619 for 50 epochs of training. The experiments compared 58 images against the gold standard ground truth images. The accuracy of our fully automated segmentation technique is 0.78 ± 0.06, 1.56 ±0.30 mm and 98.02% in terms of Dice Coefficient, Hausdorff Distance, and overall qualitative carpal recognition accuracy, respectively.