The University of Manchester
Digital pathology lends itself to the systematic use of artificial intelligence applications. Algorithms developed with machine learning on scanned images are objective, accurate and can produce results more quickly than pathologists. Algorithms are used to identify “hard to see” pathology findings more reliably. This includes a greatly enhanced ability to screen out normal tissues allowing pathologists to concentrate on complicated treatment-related or key decision point findings. In this project we will use FTIR hyperspectral imaging to examine test article lung tissue in order to identify suspicious lesions. The technique utilises molecular vibrations to obtain spatially resolved absorbance profiles of tissues sections. These data are then paired with machine and deep learning classifiers to develop a predictive algorithm that can be used to detect non-visible lesions in control and treated lungs from Syngenta studies, prior to the appearance of histopathology lesions. This work greatly increases the information obtained from tissue sections, resulting in greater insight of agrochemical adverse findings at an earlier stage in compound development. At present all agrochemicals used in China have to undergo 28 day acute inhalation toxicity studies in rats, whereby lung tissue is analysed by a pathologist. In this proposed project we aim to use FTIR imaging of rat lung tissue and develop machine learning algorithms to augment current pathology practice.
Aims and objectives: During the course of this project we aim to answer the following,
1. Can we apply deep learning to train an algorithm to recognize areas of abnormality in treated and control rat lung tissue infrared spectroscopic images?
2. Can we develop a standardized algorithm that can be applied to infrared spectroscopic images taken from any control and treated rat tissue to enable recognition of adverse findings before histopathology lesions are apparent.
3. Can we use the data from the infrared spectroscopic images and the algorithm trained to recognize adverse respiratory findings in lungs taken from rats on 24 hour inhalation studies, to convince Chinese regulatory authorities to waive the need for 28 day studies in China?
4. Will the earlier detection of adverse findings in treated lung tissue, using the algorithm enable Syngenta to conduct fewer animal studies or terminate unsuccessful studies at an earlier stage?
Equality, diversity and inclusion is fundamental to the success of The University of Manchester, and is at the heart of all of our activities. We know that diversity strengthens our research community, leading to enhanced research creativity, productivity and quality, and societal and economic impact. We actively encourage applicants from diverse career paths and backgrounds and from all sections of the community, regardless of age, disability, ethnicity, gender, gender expression, sexual orientation and transgender status.
We also support applications from those returning from a career break or other roles. We consider offering flexible study arrangements (including part-time: 50%, 60% or 80%, depending on the project/funder).
To help us track our recruitment effort, please indicate in your email – cover/motivation letter where (nearmejobs.eu) you saw this posting.