Diferencia entre revisiones de «KES-2012-Neurocomputing-issue-scope»

De Grupo de Inteligencia Computacional (GIC)
Sin resumen de edición
Sin resumen de edición
 
(No se muestran 8 ediciones intermedias del mismo usuario)
Línea 1: Línea 1:
;Title of the special issue: Bioinspired knowledge based techniques in medical image processing
;Title of the special issue: Bioinspired knowledge based techniques in medical image and information processing


;Acronym: KES medical image
;Acronym: KES medical image and information
   
   
;Definition of issue’s scope:  
;Definition of issue’s scope:  
   
   
This special issue identifies the following knowledge related challenges in the current
This special issue identifies the following current challenges in the field of medical image and information processing:  
field of pattern recognition:  
:- Combining high (semantic) and low level information for clinical decision support (CDS) or computer aided diagnosis (CAD) systems
:- Combining high (semantic) and low level information for pattern recognition.
:- 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
Such needs appear in apparently unrelated fields like motion understanding,
clinical, biochemical and medical image information
content based image retrieval (CBIR)  
:- 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.  
:- Combining multi-modal information which can not be subject of conventional
error measures, impeding the application of state-of-the-art error minimization
approaches. The sources of information are heterogeneous, and its combination
leads to unmeasurable data types. For instance, in the field of biomedical
information processing, a wide diversity information sources may be used to  
reach a diagnosis that can be validated by the human operator.
:- 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  
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.  
development of semantic 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 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 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. The special issue invites works on these areas showing the interplay
between high level semantics and low level statistical and bio-inspired data processing
techniques. 
   
   
;Specific technical topics  
;Specific technical topics  
:- Ontology reasoning and learning  
:- Bio-inspired machine learning: artificial neural networks, evolutionary computation
:- Fuzzy and probabilistic ontologies
:- Fuzzy and probabilistic machine learning approaches
:- Lattice computing approaches   
:- Lattice computing approaches   
:- Knowledge based adaptive approaches 
:- Active learning, reinforcement learning  
:- Active learning, reinforcement learning in qualitative spaces
:- Advanced classification systems (ensembles, ELM)  
:- Advanced classification systems (ensembles, ELM, clustering)  
:- Interplay of high level semantics and low level machine learning  
:- Interplay of high level semantics and low level machine learning  
;Applications
:- Sparse bayesian machine learning approaches
:- Remote sensing
:- Atlas and other a priori information
:- Multimedia information processing
:- Mixing qualitative and quantitative data sources
:- Biometrics, such as face recognition
;Domains of application
:- Fusion of clinical and medical image information 
:- circulatory system diseases, i.e. vessel image processing, and related clinical information
:- Content based image retrival
:- neurodegenerative diseases, including Alzheimer's Disease  
:- Multimodal information processing
:- genetics and proteomics
:- brain plasticity, i.e. recovery from ictus
Dear Tom, thanks for your kind response, I am thinking about 10 papers.
:- image segmentation, registration and normalization
The specific issue's topic will be the application of bio-inspired
:- brain state decoding and prediction
machine learning for the processing of medical information, including
clinical, biochemical and medical image information, with an emphasis in
two venues: (a) circulatory system diseases, i.e. vessel image
processing, and related clinical information, and (b) neurodegenerative
diseases, including Alzheimer's Disease and neuropsychyatric disorders,
involving multimodal brain imaging and related clinical information. The
kind of systems would range from image segmentation, registration and
normalization to computed aided diagnosis systems, brain state decoding
and prediction. Please let me know your views.
 
 
Submission deadline: 1st December 2012

Revisión actual - 23:23 29 mar 2013

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
Obtenido de «http://ehu.eus/ccwintco/index.php?title=KES-2012-Neurocomputing-issue-scope&oldid=14487»