Segmentation of 3D Tubular Tree Structures in Medical Images ...

More documents

Recommendations

Info

102 Chapter 6. Coronary Artery Tree Extraction what forms a kind of coned region (with an opening angle specified by ρ) pointing away from the centerline where the method searches for continuations; potential connections with too large costs C > c max are discarded. The final reconstructed trees (after removal of the non-coronary artery trees; see next paragraph) is shown in Fig. 6.1(e). Coronary artery tree identification: The method as described above also extracts the centerlines of other tubular objects (see Fig. 6.1). Thus, not just the coronary arteries are identified, but also other structures such as blood vessels in the lung and chest area, the aorta and also some of the bones and an identification of the coronary artery trees is necessary. The lung tissue is identified and removed based on thresholding (I(x) < −700 HU) and morphological closing using a spherical structuring element with a radius of 10 voxels; see Fig. 6.1(c) for the TDF response after removal of the lung tissue. Other tree structures not belonging to the coronary artery trees are typically isolated and relatively small. Thus, the coronary artery trees can be identified as the two largest connected components (regarding their centerline length). An example of the identified coronary artery trees is shown in Fig. 6.1(e). Parameters: Following set of parameters is used to process the datasets. F max = 100, t high = 0.5, t low = 0.1, and l min = 10 voxels for the extraction of tubular structures with µ = 5 and 500 iterations for the GVF computation [168] and ρ = 0.7, d max = 200 HU, and c max = 20 for the grouping and linkage. 6.3 Evaluation and Results Our approach was evaluated on 32 coronary CTA datasets from the “Rotterdam Coronary Artery Algorithm Evaluation Framework” (http://coronary.bigr.nl), whose goal is the quantitative evaluation and comparison of methods for the coronary artery centerline extraction based on a set of well defined performance measures. The datasets are split in two groups of 8 training datasets with provided reference where the parameters have been adapted and 24 testing datasets with undisclosed reference centerlines. For each of the datasets, reference centerlines of four vessels are available that were obtained based on manual annotation and reference points that unambiguously identify the corresponding vessels. In Fig. 6.3 the coronary artery trees and provided reference centerlines are shown. Based on these provided reference points the centerlines of the associated arteries were selected from the coronary artery trees – which are extracted completely with our approach
6.3. Evaluation and Results 103 – by following the centerline into both directions, at junctions of multiple vessels choosing the centerline with the smaller branching angle. (a) Extracted coronary artery trees. (b) Reference centerlines. Figure 6.3: Extracted coronary artery trees and provided reference centerlines. For visualizations just the image regions in proximity to the coronary artery trees are shown. At the proximal ends of the coronary arteries – the transition to the aorta – the centerlines extracted with our approach are sometimes slightly shorter than the reference centerlines (see Fig. 6.4). This is due to properties of the tube detection filter as these regions are not really tubular any more. To account for this issue (see the ”overlap until first error” measure in Section 6.3.1), the proximal ends of the centerlines are extrapolated along a straight line, solving this issue in most datasets, but not all of them. In the next two sections, we present quantitative results achieved with our method on the 24 testing datasets. For comparison, results achieved with other methods are summarized and discussed as well. The quantative measures were obtained by the “Rotterdam Coronary Artery Algorithm Evaluation Framework” and are available online at http://coronary.bigr.nl. 6.3.1 Results of Proposed Method The performance measures are grouped into overlap measures and an accuracy measure. For the exact description of the performance evaluation and the used measures we refer to the paper of Shaap et al. [124]. The results are summarized in Table. 6.1. Overlap: The overlap measures are used to assess the ability of the approach to identify the structures of interest. Measures are the overlap OV , the overlap until first error
Page 1:
Graz University of Technology Insti
Page 5 and 6:
Abstract The segmentation of tubula
Page 7 and 8:
Kurzfassung Die Segmentierung tubul
Page 9:
Acknowledgements I am deeply gratef
Page 13 and 14:
Contents 1 Introduction 1 1.0.1 Req
Page 15:
CONTENTS xv 8 Conclusion and Outloo
Page 18 and 19:
xviii LIST OF FIGURES 4.2 Shape pri
Page 21:
List of Tables 3.1 Average centerli
Page 24 and 25:
2 Chapter 1. Introduction (a) Porta
Page 26 and 27:
4 Chapter 1. Introduction (a) Volum
Page 28 and 29:
6 Chapter 1. Introduction (a) Inacc
Page 30 and 31:
8 Chapter 1. Introduction features
Page 32 and 33:
10 Chapter 1. Introduction 1.1.2 Di
Page 34 and 35:
12 Chapter 1. Introduction Input vo
Page 36 and 37:
14 Chapter 1. Introduction part: Me
Page 38 and 39:
16 Chapter 1. Introduction in the l
Page 40 and 41:
18 Chapter 2. Extraction of Tubular
Page 42 and 43:
Page 44 and 45:
Page 46 and 47:
Page 48 and 49:
Page 50 and 51:
Page 52 and 53:
Page 54 and 55:
Page 56 and 57:
Page 58 and 59:
Page 60 and 61:
Page 62 and 63:
Page 64 and 65:
Page 66 and 67:
Page 68 and 69:
Page 70 and 71:
48 Chapter 3. Grouping and Linkage
Page 72 and 73:
50 Chapter 3. Grouping and Linkage
Page 74 and 75: 52 Chapter 3. Grouping and Linkage
Page 88 and 89: 66 Chapter 4. Tube Segmentation Onl
Page 90 and 91: 68 Chapter 4. Tube Segmentation obt
Page 92 and 93: 70 Chapter 4. Tube Segmentation ass
Page 94 and 95: 72 Chapter 4. Tube Segmentation (a)
Page 96 and 97: 74 Chapter 4. Tube Segmentation Tab
Page 99 and 100: Chapter 5 Liver Vascular Tree Segme
Page 101 and 102: 5.2. Method 79 (a) MIP of the datas
Page 103 and 104: 5.3. Evaluation and Results 81 5.3.
Page 105 and 106: 5.3. Evaluation and Results 83 cent
Page 107 and 108: 5.3. Evaluation and Results 85 (a)
Page 115 and 116: 5.4. Discussion 93 results. Selle
Page 117: 5.5. Conclusion 95 a prior to const
Page 120 and 121: 98 Chapter 6. Coronary Artery Tree
Page 131 and 132: Chapter 7 Airway Tree Segmentation
Page 133 and 134: 7.2. Methods 111 shown in Fig. 7.1.
Page 135 and 136: 7.2. Methods 113 Additionally, the
Page 137 and 138: 7.3. Evaluation and Results 115 Gro
Page 139 and 140: 7.3. Evaluation and Results 117 Tab
Page 141 and 142: 7.4. Discussion 119 Figure 7.5: “
Page 143 and 144: 7.5. Conclusion 121 Comparison to o
Page 145 and 146: 7.5. Conclusion 123 Figure 7.6: Exa
Page 147 and 148: Chapter 8 Conclusion and Outlook Co
Page 149 and 150: 8.1. Conclusion 127 arteries - info
Page 151: 8.2. Directions for Future Work 129
Page 154 and 155: 132 Chapter A. List of Publications
Page 157 and 158: BIBLIOGRAPHY 135 Bibliography [1] A
Page 159 and 160: BIBLIOGRAPHY 137 [21] Choyke, P., Y
Page 161 and 162: BIBLIOGRAPHY 139 [41] Florin, C., P
Page 163 and 164: BIBLIOGRAPHY 141 [63] Kitslaar, P.
Page 165 and 166: BIBLIOGRAPHY 143 [85] Lindeberg, T.
Page 167 and 168: BIBLIOGRAPHY 145 [108] O’Donnell,
Page 169 and 170: BIBLIOGRAPHY 147 [129] Schmugge, S.
Page 171 and 172: BIBLIOGRAPHY 149 [150] van Bemmel,
Page 173: BIBLIOGRAPHY 151 [171] Yi, J. and R
show all

Segmentation of 3D Tubular Tree Structures in Medical Images ...

Create successful ePaper yourself

Delete template?

Save as template?