Technologies
Our Technologies and Patents
Our company DeepEyeVision has been using cutting-edge deep learning technologies to develop an “ocular fundus imaging diagnosis support
AI” that enables the early detection of diabetes and other systemic diseases as well as eye diseases.
疾患名候補表示AI（非医療機器） Ocular fundus imaging diagnosis support AI
Since 2016, DeepEyeVision has been independently developing this AI-based ocular fundus imaging diagnosis
support system (for research and development) in cooperation with Jichi Medical University.
Based on images taken during ophthalmology medical examinations,
diagnosis candidates are proposed with probabilities.
This system is compatible with products from various medical device manufacturers in Japan,
and DeepEyeVision is continuing to conduct research and development with the aim of realizing a system
that can be applied to medical check-up images and remote diagnosis.
Remote image reading service that utilizes AI
Once a medical institution uploads an ocular fundus image to a cloud system,
the AI analyzes the image and displays candidate disease names to a DeepEyeVision reading doctor.
The reading doctor then makes a diagnosis by observing the original fundus image while referring
to the displayed disease names, after which the reading result is provided to the medical institution.
Introducing this remote image reading service to various medical institutions is expected
to have the following effects.
- The diagnosis results of reading doctors can be standardized to make variance extremely small,
and medical institutions’ problem of a lack of fundus image reading doctors can be eliminated.
- Ophthalmology medical services will become sophisticated throughout Japan, including in remote areas,
and the possibility of early detection will increase for various kinds of diseases,
including diabetes and glaucoma, which are asymptomatic until the terminal stage.
Thanks to these effects, a reduction in medical costs nationwide is expected.
PATENTS
-
US10945598B2
Method for assisting corneal severity identification using unsupervised machine learning
-
特許第6745496号
糖尿病網膜症の病期判定支援システムおよび糖尿病網膜症の病期の判定を支援する方法
PAPERS
-
Keratoconus severity detection from elevation, topography and pachymetry raw data using a machine learning approach
IEEE Access 9 84344-84355 2021年
-
AIを利用した効率的な糖尿病網膜症健診
日本糖尿病合併症学会 35(1) 33-36 2021年
-
Association between visual field damage and corneal structural parameters
Scientific Reports 11 10732 2021年5月
-
Detecting Keratoconus from Corneal Imaging Date using Machine Learning
IEEE Access 8 149113-149121 2020年
-
Predicting the likelihood of need for future keratoplasty intervention using artificial intelligence
The Ocular Surface 18(2) 320-325 2020年4月
-
A Deep Learning Approach in Rebubbling After Descemet’s Membrane Endothelial Keratoplasty
Eye Contact Lens 46(2) 121-126 2020年3月
-
Keratoconus severity identification using unsupervised machine learning
PLOS ONE 13(11) e0205998 2018年11月
-
深層学習によるカラー眼底写真からの脈絡膜厚推測
眼科臨床紀要 10(10) 873 2017年10月
-
Applying artificial intelligence to disease staging: Deep learning for improved staging of diabetic retinopathy
PLOS ONE 12(6) e0179790 2017年6月
CONFERENCE PRESENTATIONS
-
Detecting keratoconus on two different populations using an unsupervised hybrid artificial intelligence model
The Association for Research in Vision and Ophthalmology 2022 Annual Meeting 2022年5月2日
-
A device-agnostic deep learning model for detecting keratoconus based on anterior elevation corneal map
The Association for Research in Vision and Ophthalmology 2022 Annual Meeting 2022年5月2日
-
AI in Fundus Images in Japan
FujiRetina 2022年4月24日
-
AIを臨床研究に応用するための実践テクニック
第126回日本眼科科学学会総会 2022年4月16日
-
AIを用いた網膜症のスクリーニング
第126回日本眼科科学学会総会 2022年4月14日
-
判断根拠を示す人工知能ヒートマップの眼科専修医読影への効果
第125回日本眼科科学会総会 2022年4月14日
-
自治医大でのAI技術活用について
第2回日本眼科AI学会総会 2021年11月21日
-
深層学習を用いた超広角走査型レーザー検眼鏡写真の非灌流領域推定
第75回日本臨床眼科科学会 2021年10月29日
-
人口知能（AI）による糖尿病網膜症の診断
第64回日本糖尿病学会年次学術集会 2021年5月20日
-
Evaluation of keratoconus detection from elevation, topography and pachymetry raw data using machine learning
The Association for Research in Vision and Ophthalmology 2021 Annual Meeting 2021年5月4日