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.

A multidisciplinary team, comprising Andrea Chatrian, Dr Richard Colling, Professor Clare Verrill, Professor Jens Rittscher and colleagues, develops an algorithm for automated requesting of additional investigation in diagnostically uncertain prostate biopsies.

Prostate biopsy slides annotated by the AI tool with regions shaded in red (certain) or blue (ambiguous). © The Authors 2021 CC BY 4.0
Prostate biopsy slides annotated by the AI tool with regions shaded in red (certain) or blue (ambiguous).

Nearly 50,000 cases of prostate cancer are diagnosed each year in the UK. During the diagnostic process, men with suspected prostate cancer undergo a biopsy, which is analysed by pathology services. There are over 60,000 prostate biopsies performed in the UK annually, which represents a high workload for pathology teams. With increasing demand and a shortage of pathologists, tools that could help streamline this workflow would provide significant pathologist time savings and accelerate diagnoses.

To confidently diagnose prostate cancer, pathologists need to identify a number of tissue architecture and cellular cues. All biopsies are stained with Hematoxylin & Eosin (H&E), which allows the pathologist to study the size and shape (morphology) of the cells and tissue. However, in 25-50% cases, H&E staining alone does not provide sufficient evidence for a diagnosis, requiring the additional process of immunohistochemistry (IHC) to study other cellular features.

One bottleneck in the current pathology workflow is the requirement for a pathologist to review the H&E-stained biopsies to determine which require IHC. To address this need, pathologists Dr Richard Colling, Dr Lisa Browning and Professor Clare Verrill (Nuffield Department of Surgical Sciences and Oxford University Hospitals NHS Foundation Trust) teamed up with biomedical image analysts Andrea Chatrian, Professor Jens Rittscher and colleagues (Institute of Biomedical Engineering, Big Data Institute and Ludwig Oxford) to take a multidisciplinary approach.

In their paper in the journal Modern Pathologythe team used prostate biopsies annotated by pathologists at Oxford University Hospitals to train an artificial intelligence (AI) tool to detect tissue regions with ambiguous morphology and decide which cases needed IHC. The tool agreed with the pathologist’s review in 81% of cases on average. By enabling automated request of IHC based on the AI tool results, the pathologist would only need to review the case once all necessary staining had been carried out. This workflow improvement is estimated to save on average 11 minutes of pathologist time for each case, which scales up to 165 pathologist hours for 1000 prostate biopsies needing IHC.

The NHS spends £27 million on locum and private services to make up for the shortfall in pathology service provision. By using this AI tool to triage prostate biopsies for IHC, pathologists would spend less time reviewing these cases, which would not only lead to financial savings but it would also accelerate prostate cancer diagnoses to inform patients and treating clinicians earlier - Professor Clare Verrill, Nuffield Department of Surgical Sciences and Oxford University Hospitals NHS Foundation Trust 

Professor Verrill said: “The NHS spends £27 million on locum and private services to make up for the shortfall in pathology service provision. By using this AI tool to triage prostate biopsies for IHC, pathologists would spend less time reviewing these cases, which would not only lead to financial savings but it would also accelerate prostate cancer diagnoses to inform patients and treating clinicians earlier.”

The tool will now be developed and validated further using pathology data from different locations to account for variation in IHC requests between pathologist teams and centres. This future work will continue to take advantage of the PathLAKE Centre of Excellence for digital pathology and artificial intelligence, of which Oxford is a member.

This work was supported by PathLAKE via the Industrial Strategy Challenge Fund, managed and delivered by Innovate UK on behalf of UK Research and Innovation (UKRI), the NIHR Oxford Biomedical Centre, the Engineering and Physical Sciences Research Council (EPSRC), the Medical Research Council (MRC) and the Wellcome Trust.

Similar stories

Omair Shariq wins Best Clinical Paper at the American Association of Endocrine Surgeons 2021 Annual Meeting

Dr Omair Shariq, a DPhil student and clinical research fellow in the Nuffield Department of Surgical Sciences (NDS) and Oxford Centre for Diabetes Endocrinology and Metabolism (OCDEM), has received the 2021 Best Presentation for Clinical Research award during the 41st Annual Meeting of the American Association of Endocrine Surgeons (AAES), which was held virtually on 25-27 April 2021.

Latest issue of JNDS now online

The latest issue of the Journal of the Nuffield Department of Surgical Sciences (JNDS) is now available to read.

New Cochrane evidence explores treatment options for chronic ear disease

A new Evidently Cochrane blog post for World Hearing Day summarises seven recent reviews on medical treatments for infection and inflammation of the middle ear.

New reporting guidelines to bridge the gap from development to implementation in clinical artificial intelligence

In a correspondence to Nature Medicine, a team of Oxford-led academics describe upcoming new guidelines to improve the reporting of early clinical stage (or first-with-human) evaluation of decision support systems driven by artificial intelligence.

Cochrane ENT awarded NIHR funding for COVID-19 project

Cochrane ENT at the Nuffield Department of Surgical Sciences has been awarded funding by the National Institute for Health Research (NIHR) to complete a suite of living systematic reviews investigating the effectiveness and safety of interventions to prevent and treat loss of smell after COVID-19 infection.

JNDS: new issue out now

Journal of the Nuffield Department of Surgical Sciences (JNDS) has published its next issue, featuring top case reports written by University of Oxford medical students during their clinical studies.

Blog posts

Celebrating women of NDS

To celebrate 100 years since women were admitted as full members of the University and on the occasion of International Women's Day, a group of inspirational women in the Nuffield Department of Surgical Sciences (NDS) reflect on their journeys, their place in Medical Sciences and their vision for the next 100 years.

The life of a research nurse: supporting the Oxford COVID-19 Vaccine Trial

Research nurses in the NHS are playing a crucial role in helping to trial new coronavirus treatments and vaccines. Three NDS research nurses stepped up to help with the fight against this new disease. Here Bhumika Patel shares her experience of working on the Oxford COVID-19 Vaccine Trial.

Why I became a Peer Supporter

The Peer Support Programme was developed in recognition of the essential role students play in supporting and encouraging one another on a day-to-day basis throughout their time at university. NDS’ own Helen Stark discusses her experience of becoming a Peer Supporter.

Racism under the microscope

As Black History Month gets underway in the UK, NDS Athena SWAN Coordinator Emily Hotine puts racism under the microscope.

In memory of Sue Bonnington

Pete Holding shares his memories of a much-loved colleague, Sue Bonnington. Based in Leicester, Sue worked remotely for the Nuffield Department of Surgical Sciences (NDS) as a ProtecT study Lead Research Nurse from 2002 to 2017.