Effectively Using Hyperspectral Imaging for Tissue Characterisation

Summary

Hyperspectral imaging is an advanced imaging technique used to capture and process information from across the electromagnetic spectrum. Unlike traditional imaging methods that capture data within specific bands of the spectrum (such as RGB in visible light), hyperspectral imaging collects and processes information across hundreds or even thousands of contiguous spectral bands. This technique provides a detailed spectral profile for each pixel in an image, offering a wealth of information beyond what traditional imaging methods can provide. Each pixel's spectral signature contains information about the object's chemical composition, material properties, and other specific characteristics that might not be visible to the human eye.

Hyperspectral imaging in medicine offers unique capabilities for various applications, leveraging detailed spectral information to aid in diagnostics, tissue analysis, and disease detection. Some examples of how hyperspectral data is used in the medical field include Cancer Detection, Tissue Analysis and Histopathology, Endoscopy, and Minimally Invasive Surgery. Several proof-of-concept studies have shown that hyperspectral imaging is capable of distinguishing diseased from non-diseased cells and tissue. There is also mounting evidence that these technologies can help predict likely outcomes of the disease. However, state-of-the-art models designed to work with specific bands of the spectrum (such as RGB in visible light) fail to efficiently make use of the wealth of information provided by hyperspectral imaging.

The topics for this project will focus on:
- Computer vision and image understanding methods to extract higher-level
semantic information from morphological images (medical/RGB).
- Developing models that effectively use hyperspectral information in addition to
morphological images.
- Demonstrating the capabilities of models that effectively use hyperspectral
imaging for tissue characterisation in clinical applications.

A good knowledge of fundamental topics in computer vision and deep learning, along with strong coding skills in Python is expected. Experience with advanced deep learning topics, particularly multi-modal deep learning, attention models is preferred.

Applicants to research degree programmes should normally have at least a first class or an upper second class British Bachelors Honours degree (or equivalent) in an appropriate discipline. The criteria for entry for some research degrees may be higher, for example, several faculties, also require a Masters degree. Applicants are advised to check with the relevant School prior to making an application. Applicants who are uncertain about the requirements for a particular research degree are advised to contact the School or Graduate School prior to making an application.

The minimum English language entry requirement for research postgraduate research study is an IELTS of 6.5 overall with at least 6.5 in writing and 6.0 in reading, listening and speaking or equivalent. The test must be dated within two years of the start date of the course in order to be valid. Some schools and faculties have a higher requirement.