Medical imaging (MI) is at the heart of many of today’s improved diagnose and treatment technologies. Computer-based solutions are vastly more capable of both quantitative measurement of the medical condition and the pre-processing tasks of filtering, sharpening, and focusing image detail. Bio-inspired and Soft Computing (BC, SC) techniques have been successfully applied in each of the fundamental steps of medical image processing and analysis (e.g. restoration, segmentation, registration or tracking). The natural partnership of humans and intelligent systems and machines in MI is to provide the clinician with powerful tools to take better decisions regarding diagnose and treatment. The main goal of the network is to create a training program where the enrolled early-stage researchers (ESRs) will be exposed to a wide variety of SC and BC techniques, as well as to the challenge of applying them to different situations and problems within the different MI stages. A personalized, exhaustive and complementary program will consist of: - a personalized research plan based on individual research projects; - local and network-wide specific training courses, both in face-to-face and virtual modalities; - the network’s complementary skills courses, workshops and final conference; and - the international research stays among the different partners. The collaboration of experts from the area of MI with those working on BC and SC applications to computer vision will generate new and viable methods and solutions from the combined ideas of these communities. The presence of both research and technical partners in the network, including hospitals and companies, will provide the appropriate framework for application domain focused research. The trained ESRs will acquire a strong background for the development of intelligent systems based on BC-SC providing flexible application-oriented solutions to current MI problems in the clinical and research field.

UUGR has been chosen in a complementary way to combine experts and prestigious researchers in the three International Training Network Disciplines to compose a complete and successful training program. UGR is dedicated to SC and BC methods, i.e., the algorithmic fundamentals of the network. In particular, new approaches to traditional classification, machine learning, and optimization techniques will be explored. Within these areas, SC and BC, UGR is the supervisor of two training projects for PhD students. They are: a) Genetic and Memetic Algorithms for Real Parameter Optimization: Evolutionary computation has been successfully applied to many different image processing tasks where real-coded evolutionary algorithms are considered for numeric parameter optimization. Within this research project, UGR intends to develop genetic algorithms and their hybrid models with local search (memetic algorithms) with good scalability properties. Collaborations with all partners solving specific MI problems are expected. b) Study and Design of Multi-Objective Genetic Fuzzy Systems for Improving the Interpretability-Accuracy Trade-Off of Linguistic Fuzzy Rule-Based Systems: In the last years, multi-objective evolutionary algorithms have been used to tackle the problem of finding the right trade-off between interpretability and accuracy of linguistic Fuzzy Rule-Based Systems (FRBSs) by simultaneously achieving accuracy and interpretability maximization. UGR intend to develop linguistic FRBSs with good interpretability properties that could help to understand the behavior of the models involved on MI problems. Collaborations with all partners solving specific MI problems are expected. Moreover, UGR is involved in all the training activities, taking part in the organization of some of them as the first complementary skills course that take place during the second year of the project at the UGR facilities, including topics about core research skills: 1. Research methodology and policy; 2. Search of scientific and technical information; 3. Data management and ethical issues; 4. Speed reading and mind mapping to allow creative thinking and problem resolution; 5. Highly specialized scientific writing and oral communication. 6. General public dissemination. In addition to UGR expertise in SC and BC, this partner will also play an important role regarding the virtual course organization. UGR’s virtual learning center (CEVUG) is in charge of designing and hosting the virtual course.

Kick-off Meeting NSB Meetings (up to 6 meetings) Reports on Ethical, Gender, Training Quality, Industrial involvement and Intellectual Property, and Dissemination Complementary skills Courses, 1 (UGR) and 2 (ULB) Online courses (UGR) Face-to-face courses (1 and 2) Workshops (1 and 2) New methods and technical reports on different techniques. Software. Final Conference and Final Meeting

The International Training Network clearly promotes the transverse exchange of knowledge among different disciplines. Furthermore, it also aims to provide a transverse research formation from different industrial sectors: scientific research, technology development, practical uses in hospitals, and companies. Thus, the proposed training program will provide the European industry with highly qualified researchers able to solve complex MI problems. These researchers will promote new scientific knowledge and technological applications in hospitals, healthcare providers, and technological companies. In summary, the trained ESRs will acquire a strong background for the development of intelligent systems based on BC-SC providing more sophisticated and flexible application-oriented solutions to current MI problems in the clinical and research field.

Soft Computing and Intelligent Information Systems

Code PAIDI: TIC 186

Francisco Herrera Triguero. Socio. 

Universidad de Granada

Budget of Andalusian group: € 374,655.80

http://sci2s.ugr.es

• European Centre for Soft Computing (ECSC), Spain
• Ghent University (UGent), Belgium
• Université Libre de Bruxelles (ULB), Belgium
• University of Nottingham (UNott), United Kingdom
• Università degli Studi di Parma(UNIPR), Italy
• University of Granada (UGR), Spain.
• Universitätsklinikum Freiburg (UKLFREI), Germany
• Henesis (Henesis), Italy