跳到主要內容

臺灣博碩士論文加值系統

(3.237.38.244) 您好!臺灣時間:2021/07/26 10:52
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:王豫勇
研究生(外文):Wang, Yuyung
論文名稱:牙齒X光片影像牙齦病灶區域偵測之研究
論文名稱(外文):A Study Of Gums’ Lesion Detection Using Dental Radiographs
指導教授:林芬蘭林芬蘭引用關係
指導教授(外文):Lin, Phenlan
口試委員:黃博惠林春宏林芬蘭
口試委員(外文):Huang, PowheiLin, ChuenhorngLin, Phenlan
口試日期:2012-07-25
學位類別:碩士
校院名稱:靜宜大學
系所名稱:資訊工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2012
畢業學年度:100
語文別:中文
論文頁數:46
中文關鍵詞:牙齦炎區域成長
外文關鍵詞:SVMRegion-growingOtsu
相關次數:
  • 被引用被引用:2
  • 點閱點閱:169
  • 評分評分:
  • 下載下載:9
  • 收藏至我的研究室書目清單書目收藏:0
牙齦炎與牙周病由牙齦內部組織是否有被破壞去判斷,但內部組織無法以肉眼做診斷,只能依靠X光片影輔助診斷。現今醫療資源越來越發達,由於各醫院每天所產生的X光片影像數量非常的可觀,龐大的X光片影像就需要電腦輔助來幫助醫生診斷,因此本論文提出牙齒X光片影像牙齦病灶區域自動偵測之研究。
由於牙齒會影響牙齦區域分層的結果,本論文所提出的方法,首先使用牙齒切割與牙齦線偵測方法篩除影像中非牙齦之區域,再對牙齦區域之封閉區塊分別以(一) Otsu 門檻值方式與(二) Support Vector Machine (SVM)方式將其分類為嚴重發炎、發炎、疑似發炎與正常4種類型區域,最後再根據嚴重性之優先順序以region-growing方法對區塊做區域成長,將同類型區塊連結成同一層級。
本論文共測試6張X光片影像,實驗結果顯示本論文所提出的兩個方法之分層結果與人眼仔細判定的結果比較,大部分都吻合。

Gingivitis and periodontal disease can be diagnosed based on the degree of alveolar- bone loss, which usually cannot be spotted without dentists examining the dental radiographs. However, poor-quality of radiographs due to improper machine setup or uneven illumination when taken increases the difficulty of lesion detection. This study of automatic dental lesion detection using dental radiographs is in hope that the research results can provide dentists with more complete information so that diagnoses can be speed up and better treatments and prognoses can be planned for patients.
Periodontal images contain both teeth parts and gums part, in which the intensity level of both healthy teeth and gums is sometimes quite similar. For reducing the ambiguity of confusing healthy tooth tissues with healthy gum tissues, we first remove teeth parts from the image by a proposed teeth-part removing method that uses a SVM classifier with both position and intensity as the classification characteristics. We then use two proposed classification method: Otsu thresholding and SVM classification to segment the blocks of gums part into non-overlapping regions of four types: serious lesion (SR), lesion region (LR), possible lesion region (PL), and normal region (NR). Finally, we connect blocks of the same type using region growing to form connected regions.
We test 6 periodontal X-ray images in this study. The experimental results show that our segmentation results using both proposed methods are quite conform to the segmentation by human visual perception.
摘 要 i
ABSTRACT ii
誌 謝 iii
目 錄 iv
表 目 錄 v
圖 目 錄 vi
第一章、緒論 1
1.1 研究動機與目的 1
1.2 研究背景 2
第二章、 相關文獻 5
2-1 相關論文引用 5
2-2 影像處理方法 7
第三章、不同階層之牙齦發炎分層 15
3.1牙齦線擷取 15
3.1.1背景影像消除 16
3.1.2牙齦點的擷取 17
3.2篩除牙齒 21
3.2.1區塊的選取 21
3.2.2區塊SVM分類 23
3.3牙齦區域分層 25
3.3.1以Otsu 方式對牙齦區域階層上分層 25
3.3.2以SVM 方式特徵做分層 31
第四章、實驗結果與分析 39
4.1 以SVM分牙齒區域 39
4.2 以Otsu分層牙齦區域結果與分析 40
4.3以SVM分層牙齦區域結果與分析 41
第五章、結論與未來方向 45
參考文獻 46
http://www.bjkq.cn/kouqiang/39648.htmlDr.
http://www.zhonghuakangwang.com/yayinyan.htm
http://www.ads.org.tw/front/bin/ptdetail.phtml?Part=200816&Category=0
Tony Information Technology Corporation, http://www.dr-tony.com.tw/
S. Li, T. Fevens, A. Krzyżak, C. Jin,“Semi-automatic computer aided lesion detection in dental X-rays using variational level set,” Pattern Recognition, 2007, pp.2861-2873.
S. Li, T. Fevens, A. Krzyżak, “An automatic variational segmentation for dental X-ray analysis in clinical environment,” Comput. Med.
Imaging Graphics, 30 (2006), pp. 65–74.
N. Otsu, “A threshold selection method from gray-level histogram,” IEEE Transactions on Systems, Man, and Cybernetics, pp. 62-66, 1979.
J.F Canny, “A Computational Approach to Edge Detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 8, pp. 679-698, 1986.
Adams, R., Bischof, L., “Seed region growing,” IEEE Transactions on Pattern Analysis and Machine Intelligence (16:6 ),1994, pp.641-647.
S. Tong, D. Koller, “Support Vector Machine Active Learning with Applications to Text Classification,” The Journal of Machine Learning Research archive, Vol. 2, pp.45-66,2002.
Sergios Theodoridis,Konstantinos Koutroumbas 著, Pattern Recognition, pp. 13 -17.
蔡雅珊著,牙齒X光片影像牙齦病灶區域偵測之研究 靜宜大學碩士論文, 2011.
Gonzalez,Wood著,謬紹綱譯,數位影像處理 3e, pp. 707-711.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top