Soft Computing. SOCO

Share:

DESIGN OF A DECISION SUPPORT SYSTEM FOR CLINICAL ONCOLOGY, BASED ON ADVANCED SOFT-COMPUTING AND VISUALIZATION METHODS

DURATION: From 1st of October 2006 to 31th September 2009

CHIEF RESEARCHER: Alfredo Vellido Alcacena

KEYWORDS:

Medical Decision Support System; Clinical Oncology; Brain Tumours; Magnetic Resonance Spectroscopy; Pattern Recognition; Machine Learning; Rule Extraction; Visualization; Virtual Reality

SUMMARY

Spain trails far behind other countries in terms of translational and clinical initiatives for the development of technologies to assist the diagnosis of cancer patients. On the other hand, there is wide consensus on that the development, practical implementation, and usage of decision support systems by medical experts and clinicians holds promise for substantially improving the quality of medical practice.

For these systems to be useful, they must be based on techniques that are robust in the presence of uncertainty. The first goal of the current project is the design and development of robust Soft Computing techniques for the reduction of the uncertainty that is inherent in medical diagnosis and prognosis in the field of clinical oncology. Novel Soft Computing techniques for data clustering, classification, feature selection (both for clustering and classification), graphical modelling, and rule extraction (both from supervised and unsupervised models), will be developed. Furthermore, novel latent models-based visualization techniques will be studied and implemented.

The second goal is the integration of these tools within a clinical oncology decision support system including flexible visualization methods integrated within a virtual reality environment.

To accomplish all the aforementioned goals, original data supplied by the Grup d'Aplicacions Biomhdiques de l'Espectroscrpia de Resson`ncia Magnhtica Nuclear (GABRMN) from Universidad Autsnoma de Barcelona (UAB), will be used. The available data consist of in vivo spectra obtained by nuclear magnetic resonance, corresponding to diverse types and grades of human brain tumours.

The developed tool prototype will be evaluated and validated by several collaborating hospitals (both national and international) specialized in oncology.

PARTICIPANTS:

Researchers from the following institutions:

  • Departament de Llenguatges y Sistemes Informàtics (UPC, Spain)
  • Liverpool John Moores University (United Kingdom)
  • The University of Manchester (United Kingdom)
  • National Research Council (Canada)
  • Clatterbridge Centre for Oncology (United Kingdom)