Medical Imaging Convention [rescheduled] Sep 15, 2021 - Sep 16, 2021 — National Exhibition Centre, Birmingham, England
2021 SINAPSE ASM Sep 16, 2021 - Sep 17, 2021 — Technology & Innovation Centre, University of Strathclyde, 99 George Street, Glasgow
Total Body PET 2021 conference [rescheduled] Sep 22, 2021 - Sep 24, 2021 — Virtual Meeting (online)
PET is Wonderful Annual Meeting 2021 Oct 26, 2021 12:00 AM — Virtual Meeting (online)

eLearning

SINAPSE experts from around Scotland have developed ten online modules designed to explain medical imaging. They are freely available and are intended for non-specialists.


Edinburgh Imaging Academy at the University of Edinburgh offers the following online programmes through a virtual learning environment:

Neuroimaging for Research MSc/Dip/Cert

Imaging MSc/Dip/Cert

PET-MR Principles & Applications Cert

Applied Medical Image Analysis Cert

Online Short Courses

Mr Blair Johnston

Position: Honorary Lecturer
Institute: NHS Greater Glasgow and Clyde
Department: MRI Physics


Description of Phd:

 

Diagnostic categorisation of scans from individual subjects with ‘functional’ psychiatric disorders (e.g. depression, schizophrenia, ADHD, addictions) is not possible in radiology.  Quantitative neuroimaging inferences (e.g. using SPM or FSL) have only been possible at a group level, not an individual level.  Recently though, machine learning techniques, such as support vector machines (SVMs), have been applied to individual scan categorisation.1,2,3Typically about 80% of a neuroimaging data set  is used to train a SVM classifier and the remainder is used to test the accuracy.  Considerable success has been reported: e.g.  ~85 to 95% accuracy in schizophrenia1 and unipolar major depression.Attention Deficit Hyperactivity Disorder (ADHD) is the most commonly diagnosed psychiatric disorder in children affecting 3 to 5%.  Whilst ~70% of children will respond to and tolerate methylphenidate (MPH), 30% do not.  There are  currently no ways to identify responders from non-responders without exposing the child/young person to a trial of the drug.  Developing methods to identify stimulant non-responders at an individual level and prior to exposure is a clinically important under-researched area. Neuroimaging studies have identified group level quantitative differences in brain structure, distinguishing treatment responders from non-responders. and positive from negative developmental outcomes.  The successful candidate would focus on further developing the high accuracy, hybrid VBM-FBM-SVM image processing technique, started at Dundee University, applying it to ADHD MPH response prediction.  Given the accuracy of categorisation that has been achieved, further development of machine learning based image categorisation techniques has the potential to make a radical advance in neuroimaging, in general, by the introduction of quantitative methods that can inform clinical decisions on individual patients, with ‘functional’ psychiatric, and other disorders.