臺灣博碩士論文加值系統

本研究是一個基於 MRI 脊椎圖，接續 SMRIVS 方法利用一系列影像處理方法將椎間盤、硬膜囊及其他組織去除掉，剩餘一組完整脊椎的系統。核磁共振造影(Magnetic Resonance Imaging)技術是利用人體內水分子中的氫原子受到外界磁場的變化所產生訊號,再透過電腦計算所獲得影像的一種造影技術。因為人體的組織都含有不同比例的水份,因此在 MRI 影像中,不同的人體組織就有不同的亮度。常用的醫療影像技術還有斷層掃描 CT，但 CT 是利用 X 光的穿透來成像，對孕婦可能會造成輻射傷害胎兒等問題，坐斷層掃描的次數也有所限制。相較起來 MRI 較為安全且被廣為運用。

近年來隨著科技的發達，使用電腦的時間與日增長。長期坐在電腦前姿勢不端正的結果會造成對脊椎的傷害諸如脊椎側彎、椎間盤突出、坐骨神經痛.....等疾病。一個骨科醫師一天可能檢查了上百個脊椎 MRI 圖，在脊椎 MRI 圖片上有許多的疾病的特徵,細節隱藏其中，難免會因為精神疲乏而造成錯誤的判斷，引起醫療糾紛。

我們提出一個自動的脊椎切割方法，透過一系列影像處理的方法，把除了脊椎骨之外的組織例如：椎間盤、硬膜囊...等從脊椎 MRI 圖中分離出去，顯示一組獨立的脊椎骨圖。這樣可以讓醫生診斷一些基本的症狀，減輕醫生的負擔進而可以增進醫病關係。

本文所提出的方法可以分為三個階段。第一階段為前處理階段，讓原始圖片的對比度增加，凸顯出我們感興趣的區域，並且對每個脊椎骨獨立處理。第二部利用脊椎骨與其他組織中會有顏色落差的特性把椎間盤及一些相鄰的組織去掉。硬膜囊因為充滿了腦脊髓液在 MRI 影像下呈現亮白色，第三步則利用硬膜囊跟脊椎骨間的顏色差異把和脊椎骨相鄰的硬膜囊除去。

透過此三個步驟，可以成功把脊椎股從 MRI 影像截取出來，平均切割相似度為 83.21%。

This paper is based on SMRIVS method to refine the results of SMRIVS method by eliminating thecal sac, intervertebral disc and other tissues on a MRI image. The proposed method is divided into three stages. The first stage is preprocessing stage, which adjusts the intensities of the results of SMRIVS method for further use. The purpose of the second stage is to eliminate intervertebral disc and some adjacency darker tissues. Because the intensities of those parts are darker than those of the vertebra bone, local thresholding and monograph operators to eliminate those parts. After that, the third stage is used to thecal sac. Thecal sac parts have high intensity in MRI image because it’s full of cerebrospinal fluid. Therefore, the intensities of the results of the second stages are enhanced using gamma equalization. The thecal sac can be eliminated by perform otsu’s method on the enhanced images. Finally, the spinal set from the MRI image can be obtained successfully. The average segmentation performance of the segmentation results in 36 spinal MRI images is 83.21%.

Abstract (in Chinese) i
Abstract (in English) ii
List of Contents iii
List of Table iv
List of Figures v
Chapter 1. Introduction 1
Chapter 2. Related Works 4
2.1. Automatic Vertebrae Segmentation of Spinal MR Images 4
2.2. Automated Vertebra Detection and Segmentation from the Whole Spine MR images 5
2.3. Dilation, Erosion, Opening, Closing, Hole filling 6
2.4. Genetic Algorithm 6
Chatper3. The Proposed Method 9
3.1. Preprocessing Stage 9
3.1.1: Modified Histogram equalization 13
3.1.2: Image enhancement method 15
3.2. Segmentation of intervertebral discs and tissues stage 15
3.2.1: Local Thresholding 16
3.2.1.1: Thresholding step 16
3.2.1.2: Merging Step 20
3.2.2: Modified Image enhancement 22
3.2.3: Double local threshold 24
3.2.4: Opening and closing 28
3.3. Segmentation of thecal sac stage 30
3.3.1: Image contrast enhancement and thresholding 31
3.3.2: Checking method 34
3.3.3: Genetic algorithm for Detecting optimal Parameter 36
Chapter 4. Experiment Results and Disscusions 41
4.1. Experiment result 41
4.2. Discussion 44
Chapter 5. Conclusions and Future Works 46
References 47

[1] J. Schmid, J. Kim, and N. Magnenat-Thalmann, “Robust Statistical Shape Models for MRI Bone Segmentation in Presence of Small Field of View,” Medical Image Analysis, vol. 15, no. 1, pp. 155–168, 2011.
[2] S. Booth and D. A. Clausi, “Image Segmentation using MRI Vertebral Cross-Sections,” Proc. Can. Conf. Electrical and Computer Engineering, vol. 2, pp.1303 -1307, 2001.
[3] J. Carballido-Gamio, S. Belongie, and S. Majumdar, “Normalized Cuts in 3-D for Spinal MRI Segmentation,” IEEE Transactions on Medical Imaging, vol. 23, no. 1, pp. 36–44, 2004.
[4] Z. Peng, J. Zhong, W. Wee, and J. Lee, “Automated Vertebra Detection and Segmentation from the Whole Spine MR Images,” Proceedings of IEEE EMBS, vol. 3, 2005.
[5] Wikipedia The Free Encyclopedia, “X-ray,” (http://en.wikipedia.org/wiki/Canny_edge_detector).
[6] Y.K. Chan, Ya-Fang Chuang, “Automatic Vertebrae Segmentation of Spinal MRI Images,”
[7] Wikipedia The Free Encyclopedia, “otsu’s method,”(http://en.wikipedia.org/wiki/Otsu''s_method).
[8] Wikipedia The Free Encyclopedia, “Spinal disc herniation,”(http://en.wikipedia.org/wiki/Spinal_disc_herniation).
[9 ] Wikipedia The Free Encyclopedia,“Osteophyte,”(http://en.wikipedia.org/wiki/Osteophyte).
[10] Wikipedia The Free Encyclopedia,“Euclidean_distance,”(http://en.wikipedia.org/wiki/Euclidean_distance ).