Biomodelling and machine learning in cancer diagnosis and prediction of metastases

Session organizers

Prof. Andrzej Świerniak, Prof. Krzysztof Fujarewicz
Department of Systems Biology and Engineering, Silesian University of Technology, Gliwice, Poland

Objectives and topics

In spite of great progress of oncology cancer is one of the cause of deaths. Advanced cancer is more likely to metastasize, leading to severe symptoms and a decrease in overall survival. The presence of distant metastases is one of the most predictive factors of poor prognosis. The main goal of this session is to present original models and methods, which support analysis of clinical, molecular and imaging data and aim at better diagnosis of cancer and prediction of its spread and colonization of tumor cells to distant organs. Since the metastatic tumor is mainly incurable, due to its resistance to treatment, we expect to be able to discuss the urgent biological and clinical question: how, when, and where the primary tumor will spread to distant locations. The proposed session is supposed to include interdisciplinary research employing methods from machine learning, data analysis, bio-mathematical modeling, image processing, bioinformatics and systems biology, with strong support from clinical, molecular and biomedical images data. It will give opportunity to present a new framework of data integration and analysis and novel algorithms that will support interdisciplinary research. We want to offer an opportunity for researchers and practitioners to identify new promising research directions as well as to publish recent advances in this area. The scope of the session includes, but is not limited to the following topics:

  • Bio-mathematical models of tumor growth, spread and metastasis
  • Feature selection and classification methods in cancer diagnosis and metastasis prediction .
  • Machine learning algorithms for prediction of cancer progress and anticancer therapy outcome
  • Image processing methods in radiomics
  • Simulation tools for modeling and prediction of cancer development and metastasis
  • Data mining techniques with application to cancer diagnosis
  • Algorithms for integration of clinical, molecular and radiomic data
  • Bioinformatic analysis of molecular data related to cancer
  • Modeling of cancer evolution
  • "Omics" in different cancers