university of Poitiers/XLIM
Scientific context:
Alzheimer’s disease (AD) is the most comment form of dementia. Neuroimaging data is an integral part of the clinical assessment providing a way for clinicians to detect brain abnormalities for AD diagnosis. Structural MRI with machine learning techniques has been widely studied to assess brain atrophy for AD detection and prediction [1][2]. In addition to structural changes, metabolic changes in some brain regions could be a good biomarker for an early AD [3]. Recently, Magnetic Resonance Spectroscopy (MRS) have been proved to be effective to quantify certain brain metabolites in vivo [4]. The proposed internship aims in testing and evaluating the effectiveness of machine learning techniques for single subject level classification of individuals affected by different stages of AD (healthy elderly subjects, Mild Cognitive Impairment (MCI) and AD subjects) based on 1H MRS data. Data used in this internship are provided by CHU of Poitiers.
Objectives:
· Evaluate and compare several machine learning algorithms for AD spectroscopy data classification
· Propose solution for learning from few data of spectroscopy data for AD subject’s classification.
· Jointly Investigate the structural and metabolic changes associated with incipient AD pathology to improve MCI subject’s detection.
References:
[1] Olfa Ben Ahmed et al “Recognition of Alzheimer’s Disease and Mild Cognitive Impairment with multimodal image-derived biomarkers and Multiple Kernel Learning”, International Journal Neurocomputing, vol. 220, p. 98-110, Elsevier 2017
[2] Sarraf, S., Tofighi, G.,. DeepAD: Alzheimer′s Disease Classification via Deep Convolutional Neural Networks using MRI and fMRI. bioRxiv 2016
[3] Wang Z, Zhao C, Yu L, et al Regional metabolic changes in the hippocampus and posterior cingulated area detected with 3-Tesla magnetic resonance spectroscopy in patients with mild cognitive impairment and Alzheimer’s disease. Acta Radiol 2009;50:312–19
[4] Pedro J Modrego et al. Magnetic resonance spectroscopy in the prediction of early conversion from amnestic mild cognitive impairment to dementia: a prospective cohort study. BMJ Open 1, e000007.
Key Words: Alzheimer, MRI, spectroscopy, Artificial Intelligence, Machine learning, information fusion, classification
Supervisors:
Dr. Olfa Ben Ahmed (Associate professor, XLIM)
Dr. Carole Guillevin (DACTIM-LMA et CHU de Poitiers)
Skills
MS student in Computer Science, Image and signal processing, Mathematics, or related streams
Strong knowledge in at least one of the following fields is required:
good image processing and machine learning knowledges
mathematical understanding of the formal background
excellent programming skills (Python, C++, MATLAB)
biomedical applications would be appreciated
Salary: 560€/ Month
Application : interested candidates should send their CV to olfa.ben.ahmed@univ-poitiers.fr , a cover letter and a transcript of recent grades