Computerised Minds. ...

A video sponsored by the society discusses Searle's Chinese Room Argument (CRA) and the heated debates surrounding it. In this video, which is accessible to the general public and those with interest in AI, Olly's Philosophy Tube ...


Erden in AI roundtab...

On Friday 4th September, philosopher and AISB member Dr Yasemin J Erden, participated in an AI roundtable at Second Home, hosted by Index Ventures and SwiftKey.   Joining her on the panel were colleagues from academia and indu...


AISB Convention 2016

The AISB Convention is an annual conference covering the range of AI and Cognitive Science, organised by the Society for the Study of Artificial Intelligence and Simulation of Behaviour. The 2016 Convention will be held at the Uni...


Bishop and AI news

Stephen Hawking thinks computers may surpass human intelligence and take over the world. This view is based on the ideology that all aspects of human mentality will eventually be realised by a program running on a suitable compu...


Connection Science

All individual members of The Society for the Study of Artificial Intelligence and Simulation of Behaviour have a personal subscription to the Taylor Francis journal Connection Science as part of their membership. How to Acce...


Al-Rifaie on BBC

AISB Committee member and Research Fellow at Goldsmiths, University of London, Dr Mohammad Majid al-Rifaie was interviewed by the BBC (in Farsi) along with his colleague Mohammad Ali Javaheri Javid on the 6 November 2014. He was a...


AISB YouTube Channel

The AISB has launched a YouTube channel: ( The channel currently holds a number of videos from the AISB 2010 Convention. Videos include the AISB round t...



AISB opportunities Bulletin Item

PhD offer - Computational strategies for iconic modeling and model-based non-rigid image registration, University Hospital Gasthuisberg, Belgium

=== See also ===

Computational strategies for iconic modeling and model-based non-rigid
image registration

Project description

In the field of medical image analysis, new methods are developed for
automated measurements in medical images to support diagnosis and
Due to the complexity of the image data (noise, poor contrast,
artifacts, ...) and of the anatomical structures to be quantified
(complex 3-D shape, biological variability, pathology,...), simple
methods that make use of the image data only are usually unreliable.
Instead, model-based strategies are required that incorporate prior
knowledge about the shape and the image appearance of the objects of
interest. Iconic models represent such knowledge by a picture (e.g., an
atlas image) that is geometrically deformed to the image under study
using non-rigid image registration, such that the anatomical structures
in the study image are automatically defined and identified based on the
information in the atlas.
Such atlas-based segmentation requires a suitable similarity measure to
determine the correct registration between atlas and study images, as
well as an appropriate deformation model to constrain the geometric
deformation of the atlas. Current state-of-the-art approaches for
non-rigid image registration make use of mutual information of
corresponding voxel intensities as similarity measure, in combination
with some generic mathematical (e.g. B-splines) or physics-based (e.g.
elastic, viscous fluid) model for the deformation field.
In this project we will extend and improve these methods by taking
statistical information obtained by learning into account, both in the
similarity measure itself as in the deformation model.
These methods will be developed and evaluated in the context of
morphometry of the brain from magnetic resonance (MR) images: volumetry
of brain tissue and subcortical structures, characterization of
inter-subject differences, detection of pathological abnormalities, ...

Function description

To develop, implement and validate methods for iconic shape modeling and
model-based non-rigid image registration and the application thereof for
morphometry of the brain from MR images
Function requirements and competencies 
Academic degree, preferably master of science in engineering or physics,
with strong interest in biomedical applications and medical image
processing in particular 
The candidate should be capable and motivated for pursuing 4 years of
research on this topic towards obtaining a PhD degree
Experience with software development using Matlab, C, C++
Knowledge of and experience with statistics and image processing are
Being capable of working in a targeted, structured, systematic and
punctual manner, social and communicative

We offer

A temporal contract for 4 years 
Flexible working hours 
A challenging job in a scientific and clinical environment 
The project is performed in the Medical Imaging Center, a new laboratory
for multidisciplinary research on medical imaging and image analysis,
located in the university hospital UZ Gasthuisberg of the K.U.Leuven,
Leuven, Belgium


Please send a CV to
Prof. Paul Suetens
Paul.Suetens at
Tel:	+32-16-34 90 26
	+32-16-32 17 13 (secr)