(3.236.222.124) 您好!臺灣時間:2021/05/19 11:38
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:林淑芳
研究生(外文):Lin, Shu-Fang
論文名稱:適用於MV影像之即時性標記物追蹤系統
論文名稱(外文):Real-time Marker Tracking for MV Treatment Beam Imaging
指導教授:林維暘
指導教授(外文):Lin, Wei-Yang
口試委員:林維暘余松年黃春融
口試委員(外文):Lin, Wei-YangYu, Sung-NienHuang, Chun-Rong
口試日期:2011-07-21
學位類別:碩士
校院名稱:國立中正大學
系所名稱:資訊工程研究所
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:2011
畢業學年度:99
語文別:英文
論文頁數:40
中文關鍵詞:即時性標記物追蹤標記物偵測影像導引放射治療
外文關鍵詞:real-time trackingmarker trackingfiducial trackingimage quality localization accuracytracking accuracyProstate radiotherapyIGRT
相關次數:
  • 被引用被引用:0
  • 點閱點閱:246
  • 評分評分:
  • 下載下載:28
  • 收藏至我的研究室書目清單書目收藏:0
通常在放射治療中,為了取得即時腫瘤的位置,患者需事先於體內植入標示記物(Marker),以利放射治療師從影像中辨識腫瘤正確位置進行修正。
影像引導放射治療(Image-grided Radiation Therapy, IGRT) 為目前最先進的放射治療技術,
IGRT 基於三度空間技術的基礎上,於治療過程中藉由機器人手臂,取得即時的影像,進行定位,再經由放射治療師做最後確認。然而經由人工確認標示記物(Marker)
的位置,相當耗時。因此我們,發展出一個自動偵測及追蹤標示記物(Marker)的技術,只需要 MV(Megavoltage) 影像,不需額外的輻射 kV(kilovolt) 影像。
我們將標示記物偵測 (Marker Detection) 看成一種分類問題,針對每一張 MV 影像感興趣區域(ROI),先利用 PCA ( Principal Component Analysis)將資料降低至較低維度再利用LDA (Linear Discriminant Analysis) 把資料投影至二維座標平面進行分類取得標示記物(marker)的候選點,最後將每一候選點經由KPCA及LDA投影至訓練樣本的投影空間,根據與訓練樣本的歐式距離(Euclidean distance)決定最後預測位置,來達到辨識標記物(Marker)的效果。找到標示記物(Marker)的初始位置之後,利用每張frame在時間上的連續性,使用Mean Shift演算法來對接下的每一張frame作標示記物(Marker)的追蹤。
Image-Guided Radiation Therapy (IGRT) is the latest technology to help a therapist decide tumor position more precisely. It is based on real-time imaging to locate the target during a treatment. However, manual inspection of the images acquired during radiotherapy is labor-intensive and thus highly undesirable. In this thesis, we develop a learning-based algorithm to detect implanted markers in the first frame and then track them in the subsequent frames. In the proposed framework, we first select marker candidates using the Principal Component Analysis (PCA). Then, candidate points are projected onto a low-dimensional subspace constructed by Kernel Principal Component Analysis (KPCA) plus Linear Discriminant Analysis (LDA). We decide marker location by calculating the minimum distance between projected points and training data. In order to exploit the temporal correlation between consecutive frames, we use the mean shift algorithm to find the maximum similarity between the adjacent frames to track the marker. We have conducted a series of experiments on patient images and the results demonstrate the effectiveness of the proposed method.
1 Introduction 1
1.1 Background . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
2 Related Work 5
3 Methods 7
3.1 Contrast Enhancement for MV Imaging . . . . . . . . . . . . . . . . . 8
3.2 Marker Detection in the First Frame . . . . . . . . . . . . . . . . . . 13
3.3 Marker Tracking in the Subsequent Frames . . . . . . . . . . . . . . . 16
3.4 Summary of Marker Tracking system . . . . . . . . . . . . . . . . . . 19
4 Experimental Results 21
4.1 Data Acquisition and Experimental Setup . . . . . . . . . . . . . . . 21
4.2 Contrast Enhancement . . . . . . . . . . . . . . . . . . . . . . . . . . 23
4.3 Marker Detection . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26
4.4 Internal Marker Tracking During Treatment Beam Delivery . . . . . . 32
4.5 Performance of Proposed Method . . . . . . . . . . . . . . . . . . . . 36
5 Conclusion 37
[1] J. Nederveen, A. Lagendijk and P. Hofman. Detection of ducial gold mark-
ers for automatic on-line megavoltage position veri cation using a marker ex-
traction kernel (MEK). International Journal of Radiation Oncology Biology
Physics, 47(5):1435{1442, 2000.
[2] AJ Nederveen, JJW Lagendijk, and P. Hofman. Feasibility of automatic marker
detection with an a-Si
at-panel imager. Physics in medicine and biology,
46(4):1219{1230, 2001.
[3] Weihua Mao, Rodney Wiersma, and Lei Xing. Fast internal marker tracking al-
gorithm for onboard MV and kV imaging systems. Medical physics, 35(5):1942{
1949, 2008.
[4] N. Lee L. Wiersma R. Xing L. Mao, W. Riaz. A ducial detection algorithm
for real-time image guided IMRT based on simultaneous MV and kV imaging.
Medical physics, 35(8):3554{3564, 2008.
[5] P. J. Keall, A. D. Todor, S. S. Vedam, C. L. Bartee, J. V. Siebers, V. R. Kini,
and R. Mohan. On the use of EPID-based implanted marker tracking for 4D
radiotherapy. Medical physics, 31(12):3492{3499, 2004.
[6] R. D. Wiersma, W. Mao, and L. Xing. Combined kV and MV imaging for real-
time tracking of implanted ducial markers. Medical physics, 35(4):1191{1198,
2008.
[7] Sang-June Park, Dan Ionascu, Fred Hacker, Harvey Mamon, and Ross Berbeco.
Automatic marker detection and 3D position reconstruction using cine EPID
images for SBRT veri cation. Medical physics, 36(10):4536{4546, 2009.
[8] Patrick Bonneau, Alexandra Branzan Albu, and Michelle Hilts.
[9] Dorin Comaniciu and Peter Meer. Mean shift: A robust approach toward
feature space analysis. IEEE Transactions on Pattern Analysis and Machine
Intelligence, 24(5):603{619, 2002.
[10] D.L. Swets and J.J. Weng. Using iscriminant eigenfeatures for image retrieval.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(8):831{
836, 1996.
[11] P.N. Belhumeur, J.P. Hespanha, and D.J. Kriegman. Eigenfaces vs. Fisherfaces:
Recognition using class speci c linear projection. IEEE Transactions on Pattern
Analysis and Machine Intelligence, 19(7):711{720, 1997.
[12] Christopher M. Bishop. Pattern recognition and machine learning. Springer
New York, 2006.
[13] T. Kailath. The divergence and bhattacharyya distance measures in signal se-
lection. Communication Technology, IEEE Transactions on, 15(1):52{60, 1967.

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top