『您的瀏覽器不支援JavaScript功能,若網頁功能無法正常使用時,請開啟瀏覽器JavaScript狀態』

跳到主要內容區塊

工業技術研究院

:::

技術名稱: 眼底影像辨識引擎 V.1

技術簡介

本技術之進階眼底影像分析技術,包含左/右眼底影像判定、視杯/視盤偵測與直徑比例計算,並以國際常用之圖像資料庫DRIVE(N=40)、STARE(N=402)及國內廠商研發之眼底鏡設備拍攝企業員工眼底影像(N=496)進行效度驗證。在執行時間上,每張影像的左/右眼底影像判定<4秒,視杯/視盤偵測與直徑比例計算為1.5秒。準確率方面,眼底影像品質分析誤差< 2 % 。準確率均達世界水準,而所需的時間更短,可提供有用的眼底圖像資訊,協助醫師判斷病情。

Abstract

The advanced technologies of fundus image analysis include left / right fundus image classification, optic cup / disc detection and C/D ratio calculation. The test dataset including DRIVE (N = 40), STARE (N = 402) and ITRI (N = 496). The execution time of each algorithms is shown below, the left / right fundus image classifier is <4 seconds, the C/D ratio calculation time is 1.5 seconds. Those technologies can provide useful fundus image information to help physicians.

技術規格

系統開發環境規格 Windows平台:採用C語言開發、使用openCV函式庫

Technical Specification

Development Env. Spec. Windows Platform:C programming language、openCV libarry

技術特色

本技術開發整合左/右眼眼底影像偵測及眼底杯盤影像標記定位 (C/D Ratio)及比例估算相關核心技術,其中針對眼底影像進行視神經頭(ONH)、黃斑部(macular)、視盤(OD)區域、視杯(OC)區域及視血管分佈進行分析及偵測,整合了色彩分離法各頻道的資訊優化辨識率、並開發了自適應的閥值自動調整方法進行外觀特徵(appearance)萃取,再以霍夫(Hough)圓轉換方法為基礎開發區域標記演算法,最後以眼底各部位的空間對應關係(視神經盤與黃斑部位置關係和血管走向關係等)進行眼底影像的non-ONH、左/右眼影像判定。就偵測準確率及效度驗證,以視杯/盤區域偵測技術而言,其視盤偵測準確率達98%,而視杯偵測準確率達86%。分析效率評估上,於HD圖像(解析度1920*1080)中,左/右眼底圖像分辨平均約1.3秒/張、視杯/盤比例估算為0.28秒/張,其服務效率<3秒。

應用範圍

數位眼底鏡製造 智慧醫療系統商

接受技術者具備基礎建議(設備)

數位眼底鏡 醫療資訊系統(HIS,CPOE)

接受技術者具備基礎建議(專業)

影像分析 視光醫學

技術分類 H-智慧醫療

聯絡資訊

聯絡人:陳建任 智慧醫療與照護組

電話:03-5913416 或 Email:cjr@itri.org.tw

客服專線:+886-800-45-8899

傳真:03-5910212

[{"text":"企業網","weight":13.0},{"text":"材化所","weight":11.5},{"text":"機械所","weight":10.0},{"text":"綠能所","weight":9.4},{"text":"生醫所","weight":8.0},{"text":"半導體","weight":6.2},{"text":"南分院","weight":5.0},{"text":"太陽能","weight":5.0},{"text":"課程","weight":5.0},{"text":"遠紅外線","weight":5.0},{"text":"雷射","weight":4.0},{"text":"LED","weight":4.0},{"text":"LED可見光","weight":3.0},{"text":"5G","weight":3.0},{"text":"工研人","weight":3.0},{"text":"電光所","weight":3.0},{"text":"綠能與環境研究所","weight":3.0},{"text":"機械","weight":3.0},{"text":"資通所","weight":2.0},{"text":"面板","weight":2.0},{"text":"文字轉語音","weight":2.0},{"text":"實習","weight":2.0},{"text":"無人機","weight":2.0},{"text":"生醫","weight":2.0},{"text":"3D","weight":2.0},{"text":"v2x","weight":2.0},{"text":"員工","weight":2.0},{"text":"地圖","weight":2.0},{"text":"太陽光電","weight":2.0},{"text":"材料與化工研究所","weight":1.0}]