An AI Model to Estimate Visual Acuity after treatment Based Solely on Cross-Sectional OCT Imaging of Various Diseases

2020 Fiscal Year Final Research Report

• Project/Area Number: 19K18888
• Research Category: Grant-in-Aid for Early-Career Scientists
• Allocation Type: Multi-year Fund
• Review Section: Basic Section 56060:Ophthalmology-related
• Research Institution: Jichi Medical University
• Principal Investigator: Inoda Satoru 自治医科大学, 医学部, 助教 (60741098)
• Project Period (FY): 2019-04-01 – 2021-03-31
• Keywords: OCT / Deep leaning / 加齢黄斑変性症

Outline of Final Research Achievements

An AI model could estimate the best-corrected visual acuity on the day of taking and on the a month after intravitreal anti-vascular endothelial growth factor injection on the solely based on the cross-sectional optical coherence tomography image with R =0.65 and 0.91, respectively. In the further study, by specifying the number or the frequency of intravitreal anti-vascular endothelial growth factor injections, an AI model would show the predictable change of visual acuity numerically. Although the estimate accuracy of visual acuity on the taking time solely based on cross-sectional optical tomography image was 0.65, for the eyes of age-related macular degeneration where retinal change are important for visual acuity, the optical coherence tomography images were important to estimate the change of visual acuity.

Free Research Field

眼科

Academic Significance and Societal Importance of the Research Achievements

簡易に撮影できる光干渉断層計のみから、視力予測を数値的に表すことで、加齢黄斑変性症の専門外の医師においても加療の必要性を数字で示すことができ、過剰・過小治療を予防することができる。また、専門外の患者は、自身の治療方針について考えを示しにくいが、数値的予測がでることで、金銭的・身体的侵襲性を考慮しつつ、医師とともに治療方針について参加しやすくなるだろう。