A new fruit fly optimization algorithm enhanced support vector machine for diagnosis of breast cancer based on high-level features.

BACKGROUND: It is of great clinical significance to develop an accurate computer aided system to accurately diagnose the breast cancer. In this study, an enhanced machine learning framework is established to diagnose the breast cancer. The core of this framework is to adopt fruit fly optimization algorithm (FOA) enhanced by Levy flight (LF) strategy (LFOA) to optimize two key parameters of support vector machine (SVM) and build LFOA-based SVM (LFOA-SVM) for diagnosing the breast cancer. The high-level features abstracted from the volunteers are utilized to diagnose the breast cancer for the first time. RESULTS: In order to verify the effectiveness of the proposed method, 10-fold cross-validation method is used to make comparison among the proposed method, FOA-SVM (model based on original FOA), PSO-SVM (model based on original particle swarm optimization), GA-SVM (model based on genetic algorithm), random forest, back propagation neural network and SVM. The main novelty of LFOA-SVM lies in the combination of FOA with LF strategy that enhances the quality for FOA, thus improving the convergence rate of the FOA optimization process as well as the probability of escaping from local optimal solution. CONCLUSIONS: The experimental results demonstrate that the proposed LFOA-SVM method can beat other counterparts in terms of various performance metrics. It can very well distinguish malignant breast cancer from benign ones and assist the doctor with clinical diagnosis.

Expressions of clinical significances of p-extracellular regulated kinase 1/2 and matrix metalloproteinase-9 in cervical squamous cell carcinoma / 中国医学科学院学报

<p><b>OBJECTIVE</b>To study the expressions and clinical significances of p-extracellular regulated kinase(P-ERK)1/2 and matrix metalloproteinase-9(MMP-9)in cervical squamous cell carcinoma.</p><p><b>METHODS</b>The expressions of P-ERK1/2 and MMP-9 in 30 cases with chronic cervicitis, 45 cases with cervical intraepithelial neoplasia (CIN), and 58 cases with cervical squamous cell carcinoma were detected by immunohistochemical method.</p><p><b>RESULTS</b>The positive rates of P-ERK1/2 and MMP-9 in chronic cervicitis, CIN, and cervical squamous cell carcinoma were 0 and 0, 28.9% and 24.4%, 77.6% and 65.5%, respectively, showing significant differences among these three groups (χ(2)= 54.393,p=0.003;χ(2)=40.968,p=0.005). The positive rates of P-ERK1/2 and MMP-9 in patients at clinical stages 2-3, at G3, with lymphatic metastasis, or with a tumor diameter greater than 4 cm were significantly higher than those at clinical stage 1(p=0.015,p=0.002), at G1-G2(p=0.013,p=0.017), without lymphatic metastasis (p=0.017,p=0.021), or with a tumor diameter less or equal than 4 cm in cervical squamous cell carcinoma(p=0.008,p=0.004). There was a positive correlation between P-ERK1/2 and MMP-9 in cervical squamous cell carcinoma (χ(2)=8.955,p=0.006).</p><p><b>CONCLUSIONS</b>The expressions of P-ERK1/2 and MMP-9 increase gradually with the progression of cervical squamous cell carcinoma. The over expressions of P-ERK1/2 and MMP-9 may promote the infiltration of cervical squamous cell carcinoma and lymphatic metastasis, druing which these two enzymes may exert their effects in a synergistic manner.</p>