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.
METHODS: Knee joint cartilages harvested from mature and immature animals were used for their distinct collagenous fibrous structure and composition. The cartilages were cut through thickness, indented over the cracked region, and processed histologically. Sample-specific birefringence was quantified as two-dimensional (2D) maps of azimuth and retardance, two measures related to local orientation and degree of alignment of the collagen fibers, respectively. The shape of mechanically indented tissue cracks, measured as depth-dependent crack opening, were compared with azimuth, retardance, or "PLM index," a new parameter derived by combining azimuth and retardance.
RESULTS: Of the three parameters, only the PLM index consistently correlated with the crack shape in immature and mature tissues.
CONCLUSION: In conclusion, we identified the relative roles of azimuth and retardance on the deformation of tissue cracks, with azimuth playing the dominant role. The applicability of the PLM index should be tested in future studies using naturally-occurring tissue cracks.