BACKArtificial Intelligence-aided Classification and System for Alzheimer’s Disease Screening from Retinal Photographs
[Licensing negotiation in progress]
[Invitation for Expression of Interest- Deadline: 3 October 2024]
We are inviting expressions of interest (EoI) for commercializing “Artificial Intelligence-aided Classification and System for Alzheimer’s Disease Screening from Retinal Photographs” technology. The innovation is developed by Dr. Carol Cheung of Department of Ophthalmology and Visuals Sciences of The Chinese University of Hong Kong (CUHK Reference: 21/MED/1055).
The Technology
There is increasing evidence that a range of retinal features identified from retinal fundus photographs are associated with Alzheimer’s disease (AD). Artificial intelligence (AI) deep learning (DL) has been shown to have significant potential for eye disease detection and screening on retinal photographs in different clinical settings, particular in primary care. Nevertheless, the role of DL approaches in detecting patients with AD from retinal photographs has yet to be determined. Besides, integrating DL algorithms into real-time clinical workflow is a priority to realize the significant potential of AI for clinical diagnosis and disease risk stratification. However, an automated pre-diagnosis image assessment is essential to streamline the application of the developed AI algorithms.
We developed an artificial intelligence-aided classification and visualization system for AD screening from retinal photographs, which includes a three-in-one DL-based “pre-diagnosis module” for image assessment and a DL-based AD classification and visualization module. For AD classification and visualization module, we developed three kinds of DL models which predict the “needs attention” /”low risk
probabilities from three directions with both eyes’ information (Direction-1), demographical information with both eye (Direction-2), and single eye information (Direction-3), respectively. For the pre-diagnosis image assessment, it consists one pre-processing model, with three additional models for each of the three classification tasks.
The invention is a cloud-based web application and can output the pre-diagnosis image assessment (i.e., image-quality, field-of-view, and laterality-of-the-eye) and a simple binary “needs attention”/”low risk” classification based on retinal photographs could add a complimentary risk profiling tool for AD and assist physicians to identify asymptomatic individuals who are more likely to have AD in the community. Higher-risk individuals could then benefit by selective referral for more intensive and specific examinations (e.g., PET imaging, plasma assays for amyloid-β and phosphorylated tau) at highly specialized clinics for facilitating early AD diagnosis and allowing the individuals to take prevention measures, such as lifestyle modification and control of risk factors. The invention will be incorporated into retinal photography devices for automated image analysis and AD screening in different scenarios.
Commercialization
The technology is now available for licensing on an exclusive basis. In order to fully realize the benefit of the technology, we expect substantial investment is necessary to enable further research and development. In addition to the financial commitment, the licensee is expected to have the appropriate expertise as well as plans in marketing and strategizing the end product to ensure successful transfer of the technology to the society. Previous or existing business involvement and experience in this area is a plus.
This invitation of expression of interest is without prejudice. We also stress that this invitation is not a tender, and the University is not bound to accept any offer, or to accept the highest monetary offer, as there are additional considerations (such as the widest possible benefit to the community) that we, as a public institution, will need to take into consideration.
Artificial Intelligence-aided Classification and System for Alzheimer’s Disease Screening from Retinal Photographs
[Licensing negotiation in progress]
[Invitation for Expression of Interest- Deadline: 3 October 2024]
We are inviting expressions of interest (EoI) for commercializing “Artificial Intelligence-aided Classification and System for Alzheimer’s Disease Screening from Retinal Photographs” technology. The innovation is developed by Dr. Carol Cheung of Department of Ophthalmology and Visuals Sciences of The Chinese University of Hong Kong (CUHK Reference: 21/MED/1055).
The Technology
There is increasing evidence that a range of retinal features identified from retinal fundus photographs are associated with Alzheimer’s disease (AD). Artificial intelligence (AI) deep learning (DL) has been shown to have significant potential for eye disease detection and screening on retinal photographs in different clinical settings, particular in primary care. Nevertheless, the role of DL approaches in detecting patients with AD from retinal photographs has yet to be determined. Besides, integrating DL algorithms into real-time clinical workflow is a priority to realize the significant potential of AI for clinical diagnosis and disease risk stratification. However, an automated pre-diagnosis image assessment is essential to streamline the application of the developed AI algorithms.
We developed an artificial intelligence-aided classification and visualization system for AD screening from retinal photographs, which includes a three-in-one DL-based “pre-diagnosis module” for image assessment and a DL-based AD classification and visualization module. For AD classification and visualization module, we developed three kinds of DL models which predict the “needs attention” /”low risk
probabilities from three directions with both eyes’ information (Direction-1), demographical information with both eye (Direction-2), and single eye information (Direction-3), respectively. For the pre-diagnosis image assessment, it consists one pre-processing model, with three additional models for each of the three classification tasks.
The invention is a cloud-based web application and can output the pre-diagnosis image assessment (i.e., image-quality, field-of-view, and laterality-of-the-eye) and a simple binary “needs attention”/”low risk” classification based on retinal photographs could add a complimentary risk profiling tool for AD and assist physicians to identify asymptomatic individuals who are more likely to have AD in the community. Higher-risk individuals could then benefit by selective referral for more intensive and specific examinations (e.g., PET imaging, plasma assays for amyloid-β and phosphorylated tau) at highly specialized clinics for facilitating early AD diagnosis and allowing the individuals to take prevention measures, such as lifestyle modification and control of risk factors. The invention will be incorporated into retinal photography devices for automated image analysis and AD screening in different scenarios.
Commercialization
The technology is now available for licensing on an exclusive basis. In order to fully realize the benefit of the technology, we expect substantial investment is necessary to enable further research and development. In addition to the financial commitment, the licensee is expected to have the appropriate expertise as well as plans in marketing and strategizing the end product to ensure successful transfer of the technology to the society. Previous or existing business involvement and experience in this area is a plus.
This invitation of expression of interest is without prejudice. We also stress that this invitation is not a tender, and the University is not bound to accept any offer, or to accept the highest monetary offer, as there are additional considerations (such as the widest possible benefit to the community) that we, as a public institution, will need to take into consideration.
N/A
Ms. Erika YUEN
Office of Research and Knowledge Transfer Services
Dr. Carol Cheung
N/A