METHODS: This study involved 70 consecutive Lenke 1 and 2 AIS patients who underwent scoliosis correction with alternate-level pedicle screw instrumentation. Preoperative parameters that were measured included main thoracic (MT) Cobb angle, proximal thoracic (PT) Cobb angle, lumbar Cobb angle as well as thoracic kyphosis. Side-bending flexibility (SBF) and fulcrum-bending flexibility (FBF) were derived from the measurements. Preoperative height and post-operative height increment was measured by an independent observer using a standardized method.
RESULTS: MT Cobb angle and FB Cobb angle were significant predictors ( p < 0.001) of height increment from multiple linear regression analysis ( R = 0.784, R2 = 0.615). PT Cobb angle, lumbar, SB Cobb angle, preoperative height and number of fused segment were not significant predictors for the height increment based on the multivariable analysis. Increase in post-operative height could be calculated by the formula: Increase in height (cm) = (0.09 × preoperative MT Cobb angle) - (0.04 x FB Cobb angle) - 0.5.
CONCLUSION: The proposed formula of increase in height (cm) = (0.09 × preoperative MT Cobb angle) - (0.04 × FB Cobb angle) - 0.5 could predict post-operative height gain to within 5 mm accuracy in 51% of patients, within 10 mm in 70% and within 15 mm in 86% of patients.
METHODS: The proposed method uses a 2D contourlet transform and a set of texture features that are efficiently extracted from the transformed image. Then, the combination of a kernel discriminant analysis (KDA)-based feature reduction technique and analysis of variance (ANOVA)-based feature ranking technique was used, and the images were then classified into various stages of liver fibrosis.
RESULTS: Our 2D contourlet transform and texture feature analysis approach achieved a 91.46% accuracy using only four features input to the probabilistic neural network classifier, to classify the five stages of liver fibrosis. It also achieved a 92.16% sensitivity and 88.92% specificity for the same model. The evaluation was done on a database of 762 ultrasound images belonging to five different stages of liver fibrosis.
CONCLUSIONS: The findings suggest that the proposed method can be useful to automatically detect and classify liver fibrosis, which would greatly assist clinicians in making an accurate diagnosis.