Synovial Sarcoma Classification Technique Using Support Vector Machine and Structure Features

Digital clinical histopathology technique is used for accurately diagnosing cancer cells and achieving optimal results using Internet of Things (IoT) blockchain technology. The cell pattern Synovial Sarcoma (SS) images always appeared as spindle shaped (SSC) structures. Identifying the SSC its prognostic indicator are very crucial problems computer aided diagnosis, especially in healthcare industry applications. A constructive framework has been proposed classification feature components Support Vector Machine (SVM) with assistance relevant Vectors (SVs). This SS images, it transformed into frequency sub-bands Discrete Wavelet Transform (DWT). sub-band wavelet coefficients other Structure Features (SF) extracted Principle Component Analysis (PCA), Linear Discriminant (LDA), Quadratic (QDA) techniques. Here, maximum minimum margin between hyperplane values kernel parameters adjusted periodically a result storing SF SVs IoT devices. performance characteristics internal cross-validation statistical properties evaluated by cross-entropy measures compared nonparametric Mann-Whitney U test. significant differences techniques analyzed receiver operating (ROC) curve. combination QDA + SVM will be required intelligent diagnosis future, gives reduced statistic parameter set greater accuracy. network based led to improvement prognosis medical applications