ログイン
言語:

WEKO3

  • トップ
  • ランキング
To
lat lon distance
To

Field does not validate



インデックスリンク

インデックスツリー

メールアドレスを入力してください。

WEKO

One fine body…

WEKO

One fine body…

アイテム

  1. 40 大学院工学研究科・工学部
  2. 40D 学位論文
  3. 博士論文 本文
  4. 2012年度

Automatic Extraction of Retinal Disease Area for Optical Coherence Tomography Image

http://hdl.handle.net/10076/13532
http://hdl.handle.net/10076/13532
54d6abdf-0ae9-47fb-87e0-3db036b1f32c
名前 / ファイル ライセンス アクション
2012D001.pdf 2012D001.pdf (2.6 MB)
Item type 学位論文 / Thesis or Dissertation(1)
公開日 2013-11-25
タイトル
タイトル Automatic Extraction of Retinal Disease Area for Optical Coherence Tomography Image
言語 en
言語
言語 eng
資源タイプ
資源タイプ識別子 http://purl.org/coar/resource_type/c_46ec
資源タイプ thesis
著者 Mohd, Fadzil Bin Abdul Kadir

× Mohd, Fadzil Bin Abdul Kadir

en Mohd, Fadzil Bin Abdul Kadir

Search repository
抄録
内容記述タイプ Abstract
内容記述 Optical Coherence Tomography (OCT) is an emerging technology that can provide high-resolution cross-sectional images of the retina for identifying, and quantitatively assessing of the retinal disease. On OCT images, retinal disease area appears in two conditions, either white or black color. Quantitative information of retina is needed to evaluate the degree of disease and the effectiveness of the treatment. In the previous researches, we already proposed some automatic measurement methods of the thickness between Inner Limiting Membrane (ILM) and Retinal Pigment Epithelium (RPE) from OCT images. One of the methods used was the combination of bottom-up image processing technique and a proposed contour active net model (One Directional Active Net (ODAN)), but resulted in similar problems namely inability to extract abnormal area in some cases and inability to extract the abnormal area in white condition. The main objective of this research is to develop a new generation computer aided diagnosis support system for OCT. The experimental materials used in this research, consists of two sets of 128 pieces of two-dimensional images of a retina. One set was obtained from a drusen patient and another set from a diabetic macular ederma (DME) patient. All of these images were digitalized to a pixel size of 6μm × 6μm, 16-bit gray scale with resolution 512 × 480 pixels. Out of 128 pieces of OCT images from each set, only 36 pieces of images which contained abnormal area were used as the final experimental materials. In this research, we used two conventional methods and proposed three new methods. At the end of the experiment, a comparison was made xiv between different methods of extracting the abnormal area from selected images. The results showed that a new proposed method which is border tracking procedure using regional statistics method provides the best extraction rate compared to others. We hope that this procedure may be added in the commercial OCT unit to evaluate the degree of retinal disease suffered and enable appropriate response for treatment.
言語 en
内容記述
内容記述タイプ Other
内容記述 三重大学大学院工学研究科博士後期課程システム工学専攻
内容記述
内容記述タイプ Other
内容記述 77p
書誌情報
発行日 2012-01-01
フォーマット
内容記述タイプ Other
内容記述 application/pdf
著者版フラグ
出版タイプ VoR
出版タイプResource http://purl.org/coar/version/c_970fb48d4fbd8a85
出版者
出版者 三重大学
修士論文指導教員
姓名 小林, 英雄
言語 ja
資源タイプ(三重大)
値 Doctoral Dissertation / 博士論文
戻る
0
views
See details
Views

Versions

Ver.1 2023-06-19 17:11:22.505822
Show All versions

Share

Mendeley Twitter Facebook Print Addthis

Cite as

エクスポート

OAI-PMH
  • OAI-PMH JPCOAR 2.0
  • OAI-PMH JPCOAR 1.0
  • OAI-PMH DublinCore
  • OAI-PMH DDI
Other Formats
  • JSON
  • BIBTEX

Confirm


Powered by WEKO3


Powered by WEKO3