| Abstrakt: |
Indistinct soft tissue sarcomas are a form of tumor that can be difficult to diagnose in a tremendous population. For earlier prediction of distant metastasis, some traditional classifications are suffered by technological issues, lack of enhancement methods, reliability, and so on. To provide a better classification, this paper introduces a new deep learning-based soft tissue sarcoma classification framework. Initially, spatial features and LVP features are extracted.The main aim of this phase is to generate LVP using each pixel vector and provides the benefits of inherent structures in edge patches. The subsequent classification phase is utilized an optimized Convolutional Neural Network (CNN). Moreover, the weight and filter size of CNN will be optimally tuned by the new Self Adaptive Bat Algorithm (SA-BA). Finally, SA-BA method is compared over some existing classifiers in terms of various measures. [ABSTRACT FROM AUTHOR] |
Full text from SpringerLink