Development of New Low Cost Point of Care Diagnostic Technologies for Diabetic Retinopathy in China
Lead Research Organisation:
University of Liverpool
Department Name: Institute of Ageing and Chronic Disease
Abstract
We will develop novel, low-cost, diagnostic technologies for the detection of a blinding condition called diabetic retinopathy (DR) in China. These technologies will enable cost-effective, large-scale detection of sight-threatening disease to be performed by non-expert health care workers at the time and place of patient care in China.
Over 110 million people in China live with diabetes and this number is expected to increase to 150m by 2040. Diabetes causes visual loss through damage to blood vessels of the retina at the back of the eye. Treatments are effective (and increasingly affordable in China) but only if the disease is detected early enough. Improving early diagnosis and treatment of DR is one of the principal objectives of the Chinese Government's 5-Year National Plan of Eye Health (2016-2020). Current methods of detecting DR rely on costly imaging equipment and many skilled personnel to take and interpret retinal images. China has very few health workers with these skills. Case detection strategies which are cost-effective in Western Europe cannot possibly be replicated at the scale necessary for China.
Building on an existing collaboration between the University of Liverpool, Peking University and the Chinese Medical Association (CMA), our joint research team from Liverpool and China of engineers, statisticians, education specialists, eye doctors and health economists are well placed to develop a new diagnostic imaging solution tailored to local needs.
Our objectives for this project are:
1. To develop a novel, low-cost, robust imaging device for detection of DR
2. To develop new automated computer algorithms to rate images of the retina for sight-threatening disease
3. To develop a novel comparative judgement method to refine the DR severity grading from automated computer algorithms
4. To validate the new technologies in the UK and test them in China to ensure maximum cost-effectiveness
We will develop a new low-cost, camera designed specifically for the needs of China. This device will produce both high-quality colour images and optical coherence tomography (OCT) images of the retina. OCT is widely available but current commercial systems are very expensive. Our new device will be based on our novel patent-pending technology and will be first tested on human donor tissue.
We will develop and evaluate new, automated image analysis techniques allowing computers to learn to analyse both colour and OCT images of the retina. We aim to produce systems capable of differentiating between patients with and without DR and between those with mild/moderate and severe disease at the time and place of patient care.
In order to achieve a high level of diagnostic accuracy (over and above automated image analysis), we will develop and evaluate a new human learning system. This system will harness the collective judgements of Chinese health workers to rank images in terms of DR severity. We will create a self-sustaining network of activity where novices and experts support each other in making effective clinical judgements. We will develop new statistical methods to underpin the system and to evaluate both diagnostic accuracy and performance of the health workers. Our imaging and diagnostic system will be validated in 241 patients with diabetes in the UK. Our project team in China will then undertake a pilot study of 461 patients and a costing exercise. The diagnostic accuracy of the system and its cost-effectiveness will be investigated.
We will engage policy makers through our Chinese team who occupy leading roles in the CMA. Detection and treatment of sight threatening DR will prevent disability with benefit to Chinese society and China's economy. Our systems will upskill health care workers, strengthen existing health systems and build research capacity in China. Dissemination of our techniques through open-source software will maximise benefits for other low and middle-income countries.
Over 110 million people in China live with diabetes and this number is expected to increase to 150m by 2040. Diabetes causes visual loss through damage to blood vessels of the retina at the back of the eye. Treatments are effective (and increasingly affordable in China) but only if the disease is detected early enough. Improving early diagnosis and treatment of DR is one of the principal objectives of the Chinese Government's 5-Year National Plan of Eye Health (2016-2020). Current methods of detecting DR rely on costly imaging equipment and many skilled personnel to take and interpret retinal images. China has very few health workers with these skills. Case detection strategies which are cost-effective in Western Europe cannot possibly be replicated at the scale necessary for China.
Building on an existing collaboration between the University of Liverpool, Peking University and the Chinese Medical Association (CMA), our joint research team from Liverpool and China of engineers, statisticians, education specialists, eye doctors and health economists are well placed to develop a new diagnostic imaging solution tailored to local needs.
Our objectives for this project are:
1. To develop a novel, low-cost, robust imaging device for detection of DR
2. To develop new automated computer algorithms to rate images of the retina for sight-threatening disease
3. To develop a novel comparative judgement method to refine the DR severity grading from automated computer algorithms
4. To validate the new technologies in the UK and test them in China to ensure maximum cost-effectiveness
We will develop a new low-cost, camera designed specifically for the needs of China. This device will produce both high-quality colour images and optical coherence tomography (OCT) images of the retina. OCT is widely available but current commercial systems are very expensive. Our new device will be based on our novel patent-pending technology and will be first tested on human donor tissue.
We will develop and evaluate new, automated image analysis techniques allowing computers to learn to analyse both colour and OCT images of the retina. We aim to produce systems capable of differentiating between patients with and without DR and between those with mild/moderate and severe disease at the time and place of patient care.
In order to achieve a high level of diagnostic accuracy (over and above automated image analysis), we will develop and evaluate a new human learning system. This system will harness the collective judgements of Chinese health workers to rank images in terms of DR severity. We will create a self-sustaining network of activity where novices and experts support each other in making effective clinical judgements. We will develop new statistical methods to underpin the system and to evaluate both diagnostic accuracy and performance of the health workers. Our imaging and diagnostic system will be validated in 241 patients with diabetes in the UK. Our project team in China will then undertake a pilot study of 461 patients and a costing exercise. The diagnostic accuracy of the system and its cost-effectiveness will be investigated.
We will engage policy makers through our Chinese team who occupy leading roles in the CMA. Detection and treatment of sight threatening DR will prevent disability with benefit to Chinese society and China's economy. Our systems will upskill health care workers, strengthen existing health systems and build research capacity in China. Dissemination of our techniques through open-source software will maximise benefits for other low and middle-income countries.
Planned Impact
Diabetic retinopathy (DR) is the leading cause of blindness in working age people in the majority of industrialised countries. Sight loss from DR undermines the economic productivity of persons in their prime earning years affecting the stability of families and communities who depend on them. Timely laser treatment can prevent 90% of severe vision loss from DR, but only a small minority of those affected in China receive treatment. Our proposed collaboration will address a crucial demand articulated by local stakeholders and the Chinese Government: to develop an environment-specific, cost-effective, scalable model for detection of sight threatening DR. Our project will benefit the following groups:
Researchers
The knowledge gained from this project will lead to benefit for researchers working in the fields of optics, medical image analysis, biostatistics, epidemiology, ophthalmology and health services research.
People living with diabetes in China
The low-cost imaging and diagnostic technologies developed in this project will enable large scale DR detection programmes in China where over 110 million people live with diabetes (Diabetes atlas, 4th edn, 2009). As a result of advocacy to Government by our existing collaborators in the Chinese Medical Association (CMA) (including co-investigator and former CMA president Professor X. Li), health service providers will soon be permitted to charge for DR case detection. We will provide healthcare and social insurance (SheBao) providers with a validated, cost-effective and scalable model of DR case detection. Professor Li will continue to engage policy makers, ensuring national and local government investment in DR services utilising our trial-proven technologies. Detection of sight threatening DR and its timely treatment will preserve vision and quality of life for hundreds of thousands persons with diabetes.
Chinese economy and society
Reduction in healthcare costs for detection and treatment of DR, and increased productivity of persons relieved from visual impairment, will benefit one of the world's largest economies. Preventing disability in working age persons will protect families and communities who depend on them and ensure relatives remain economically productive rather than becoming careers. China has a rapidly growing market in preventative and screening services. Our package will engage a diverse range of providers and thereby create jobs. Crucially our package is flexible to the needs of the provider. Thresholds for disease detection can be adjusted according to the resources available for treatment of DR.
Chinese health care workers
China has very few health workers with the knowledge and skills to interpret retinal images. Our diagnostic technologies will create a network of comparative judgement activity in which novices and experts support each other in making effective clinical judgements. Participation in this network will increase the knowledge and skills of health workers. Utilising existing, non-expert, health care workers will allow our package to integrate into existing health care systems and strengthen them.
Families and individuals affected by diabetes in other low and middle income countries
Proven models of low-cost, scalable care for the complications of diabetes are desperately needed in other low-resource settings and will offer many of the same health and economic benefits to persons living with diabetes and their families.
UK and global economy
All of the applicants, in particular YS and YZ, have a good track record of engagement with industry. The primary economic benefits of our project will be realised in China. Benefits will also be felt by our industry partner NVIDIA (USA). We are confident that our work will prove influential on software development for medial image analysis in the future. The University of Liverpool Business Gateway is well placed to facilitate further industry collaboration.
Researchers
The knowledge gained from this project will lead to benefit for researchers working in the fields of optics, medical image analysis, biostatistics, epidemiology, ophthalmology and health services research.
People living with diabetes in China
The low-cost imaging and diagnostic technologies developed in this project will enable large scale DR detection programmes in China where over 110 million people live with diabetes (Diabetes atlas, 4th edn, 2009). As a result of advocacy to Government by our existing collaborators in the Chinese Medical Association (CMA) (including co-investigator and former CMA president Professor X. Li), health service providers will soon be permitted to charge for DR case detection. We will provide healthcare and social insurance (SheBao) providers with a validated, cost-effective and scalable model of DR case detection. Professor Li will continue to engage policy makers, ensuring national and local government investment in DR services utilising our trial-proven technologies. Detection of sight threatening DR and its timely treatment will preserve vision and quality of life for hundreds of thousands persons with diabetes.
Chinese economy and society
Reduction in healthcare costs for detection and treatment of DR, and increased productivity of persons relieved from visual impairment, will benefit one of the world's largest economies. Preventing disability in working age persons will protect families and communities who depend on them and ensure relatives remain economically productive rather than becoming careers. China has a rapidly growing market in preventative and screening services. Our package will engage a diverse range of providers and thereby create jobs. Crucially our package is flexible to the needs of the provider. Thresholds for disease detection can be adjusted according to the resources available for treatment of DR.
Chinese health care workers
China has very few health workers with the knowledge and skills to interpret retinal images. Our diagnostic technologies will create a network of comparative judgement activity in which novices and experts support each other in making effective clinical judgements. Participation in this network will increase the knowledge and skills of health workers. Utilising existing, non-expert, health care workers will allow our package to integrate into existing health care systems and strengthen them.
Families and individuals affected by diabetes in other low and middle income countries
Proven models of low-cost, scalable care for the complications of diabetes are desperately needed in other low-resource settings and will offer many of the same health and economic benefits to persons living with diabetes and their families.
UK and global economy
All of the applicants, in particular YS and YZ, have a good track record of engagement with industry. The primary economic benefits of our project will be realised in China. Benefits will also be felt by our industry partner NVIDIA (USA). We are confident that our work will prove influential on software development for medial image analysis in the future. The University of Liverpool Business Gateway is well placed to facilitate further industry collaboration.
Publications
Zhao Z
(2021)
Characterization of Electrical-Thermal-Mechanical Deformation of Bonding Wires Under Silicone Gel Using LF-OCT
in IEEE Transactions on Power Electronics
Zhang Z
(2023)
Rapid imaging and product screening with low-cost line-field Fourier domain optical coherence tomography.
in Scientific reports
Yang X
(2022)
Using a graph-based image segmentation algorithm for remote vital sign estimation and monitoring.
in Scientific reports
Wu X
(2020)
Cooperative Low-Rank Models for Removing Stripe Noise From OCTA Images.
in IEEE journal of biomedical and health informatics
Description | (1) a new low-cost fundus camera combined with OCT was developed and now ready for a clinical study (2) New AI solution was developed tailored for automated diabetic screening, which is under consideration for a patent, and subject to a clinical study (3) New health economics models were developed |
Exploitation Route | Commercialisation of the new hardware and software developed will be a key step to move forward. |
Sectors | Digital/Communication/Information Technologies (including Software) Education Electronics Healthcare Manufacturing including Industrial Biotechology |
Description | A new spin-out company, AI Sight Ltd, has been made to commercialise a next generation AI system that will revolutionise diabetic eye screening. AI Sight Ltd is underpinned by The University of Liverpool AI system research funded by this EPSRC award. |
First Year Of Impact | 2022 |
Sector | Digital/Communication/Information Technologies (including Software),Healthcare |
Impact Types | Economic |
Description | AI4EYE: Is AI the future for eye screening |
Amount | £21,600 (GBP) |
Funding ID | 2020-RLWK12-10206 |
Organisation | British Council |
Sector | Charity/Non Profit |
Country | United Kingdom |
Start | 01/2021 |
End | 12/2021 |
Description | Development of AI Techniques to Predict Eye Cancer Using Big Longitudinal Data |
Amount | £149,667 (GBP) |
Organisation | National Institute for Health Research |
Sector | Public |
Country | United Kingdom |
Start | 01/2021 |
End | 12/2021 |
Description | EYE-SCREEN-4-DPN: Development of an innovative Intelligent EYE imaging solution for SCREENing of Diabetic Peripheral Neuropathy |
Amount | £1,019,988 (GBP) |
Funding ID | EP/X01441X/1 |
Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
Sector | Public |
Country | United Kingdom |
Start | 07/2023 |
End | 07/2027 |
Description | Predicting Acute and Post-Recovery Outcomes in Cerebral Malaria by Optical Coherence Tomography |
Amount | £1,378,334 (GBP) |
Funding ID | 222530/Z/21/Z |
Organisation | Wellcome Trust |
Sector | Charity/Non Profit |
Country | United Kingdom |
Start | 09/2021 |
End | 09/2025 |
Description | Translation to policy, practice and product for low and middle income countries |
Amount | £658,971 (GBP) |
Funding ID | EP/T015217/1 |
Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
Sector | Public |
Country | United Kingdom |
Start | 09/2019 |
End | 03/2022 |
Company Name | AI Sight |
Description | AI Sight develops artificial intelligence (AI) technology that analyses images from diabetic retinopathy screenings, a medical screening aiming to detect eye diseases and prevent blindness. |
Year Established | 2022 |
Impact | The company has received investment from the University of Liverpool's Enterprise Investment Fund to provide start-up capital and is currently raising its Series A venture capital funding. The University of Liverpool AI system research was funded by EPSRC and the Chief Investigator was Yalin Zheng, Professor of AI in Healthcare. |
Website | https://www.ai-sight.co.uk/ |
Description | Grading for Diabetic Retinopathy - An Interactive Session introducing Comparison as a Tool to Improve Accuracy |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Professional Practitioners |
Results and Impact | In this session we will introduce some new concepts in grading for DR and revise the current feature based approach and classification systems. We will ask delegates to contribute. There will be an interactive grading session to help develop your skills and to introduce comparison as an aid to grading. You will need to be at a laptop to get the most out of the session. We will forward the slide deck in advance. The session is aimed at ophthalmologists, screeners and optometrists engaged in grading and managing DR and Scientists and technicians involved in image analysis and grading. |
Year(s) Of Engagement Activity | 2021 |
Description | Grading for Diabetic Retinopathy - An Interactive Session introducing Comparison as a Tool to Improve Accuracy |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Professional Practitioners |
Results and Impact | This short series of training events is aimed at all clinical trainees, scientists working in fields related to AI and DR, and trained eye health care professionals interested in refreshing or extending their skills/knowledge in AI and DR. Over the 3 events we will present the latest developments in key areas of DR and will include interactive training in assessing the retina. There will be an offline training module to be taken between the two sessions. |
Year(s) Of Engagement Activity | 2021 |
Description | Grading for Diabetic Retinopathy - An Interactive Session introducing Comparison as a Tool to Improve Accuracy (Part 1) |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Professional Practitioners |
Results and Impact | This short series of training events is aimed at all clinical trainees, scientists working in fields related to AI and DR, and trained eye health care professionals interested in refreshing or extending their skills/knowledge in AI and DR. Over the 3 events we will present the latest developments in key areas of DR and will include interactive training in assessing the retina. There will be an offline training module to be taken between the two sessions. |
Year(s) Of Engagement Activity | 2021 |
Description | Invitation to attend St Paul's PIER (Patient Involvement in Eye Research) |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | Regional |
Primary Audience | Patients, carers and/or patient groups |
Results and Impact | This is a special meeting being held to recognise the contribution Sister Sandy Taylor has made to the development of the PPIER group and she has been asked to be a guest speaker reflecting on her experience of the evolution of clinical research in ophthalmology. |
Year(s) Of Engagement Activity | 2018 |
Description | Participation in an activity, workshop or similar - Invitation to attend St Paul's PIER (Patient Involvement in Eye Research) |
Form Of Engagement Activity | A formal working group, expert panel or dialogue |
Part Of Official Scheme? | No |
Geographic Reach | Local |
Primary Audience | Patients, carers and/or patient groups |
Results and Impact | 15 members of the patient group attended 2 meetings, held in September 2019 and December 2019. The purpose of the meeting was to understand the groups opinions on Diabetic Retinopathy diagnosis / referral provided by a computer and what we could do to ensure they had more confidence with computer results. There were also discussions around how the current OCT device is uncomfortable for patients which allowed us to incorporate changes to our model for the patients comfort. |
Year(s) Of Engagement Activity | 2019 |
Description | meeting with SPEU PPIER |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | Regional |
Primary Audience | Patients, carers and/or patient groups |
Results and Impact | We met with the PPIER group and provided an update of the progress of our research projects that have been supported by the group, and sought supports for future research projects. The group was very excited about the achievements and will continue to support our ongoing research. Th group has also expressed their opinions on the use of AI in healthcare. |
Year(s) Of Engagement Activity | 2023 |