September 11, 2024 
DeepEyeVision Inc.

DeepEyeVision Inc., a venture from Jichi Medical University (Headquarters: Shimotsuke, Tochigi Prefecture,Japan; CEO: Hidenori Takahashi, hereinafter referred to as “DeepEyeVision”), embarks on R&D aimed at improving the accuracy of glaucoma diagnosis, the leading cause of blindness among middle-aged and elderly in Japan. The company is developing a method using AI to estimate “visual field” values necessary for glaucoma diagnosis from OCT (Optical Coherence Tomography) images of the eye.

 1. Background of the R&D

In Japan, one in twenty people over the age of 40 suffers from glaucoma, which is also the leading cause of blindness among middle-aged and elderly individuals^*1. As a result, glaucoma is one of the factors contributing to the shortening of healthy life expectancy in Japan, where rapid aging is occurring.

While early detection and timely initiation of treatment can slow the progression of glaucoma, it remains an incurable disease. Therefore, after beginning treatment, patients are required to make continuous visits to medical facilities and undergo visual field tests, which demand high concentration to assess visual field defects. This imposes significant economic and psychological burdens on patients, posing a serious social challenge.

Furthermore, from the perspective of medical institutions, the treatment of glaucoma necessitates the implementation of visual field tests^*2, which typically take about 15 minutes each. This requirement places a considerable burden on medical staff, highlighting another critical issue in glaucoma management.

2. Research Content and Significance

In response, DeepEyeVision has initiated research and development aimed at improving the accuracy of early-stage glaucoma diagnosis and enhancing the efficiency of testing through the use of AI. Specifically, the company is developing a program that employs deep learning technology to estimate visual fields from cross-sectional images of the eye taken with OCT. This program aims to significantly reduce the time required for visual field testing, thereby alleviating the burden on both patients and medical institutions^*3.

Additionally, by accumulating the quantitative measurement results obtained from the program in a database for each patient, the company is exploring the development of methods to support physicians in formulating treatment plans.

To advance this research and development, DeepEyeVision has appointed Dr. Makoto Koyama, the director of Minamikoyasu Eye Clinic in Kimitsu City, Chiba Prefecture, Japan, as an advisor. Dr. Koyama has previously presented^*4 an AI model for estimating Humphrey visual fields at the Japan Ophthalmic AI Society, among other platforms. In addition, DeepEyeVision has initiated technical exchanges with several academic institutions, including Jichi Medical University and the University of Tsukuba, as well as with OCT manufacturers both domestically and internationally.

Through these initiatives, DeepEyeVision aims to implement this program in society in the future^*5 and reduce the number of patients whose health is compromised by glaucoma.

3. Symposium Presentation and Exhibition at the 35th Meeting of the Japan Glaucoma Society

Regarding this research, Dr. Makoto Koyama, an advisor to DeepEyeVision, will be presenting at the following session:

• The 35th Meeting of the Japan Glaucoma Society Symposium 
  • Symposium 2: Utilization of Genomic Information, Big Data, and AI for Precision Medicine in Glaucoma
    • Date: Friday, September 20, 2024, 15:25-16:55 (JST)
    • Venue: Acrea HIMEJI, Room1 (2nd Floor, Main Hall) 
    • Presentation Title: Glaucoma Diagnosis Support Using a 3D AI Model 
    • Presenter: Dr. Makoto Koyama (Minamikoyasu Eye Clinic, Advisor to DeepEyeVision) 
    • URL: https://www.congre.co.jp/jgs2024/program/index.html

Additionally, at the exhibition accompanying this society meeting, a demonstration of this AI model^*6 will be conducted. Please note that this model will be exhibited as a non-approved medical device (not for sale or distribution) in accordance with the application submitted to the conference.

• The 35th Meeting of the Japan Glaucoma Society – Equipment Exhibition
  • Exhibition Period: Friday, September 20, to Sunday, September 22, 2024 
  • Venue: Acrea HIMEJI, Exhibition Hall A+B 
    • Booth Number: 34 
    • Exhibitor: DeepEyeVision

Comments on This R&D (Honorifics Omitted)

Tetsuro Oshika, M.D., Ph.D, Professor, Department of Ophthalmology,  Faculty of Medicine, University of Tsukuba

Dr. Makoto Koyama (Advisor to DeepEyeVision, Director of Minamikoyasu Eye Clinic, and a graduate of the University of Tsukuba) has developed an AI for visual field estimation that is a groundbreaking technology. It significantly reduces the burden on glaucoma patients and improves treatment outcomes. Collaboration with DeepEyeVision, which has contributed to the field of ophthalmic AI, is expected to advance ophthalmic care and further the prevention of blindness.

Kenji Kashiwagi, M.D., Ph.D, Professor, Graduate Faculty of Interdisciplinary Research Faculty of Medicine Clinical Medicine (Ophthalmology), University of Yamanashi

Expectations for Glaucoma Diagnosis
Glaucoma, the leading cause of blindness, poses a significant risk, particularly as aging progresses, and the number of patients is expected to increase. Because glaucoma results in irreversible visual impairment, early detection and appropriate treatment are crucial. However, ensuring early detection requires substantial medical personnel and resources, and effective treatment necessitates patient cooperation. Currently, neither of these conditions is fully met, making it difficult to overcome the challenges presented by glaucoma. The R&D efforts being undertaken by DeepEyeVision are expected to make significant contributions to addressing these challenges.

---

*1 Japan Glaucoma Society: Epidemiological Survey Report of the Tajimi Study, 2012.
*2 There are various methods and devices for visual field testing, and the testing time may vary depending on the method used by the medical institution and the purpose of the test.
*3 This research does not aim to replace conventional visual field tests.
*4 Awarded first place at the 2021 2nd Annual Meeting of the Japan Ophthalmic AI Society’s AI Contest.
Koayama. On a 3D Glaucoma AI Model for Estimating Visual Fields from OCT Images, 2022.
https://jglobal.jst.go.jp/detail?JGLOBAL_ID=202202254722768345
Koyama M et al. 2024. OCT-based Visual Field Estimation Using Segmentation-free 3D CNN Shows Lower Variability than Subjective Standard Automated Perimetry.
MedRxiv doi:　https://doi.org/10.1101/2024.08.17.24312150
*5 While we are also planning the design and development of a medical device program (SaMD), we will proceed by formulating specific plans in accordance with academic perspectives and various legal regulations, including the Pharmaceutical and Medical Device Act. Additionally, the algorithm mentioned in this announcement may not necessarily be applied to the products that DeepEyeVision plans to design and develop in the future.
*6 This model is being exhibited as an unapproved medical device (non-medical device) with application submitted to the conference, and it differs from the products that DeepEyeVision plans to design and develop.

About DeepEyeVision Inc.

DeepEyeVision Inc. is a venture company originating from Jichi Medical University, established by Dr. Hidenori Takahashi, M.D., Ph.D., who is a Professor at the Cybermedicine Research Center of the University of Tsukuba and an Associate Professor in the Department of Ophthalmology at Jichi Medical University. The company was founded with the mission of bringing medical AI technologies developed in academic research to the broader society. Leveraging AI-based imaging diagnostics, DeepEyeVision is committed to advancing not only ophthalmology but also various other medical fields through its research and development efforts.

– CEO: Hidenori Takahashi, M.D., Ph.D.
– Headquarters: C/O Department of Ophthalmology, Jichi Medical University, 3311-1 Yakushiji, Shimotsuke, Tochigi Prefecture, Japan.
– Website: https://deepeyevision.com/

Certifications

– Second-class medical device manufacturing and sales (License No. 09B2X10014)
– Medical Device Manufacturing (Registration No. 09BZ200083)
– Controlled Medical Device Sales Business Notification (Notification No. B42917)

Affiliated Organizations

– Japan Ophthalmic Instrument Association (JOIR)
– Japan Medical Imaging and Radiological Systems Industries Association (JIRA)
– Council for AI Medical Devices
– Japan Ocular Imaging Registry
– Japanese Society of Artificial Intelligence in Ophthalmology

Contact

DeepEyeVision Inc.
E-mail:　pr@deepeyevison.com