SBRI: Skin Cancer detection using Artificial Intelligence

NHS Forth Valley, on behalf of the AI Dermatology Consortium, NHS Scotland and the Scottish Health and Industry Partnership (SHIP), Scottish Government are hosting the AI Dermatology Open Innovation Challenge.

This challenge will provide an opportunity for companies to enhance or refine existing AI algorithms developed using healthcare data, for testing in redesigned community to hospital referral pathways. This will lead to accelerated detection and diagnosis of skin cancer and better use of constrained healthcare resources.

This is a Small Business Research Initiative (SBRI) competition funded by the Scottish Health Industry Partnership (SHIP).

The aim of the competition is to improve existing Artificial Intelligence (AI) algorithms for skin cancer to accelerate detection and diagnosis. We are seeking partners who wish to improve the diagnostic ability of their AI.

Companies will be expected to understand the performance of their algorithm prior to the challenge. A successful outcome for phase 1 projects would be the ability to improve performance using the new dermatology Digital Imaging and Communications in Medicine (DICOM) standard.

This is phase 1 of a potential 2 phase competition. The decision to proceed with phase 2 will depend on the outcomes from phase 1 and assessment of a separate application into a subsequent phase 2 competition.

Successful companies going through to phase 2 will improve and refine the capability of the algorithm to diagnose skin cancer using simulated, or actual healthcare data and present data back to the clinician in a way that fits with the clinical diagnostic process and pathway.

Only the successful applicants from phase 1 will be invited to apply to take part in phase 2.

Any adoption and implementation of a solution from this competition would be subject to a separate, possibly competitive, procurement exercise. This competition does not cover the purchase of any solution.

Eligibility

Phase 1 projects must:

• aim to start by 1 September 2023
• end 4 months after the agreed start date
• work with the identified NHS Scotland Regional Test Bed and academic research partner to develop their solution
• provide details of certification and compliance with relevant standards and regulations for developed algorithms, for example: CA/CE mark, ISO13485

Successful applicants from phase 1 will be invited to apply to take part in a potential phase 2 of the competition.

To lead a project, you can:

• be an organisation of any size, registered in the UK, European Union (EU) or the European Economic Area (EEA)
• work alone or with others from business, academia research, and technology organisations or the third sector, as subcontractors

You must work in conjunction with the identified test bed partner and identified academic research partner. The initial test bed site will be NHS Tayside working with the academic research partner, The Health Informatics Centre in Dundee University.

Scope

The aim of this competition is to improve existing AI algorithms for skin cancer to accelerate detection and diagnosis. To achieve this, applicants will be required to work with real world images and metadata in a standardised, Digital Imaging and Communications in Medicine (DICOM) format in a trusted research environment.

The data pipeline that has been created for this challenge contains standardised image and metadata. This will be captured as part of everyday patient pathways from specifically designed community locality image centres, labelled by consultant dermatologists, and delivered as DICOM format files.

The specific use case for these algorithms is the stream of potential skin cancer referrals from primary to secondary care.

You must:

• have an algorithm that has been developed for potential skin cancer referrals from primary to secondary care
• detail how you will work with the identified test bed and academic research partner by delivering R&D services to develop your solution in preparation for integration into clinical practice and work towards product approval across UK health systems
• set out a plan to work towards necessary approval in the all the UK health systems
• demonstrate a credible and practical route to market, so your application must include a plan to commercialise your results including plans to achieve regulatory compliance where required.

At this stage contracts will be given for phase 1 only. You must define your goals in your application and outline your plan for the potential phase 2. In phase 2 we will ask successful applicants from phase 1 to further improve and refine the capability of their algorithm.

A virtual briefing will be held on Monday 17th April: register below.

If you would like help in finding a project partner, contact Innovate UK KTN’s AI In Health team.