Cookies on this website
We use cookies to ensure that we give you the best experience on our website. If you click 'Continue' we'll assume that you are happy to receive all cookies and you won't see this message again. Click 'Find out more' for information on how to change your cookie settings.

The new Oxford-developed artificial intelligence tool PathProfiler automates the quality control of large retrospective pathology image datasets to increase their usability in downstream research.

Examples of pathology image artefacts
Examples of pathology image artefacts

During investigations for cancer, a tissue biopsy may be taken and studied under the microscope to identify abnormal cells. This can help to diagnose and characterise cancer if present, and guide treatment selection. 

In more recent times the development of diagnostic digital pathology has gained interest, whereby instead of a light microscope for assessment of a histopathology image, the image is digitised and viewed on a computer screen. Although to date there are limited NHS Cellular Pathology departments with access to such facilities (Oxford being one such centre within the PathLAKE consortium), there is an increasing drive towards the use of digital pathology within the clinical setting, which brings with it the potential to use artificial intelligence (AI) tools. 

To realise this opportunity, there has been a surge in research focused on developing and using AI to support pathologists in the assessment of diagnostic biopsies and also in uncovering new disease biology. However, to develop and train AI algorithms requires large datasets of digitised pathology images accompanied by clinical outcome data. Gathering such large datasets requires collating images from multiple diagnostic laboratories, which introduces potential variability in image quality and the risk of a negative impact on downstream analysis. Furthermore, digitised images are often collated retrospectively from stored histopathology glass slides that are subject to age- and storage-related imaging artefacts. 

Image quality in the training dataset is known to have an impact on the performance of AI models and the reliability of the generated results. For this reason, it is important to assess image quality during the development and use of AI algorithms. Currently reliant upon manual assessment by pathologists, this is unsustainable given the need for increasingly large datasets; an automated tool is needed to assess image quality that takes into account a combination of potential artefacts and recognises the potential for an intervention to improve the quality.

To address this need, pathologists Dr Lisa Browning (Department of Cellular Pathology, Oxford University Hospitals (OUH) NHS Trust) and Professor Clare Verrill (Nuffield Department of Surgical Sciences and Department of Cellular Pathology, OUH) teamed up with Dr Maryam Haghighat (Institute of Biomedical Engineering, Department of Engineering) and Professor Jens Rittscher (Institute of Biomedical Engineering, Big Data Institute and Ludwig Oxford).

Using retrospective pathology images from the ProMPT (Prostate Cancer Mechanisms of Progression and Treatment) prostate cancer cohort, the team developed PathProfiler, an AI tool to automate quality assessment including a range of potential image artefacts. The tool outputs a usability score, which will help to guide whether an image can be included in the AI training dataset. The scores from the AI algorithm and manual scoring by three expert pathologists were highly correlated (0.89). 

To further test PathProfiler, the team assessed the Cancer Genome Atlas prostate and FOCUS colorectal cancer cohorts. In addition to providing a quality score and indicating quality-impacting artefacts that are present, PathProfiler is also able to predict which images could be improved for example, by re-scanning or re-staining. This prediction becomes important particularly for highly curated retrospective cohorts such as those used in prostate cancer research. 

The PathProfiler software is available to the public so that other groups can use it for their own research and contribute to the further development of this methodology. The team now plan to further optimise the model, including taking into account additional artefacts observed in other tissue types and cohorts, and to assess the performance and utility of the tool within a clinical pathology digital pipeline.

This study is published in Scientific Reports.

Similar stories

Oxford's largest ever study into varicose veins shows need for surgery is linked to genetics

Varicose veins are a very common manifestation of chronic venous disease, affecting over 30% of the population in Western countries. In America, chronic venous disease affects over 11 million men and 22 million women aged 40–80 years old. Left untreated it can escalate to multiple health complications including leg ulcers and ultimately amputations. A new international study by Oxford researchers published on 2 June 2022 in Nature Communications establishes for the first time, a critical genetic risk score to predict the likelihood of patients suffering with varicose veins to require surgery, as well as pointing the way towards potential new therapies.

New reporting guidelines developed to improve AI in healthcare settings

New reporting guidelines, jointly published in Nature Medicine and the BMJ by Oxford researchers, will ensure that early studies on using Artificial Intelligence (AI) to treat real patients will give researchers the information needed to develop AI systems safely and effectively.

Study finds higher risk of all-cause mortality among paediatric cancer patients in LMICs during the pandemic

During the first nine months of the COVID-19 pandemic, paediatric cancer patients from lower- and middle-income countries (LMICs) faced a higher risk of all-cause mortality than those in high-income countries, according to an international study led by the University of Oxford.

Blog posts

Oxford MedSci goes silver: 10 Years of Athena SWAN

The Medical Sciences Division is celebrating 10 years since its first Athena Swan bronze application, and the first year in which all 16 of its departments have achieved a silver award. The silver award recognises commitment to gender equality, understanding culture and context, and more. Read about our department’s hard work and innovation.

Lights, camera, action! My journey into video production

Dr Hannah McGivern provides a 'behind-the-scenes' account of her experience producing the video 'Journey of a QUOD Sample: Donating to Transplant Research', supported by the funds from the University of Oxford Public Engagement with Research (PER) Seed Fund.

Mentoring in practice

NDS has launched a new, interdepartmental mentoring scheme called RECOGNISE. In this podcast, Gemma Horbatowski (HR Advisor) interviews Monica Dolton (Programme Manager and Research Project Manager) about her experiences of mentor-mentee relationships.