Prediction analysis for tumor growth from large scale non-invasive image
Kodrani Kajal Pradipkumar, Desai Devanshi Manojbhai, R. Rajamenakshi · 2016
Large volumes of data is generating a lot of publicity in all industries including healthcare. Some health institutions or academic-research priority or experienced with large volumes of data or use in advanced research projects. These institutions are based on scientific, statistical, graduate students' data, and the like quarrelling with the complexities of large volumes of data. Cancer is a disease that many people around the world as a significant, predictable analysis must be completed using digital imaging in health data. The main objective of our proposed work is to predicting the tumor growth in cancer images. As an addition to functional imaging, mathematical modelling based on the imaging is an alternative, cross-disciplinary area of development. Modelling is used in oncology in order to understand and predict tumor growth, and also to anticipate the effects of targeted and untargeted therapies. Here we have proposed a tumor growth prediction model using mathematical models. In this model, we are going to use features that can be extracted from the patients' details and DICOM images both. This model gives the growth rate of tumor cells between two consecutive time point of CT images. And the result is used for the analysis and predict the future growth rate. The proposed model is designed for the lung tumor affected patients.