Research
My research mainly focuses on medical image processing and analysis. I am interested in the development of segmentation and classification methods for computer-aided diagnosis, with a particular interest in the use of the machine learning techniques for neurodegenerative diseases detection and prediction. My last works have concerned the development and the validation of new imaging biomarkers for the Alzheimer’s disease early detection.
Recently, many studies have proposed biomarkers to perform early detection of Alzheimer's disease.
Some of them have proposed methods based on inter-subject similarity
while other approaches have investigated framework using intra-subject variability.
In this work, we propose a novel framework combining both approaches
within an efficient graph of brain structures grading. Subsequently, we demonstrate the competitive
performance of the proposed method compared to state-of-the-art methods.
The aim of our work is to
study the efficiency of hippocampal subfields compared to the whole hippocampus structure with a multimodal
patch-based framework that enables to capture subtler structural and microstructural alterations. To this end, we analyze
the significance of the different hippocampal subfields for AD diagnosis and prognosis with volumetric, diffusivity
measurements and a novel multimodal patch-based grading framework that combines structural and diffusion MRI.
The experiments conducted in this work showed that the use of the whole hippocampus provides the most discriminant biomarkers for advanced AD
detection while biomarkers applied into subiculum obtain the best results for AD prediction, improving by 2% the
accuracy compared to the whole hippocampus.
We study the potential using texture information based on Gabor
filters to improve patch-based grading method performance, with a focus on the
hippocampal structure.
We also propose a novel fusion framework to efficiently combine multiple grading maps
derived from a Gabor filters bank.
Finally, we compare our new texture-based grading biomarker with the state-of-the-art approaches
to demonstrate the high potential of the proposed method.
We propose to use a similar framework on different
diffusion parameters extracted from DTI.
We also propose to use a fast patch-based search strategy
to provide novel biomarkers for the early detection of AD.
We intensively compare our new grading-based DTI features with
basic MRI/DTI biomarkers and evaluate our method within a cross validation
classification framework.
Finally, we demonstrate that the proposed biomarkers obtain competitive results for
the identification of the different stages of AD.
To date, the evolution of aortic remodeling, following a type B aortic dissection, is still unknown. Physicians need new tools to extract
parameters describing the morphology of the aorta and the properties of the dissection such as the volume of the true and false lumens,
and the position of the different tears. In this work, we propose a new method for the aorta segmentation and the extraction of medical
parameters related to the aortic dissection (i.e., the volume of the true and the false lumen, position and morphology of the tears).
Master thesis [In French]