Neuroanatomical changes are of paramount importance for the assessment of brain alterations in many different diseases (e.g. neurodegenerative, auto-immune, and inflammatory), and for the understanding of brain adaptation to animal morphology, behaviour and environment.
The possibility of providing quantitative evaluation of cytoarchitecture of the brain from imaging data, obtained through microscopy imaging of NISSL-stained or immunohistochemical-stained slices, would results an invaluable tool for all the research community.
In order to provide this tool, the layers of different brain types (mostly mammals) and the types of cells present in each layer need to be identified, and then a quantitative morphological assessment of cells and layers need to obtained.
The PhD student will join an exciting multidisciplinary research including computer scientists and engineers at LSBU, statisticians, biologists and veterinarians at the University of Padova with access to unique data from a variety of mammals brain.
The PhD will develop new solutions to analyse and interpret the imaging data using AI, and to integrate the results to answer biological and evolutionary questions.
The outcomes of this project for the PhD candidate are listed below:
- understand digital histology imaging;
- gain experience in medical image analysis and processing techniques;
- learn state of the art AI/deep learning methods in digital pathology and apply them the specific problem;
- develop new methods for targeting the specific imaging challenges brain neuroanatomy;
- work with biologists and veterinarians to develop computer-aided imaging solutions;
- present the findings of the project in international conferences;
- perform high-quality research and publish it as journal articles.
This will be a 3-year fully funded studentship for an EU/UK and overseas applicants who are keen to conduct research in medical imaging at LSBU in the School of Engineering.
Requirements: Applicants must be of outstanding academic merit and should have (or be expected to gain) either a first class or an upper second class Honours degree (or the international equivalent), or an MSc/MRes with distinction. Enthusiastic and self-motivated candidates from all countries with a background in either Computer Science, Engineering, Physics or Mathematics or a related discipline are encouraged to apply.
A good knowledge and experience in imaging, medical imaging, computer vision, machine learning/deep learning would be advantageous.