Both feature representation and classifier performance are important factors that determine the performance of computer-aided diagnosis (CAD) systems. In order to improve the performance of ultrasound-based CAD for breast cancers, a novel multiple empirical kernel mapping (MEKM) exclusivity regularized machine (ERM) ensemble classifier algorithm based on self-paced learning (SPL) is proposed, which simultaneously promotes the performance of both feature representation and the classifier. The proposed algorithm first generates multiple groups of features by MEKM to enhance the ability of feature representation, which also work as the kernel transform in multiple support vector machines embedded in ERM. The SPL strategy is then adopted to adaptively select samples from easy to hard so as to gradually train the ERM classifier model with improved performance. This algorithm is verified on a B-mode ultrasound dataset and an elastography ultrasound dataset, respectively. The results show that the classification accuracy, sensitivity and specificity on B-mode ultrasound are (86.36±6.45)%, (88.15±7.12)%, and (84.52±9.38)%, respectively, and the classification accuracy, sensitivity and specificity on elastography ultrasound are (85.97±3.75)%, (85.93±6.09)%, and (86.03±5.88)%, respectively. It indicates that the proposed algorithm can effectively improve the performance of ultrasound-based CAD for breast cancers with the potential for application.
Objective To investigate the effect of epigallocatechin gallate (EGCG) on chondrocyte senescence and its mechanism. Methods The chondrocytes were isolated from the articular cartilage of 4-week-old Sprague Dawley rats, and cultured with type Ⅱcollagenase and passaged. The cells were identified by toluidine blue staining, alcian blue staining, and immunocytochemical staining for type Ⅱ collagen. The second passage (P2) cells were divided into blank control group, 10 ng/mL IL-1β group, and 6.25, 12.5, 25.0, 50.0, 100.0, and 200.0 μmol/L EGCG+10 ng/mL IL-1β group. The chondrocyte activity was measured with cell counting kit 8 after 24 hours of corresponding culture, and the optimal drug concentration of EGCG was selected for the subsequent experiment. The P2 chondrocytes were further divided into blank control group (group A), 10 ng/mL IL-1β group (group B), EGCG+10 ng/mL IL-1β group (group C), and EGCG+10 ng/mL IL-1β+5 mmol/L 3-methyladenine (3-MA) group (group D). After cultured, the degree of cell senescence was detected by β-galactosidase staining, the autophagy by monodansylcadaverine method, and the expression levels of chondrocyte-related genes [type Ⅱ collagen, matrix metalloproteinase 3 (MMP-3), MMP-13] by real-time fluorescent quantitative PCR, the expression levels of chondrocyte-related proteins (Beclin-1, LC3, MMP-3, MMP-13, type Ⅱ collagen, P16, mTOR, AKT) by Western blot. Results The cultured cells were identified as chondrocytes. Compared with the blank control group, the cell activity of 10 ng/mL IL-1β group significantly decreased (P<0.05). Compared with the 10 ng/mL IL-1β group, the cell activity of EGCG+10 ng/mL IL-1β groups increased, and the 50.0, 100.0, and 200.0 μmol/L EGCG significantly promoted the activity of chondrocytes (P<0.05). The 100.0 μmol/L EGCG was selected for subsequent experiments. Compared with group A, the cells in group B showed senescence changes. Compared with group B, the senescence rate of chondrocytes in group C decreased, autophagy increased, the relative expression of type Ⅱ collagen mRNA increased, and relative expressions of MMP-3 and MMP-13 mRNAs decreased; the relative expressions of Beclin-1, LC3, and type Ⅱ collagen proteins increased, but the relative expressions of P16, MMP-3, MMP-13, mTOR, and AKT proteins decreased; the above differences were significant (P<0.05). Compared with group C, when 3-MA was added in group D, the senescence rate of chondrocytes increased, autophagy decreased, and the relative expressions of the target proteins and mRNAs showed an opposite trend (P<0.05). ConclusionEGCG regulates the autophagy of chondrocytes through the PI3K/AKT/mTOR signaling pathway and exerts anti-senescence effects.