The PathLAKE (Pathology image data Lake for Analytics, Knowledge and Education) is a cross-faculty research consortium comprising researchers from the University of Warwick, University Hospitals Coventry and Warwickshire NHS Trust, and Royal Philips to create a national centre of excellence in AI in pathology, linked to five digitised NHS pathology labs. The cutting-edge AI technologies will assist pathologists in diagnosing cancer more efficiently and selecting the optimal treatment for cancer patients.
Highlights of PathLAKE:
- A unique data resource of cancer images and artificial intelligence (AI) techniques will be developed, led by Professor Nasir Rajpoot of the Department of Computer Science at the University of Warwick - as part of a £15.7m project with £10m funding awarded by UK Research and Innovation (UKRI) for the PathLAKE project.
- The University of Warwick researchers will work together with University Hospitals Coventry and Warwickshire NHS Trust and Royal Philips to create a national centre of excellence in AI in pathology, linked to five digitised NHS pathology labs.
- The cutting-edge technologies will assist pathologists in diagnosing cancer more efficiently and selecting the optimal treatment for cancer patients – which could bring an end to the ‘limbo’ of waiting for a diagnosis.
The University of Warwick is leading the computational arm of PathLAKE, working together with partners and experts at the lead partner University Hospitals Coventry and Warwickshire NHS Trust, Royal Philips and teaching hospitals and universities at Belfast, Oxford and Nottingham in the three-year project, focussing on breast, prostate, lung and colon cancers.
The aim of PathLAKE is to significantly speed up the time in which cancer is diagnosed and treated, by using Innovative solutions in digital pathology and Artificial Intelligence (AI).
The PathLAKE Vision. The image is a colourful lightbulb illustration divided into different sections: At the bottom of the lightbulb, an electrical current icon and the words "Digitisation PathLAKE Innovation Platform". The next section going up the lightbulb, a waves icon and "Well Curated Data Repository". Then a small lightbulb icon and "AI Innovation R&D". Then a handshake icon and "Validation and Regulatory". Then a money and dollar icon and "Commercialization". At the top of lightbulb a doctor icon and "Clinical Adoption" .
The PathLAKE consortium aims to meet the ‘Data to Early Diagnosis and Precision Medicine Challenge’ through two high-impact exemplar projects. Firstly, by embedding and demonstrating the diagnostic efficiencies of computer aided testing of pathology samples. Secondly, by developing novel AI tools to support advanced identification of predictive chemotherapy response markers for personalised medicine and markers of disease progression in disease surveillance.
Working ethically within stringent regulatory and industry standards, a unique data resource comprising of large number of pathology images will provide a foundation archive to support exemplar projects in AI based diagnostic efficiency and optimal treatment selection. These images and tools will be made available across the consortium partners, including industrial partners Philips, Nvidia and four SMEs (Small and medium-sized enterprises – independent firms) in Perspectum, Oxford Cancer Biomarkers, Glencoe Software and Sonrai to support the development of a burgeoning UK digital health industry.
The consortium will also provide the backbone of a network for multi-site clinical trials and further advanced research projects to provide world-class training and education to the pathology and computer science communities.
- Establish a national centre of excellence for the use of digtial pathology and AI in pathology
- Improve efficiency of pathology reporting and selection of patients for personalised medicine
- Support the growth of this sector and job creation to ensure UK leadership in pathology AI
- Generate significant know-how through a multidisciplinary, integrated AI programme focused on tissue and cellular pathology
- Create a pathway for AI tool adoption in the NHS