(MRC DTP) Image analysis and software development to study tissue repair using artificial intelligence (AI)

Trauma and surgery require efficient restoration of skin, making wound healing a central concern of clinical care worldwide. Large-area wounds, congenital defects of the skin, diabetes and cancer can lead to the loss of the epidermal barrier, which protects our body from pathogens, irradiation, and water loss. A wound-healing cascade is initiated upon damage to the skin, and the restoration of the epidermis is indispensable to successful healing. Fast and complete regeneration of the epidermal layer, composed of keratinocytes, is the major challenge in the clinics1.
Genetically altered (GA) mice remain the best model to study the mechanisms of tissue repair as they provide a possibility of the systemic in vivo analysis of the wound, followed by detailed in vitro analyses. The main challenge in these analyses is the quantification and comparison of healing parameters between GA mice and the control littermates. The latter is currently a “bottle-neck” in studies aiming to understand the reasons behind an improved/impaired wound closure.
This project will develop and evaluate methods and software for the automated analysis of images used to study the mechanisms behind efficient tissue repair. Methods from machine-learning, a branch of AI, will be applied to automatically (i) detect and quantify different tissue types and characteristics (e.g. epidermis, collagen) in histologic images; and (ii) locate and count immune cells in immunofluorescent images. The software can then be used to compare wound healing properties between GA mice and control littermates.
The methods and software to be developed have the potential to accelerate and improve the outcomes of wound healing studies. A faster, more sophisticated and robust wound image analysis will provide researchers with the information and time needed to refine the hypothesis, to better design further experiments, and to adjust the breeding strategy. This project may also lead to the identification of the molecular mechanisms behind improved wound healing.
The student will join a well-established research group, and will gain extensive experience of working in an interdisciplinary team. They will gain vast knowledge of state-of-the-art machine vision algorithm development for biomedical imaging problems. The student will also have the opportunity to gain in-depth knowledge of the molecular mechanisms in regenerative medicine.

https://www.research.manchester.ac.uk/portal/svitlana.kurinna.html
https://personalpages.manchester.ac.uk/staff/claudia.lindner/
https://personalpages.manchester.ac.uk/staff/timothy.f.cootes/

Entry Requirements:
Applications are invited from UK/EU nationals only. Applicants must have obtained, or be about to obtain, at least an upper second class honours degree (or equivalent) in a relevant subject.