KES-2012-Neurocomputing-issue-scope

Title of the special issue

Bioinspired knowledge based techniques in medical image and information processing

Acronym

KES medical image and information

Definition of issue’s scope

This special issue identifies the following current challenges in the field of medical image and information processing:

- Combining high (semantic) and low level information for clinical decision support (CDS) or computer aided diagnosis (CAD) systems

- Combining multi-modal information. A wide diversity information sources may be used to reach a diagnosis that can be validated by the human operator: including

clinical, biochemical and medical image information

- New views on uncertainty, ambiguity and data artifacts (i.e. noise, missing data) allowing to effectively deal with them in a systematic and integrative way.

These challenges are currently being addressed from a number of points of view. The development of semantics based pattern recognition systems, able to learn ontologies from data, even heterogeneous data, as well as of ontology based reasoning allow for the interplay between high-level semantics and low-level features. Hybrid systems combining ontologies with fuzzy and bio-inspired systems allow introduce uncertain modeling and reasoning in the semantic domain. Lattice computing approaches allow seamlessly treatment of heterogeneous data through lattice theory, while allowing new more robust reasoning process diverging from the conventional statistics framework. Still, despite a long tradition of research and results, new bio-inspired and statistical classification algorithms are being extended to deal with heterogenous, ambiguous and artifact prone data. Also new ways of interactive development of systems, such as active learning or reinforcement feedback approaches can help to improve the efficiency of learning under scarce or expensive data collection.

Specific technical topics

- Bio-inspired machine learning: artificial neural networks, evolutionary computation

- Fuzzy and probabilistic machine learning approaches

- Lattice computing approaches

- Active learning, reinforcement learning

- Advanced classification systems (ensembles, ELM)

- Interplay of high level semantics and low level machine learning

- Sparse bayesian machine learning approaches

- Atlas and other a priori information

- Mixing qualitative and quantitative data sources

Domains of application

- circulatory system diseases, i.e. vessel image processing, and related clinical information

- neurodegenerative diseases, including Alzheimer's Disease

- genetics and proteomics

- brain plasticity, i.e. recovery from ictus

- image segmentation, registration and normalization

- brain state decoding and prediction