This fully funded, 4-year PhD project is part of a competition funded by the BBSRC EASTBIO Doctoral Training Partnership.
Across our life span, radiological screening techniques are crucial for the health of millions of people. They are, however, still far from perfect: false negative and false positive rates have been reported to be 0.15% and 9%, respectively (Nelson et al., 2016). One critical reason for misdiagnoses is the misinterpretation of radiographs by experts.
When looking at radiographs, experts are typically asked to localize lesions (if present), and then to classify them by judging their size, class, and so on. It is thus crucial for experts to correctly recognize cluttered radiographs, discarding non-relevant material. In everyday life, psychophysical research showed that our percept in cluttered environments is biased by contextual effects. For example, visual perception is limited by ‘crowding’, which is the deleterious influence of nearby objects on object recognition (Manassi et al. 2018). Crowding is a major bottleneck for object recognition, impeding reading and visually guided actions. Given its importance and ubiquity, we will investigate the impact of crowding in radiological screening.
We will first establish with psychophysical methods how visual recognition in radiologists and untrained observers is affected by crowded radiographs. Second, we will characterize what kind of visual elements are mostly impacted by crowding. Third, we will test how AI algorithms in screening perform in crowding situations. Finally, we will compare recognition performance in untrained observers, radiologists, and AI algorithms (de Vries et al. 2021).
The outcome of the research will advance our knowledge regarding perceptual factors underlying the interpretation of medical images. Importantly, it will provide a more integrative understanding of the visual search mechanisms of radiologists and artificial intelligence systems used for medical screening, highlighting critical advantages and disadvantages. The long-term goal is to improve cancer image screening by developing AI algorithms for radiological screening which take contextual effects into account.
The PhD candidate will learn (1) psychophysical techniques, (2) breast cancer imaging techniques and (3) will acquire knowledge regarding AI algorithms implemented for medical image screening. This project will involve developing a high level of expertise in digital signal processing and programming (Matlab, Python, R), skills highly useful in both industry and academia. The project is suitable for candidates with a background in psychology, neuroscience, computer science, engineering (or radiology) who have interests in visual perception or imaging.
- Applicants should hold a minimum of a 2:1 UK Honours degree (or international equivalent) in a relevant subject. Those with a 2:2 UK Honours degree (or international equivalent) may be considered, provided they have (or are expected to achieve) a Distinction or Commendation at master’s level.
- All students must meet the eligibility criteria as outlined in the UKRI guidance on UK, EU and international candidates. This guidance should be read in conjunction with the UKRI Training Grant Terms and Conditions, esp. TGC 5.2 & Annex B.
- It may be possible to undertake this project part-time, in discussion with the lead supervisor, however, please note that part-time study is unavailable to students who require a Student Visa to study within the UK.
- Please visit this page for full application information: How to apply | eastbio (eastscotbiodtp.ac.uk)
- Please send your completed EASTBIO application form, along with academic transcripts to Alison Innes at: [Email Address Removed]
- Two references should be provided by the deadline using the EASTBIO reference form. References should be sent to [Email Address Removed]
- Unfortunately, due to workload constraints, we cannot consider incomplete applications.
- CV's submitted directly through a FindAPhD enquiry WILL NOT be considered.