臺灣博碩士論文加值系統

從不同的醫療儀器所產生的影像中，如何辨識目標物件或區域，對於醫學影像分析而言，是一個重要的問題。於先前的研究，其主要目標是專注在影像中的單一物件之描繪，例如：心臟、肺部或肝臟等器官。近期研究則以偵測或定位多個組織結構，且應用於三維電腦斷層掃描影像。但還有少數的研究，並非只偵測單一或多個物件或器官，而是將擷取和辨識技術整合於同一架構。此架構所採用的技術為納入物件周圍的資訊，且已被證實能夠提升物件辨識或偵測的效能。
於本論文，我們亦考慮物件周圍的資訊，應用於肺癌電腦輔助診斷系統中的兩項主要元素：腫瘤良惡性分類和腫瘤邊緣擷取。並且嘗試回答下列問題：第一：肺部電腦斷層掃描影像中的哪些資訊，可有效地被使用於肺癌風險評估？我們採用腫瘤與其周圍資訊，結果顯示能夠有效提升預測肺腫瘤的惡性機率。第二：如何辨識肺部電腦斷層掃描影像內的解剖構造？研究結果顯示，結合統計式區域合併與條件式隨機模型，可以透過圖形劃分最佳化，得到多項特定的肺部組織結構。

The task of recognizing every object/region in images acquired with different medical imaging modalities is a key problem in medical image analysis (also called image understanding). Most of the earlier object/organ recognition algorithm assigns a single label to an image, e.g. an image of a heart, a lung or a liver. Some go further in detecting and localizing multiple anatomical structures within three-dimensional computed tomography (CT) scans. Instead of applying to a single or multiple object/organ detection, a few concurrent approaches combine segmentation and recognition into one coherent framework. Incorporating contextual information into coherent framework has proven to enhance performance of higher level tasks such as object recognition or detection.
In this thesis, we adopt the concept of image understanding to investigate two key components of computer-aided diagnosis (CAD) system for lung cancer, namely nodule classification and nodule segmentation. Specifically, we ask two questions. First: What information from pulmonary CT images can be helpful as context for lung cancer risk prediction? We show that recognition of anatomic patterns of pulmonary nodules can be potentially useful and robust algorithm in predicting the probability of the malignancy of pulmonary nodules. Second: How can recognition of anatomic structures in pulmonary CT images be performed? We show that given an image, semantically meaningful regions each labeled with a specific lung tissue class can be extracted by unifying the techniques of statistical region merging and conditional random field (CRF) with graph cut optimization.

Contents
Acknowledgements (Chinese) i
Abstract (Chinese) ii
Abstract iii
Contents v
List of Figures vii
List of Tables ix
Chapter 1 1
Introduction 1
1.1 Objective of this work 1
1.2 Problem Specification 3
1.3 Why total understanding in pulmonary CT images is hard? 4
1.4 Overview of the Proposed Approach 5
1.5 Outline 6
Chapter 2 9
Computer Aided Diagnosis of Benign and Malignant Lung Nodules in Computed Tomography Using Integrated Spatially and Extended Anatomic Structures 9
2.1 Introduction 9
2.2 Materials and Methods 11
2.3 Results 17
2.4 Discussion 22
2.5 Reference 27
Chapter 3 33
Anatomy packing with hierarchical segments: An algorithm for segmentation of pulmonary nodules in CT images 33
3.1 Introduction 33
3.2 Related Work 37
3.3 Proposed Method 41
3.3.1 Hierarchical Segments: Tree Structure 43
3.3.2 APHS for Pulmonary Nodule Segmentation 46
3.3.3 Image Data and Evaluation Methods 49
3.4 Results 53
3.5 Discussion 60
3.6 Conclusions 62
3.7 Reference 63
Chapter 4 73
Conclusions 73
4.1 Summary and Contributions 73
4.2 Future Work 74
Reference 77
Appendix A 81
Related Publications 81

American Lung Association. (2012). Lung Cancer Fact Sheet, Washington, DC, USA [Online]. Available: http://seer.cancer.gov/statfacts/html/lungb.html
Balabanian JP, Viola I, and Groller ME., Interactive illustrative visualization of hierarchical volume data. In Proceedings of Graphics Interface 2010, pages 137–144, 2010.
Criminisi, A., Shotton, J., 2013(a). Decision Forests for Computer Vision and Medical Image Analysis. Advances in Computer Vision and Pattern Recognition. Springer.
Criminisi A, Robertson D, Konukoglu E, Shotton J, Pathak S, White S, Siddiqui K. Regression forests for efficient anatomy detection and localization in computed tomography scans. Med Image Anal. 2013(b) Dec;17(8):1293-303.
Crouzet, S.M., and Serre, T., “What are the Visual Features Underlying Rapid Object Recognition?,” Frontiers in Psychology 2, (2011).
Dehmeshki, J., Amin, H., Valdivieso, M., Ye, X.: Segmentation of pulmonary nodules in thoracic CT scans: a region growing approach. IEEE Trans Med Imaging. 27, 467–80 (2008)
El-Baz, A., Nitzken, M., Khalifa, F., Elnakib, A., Gimel’farb, G., Falk, R., Abo El-Ghar, M.: 3D Shape Analysis for Early Diagnosis of Malignant Lung Nodules. In: Sz’ekely, G., Hahn, H.K. (eds.) IPMI 2011, LNCS, vol. 6801, pp. 772–783. Springer, Heidelberg (2011)
El-Baz A, Beache GM, Gimel''farb G, et al. Computer-aided diagnosis systems for lung cancer: challenges and methodologies. Int J Biomed Imaging 2013;2013:942353.
Gavrielides MA, Kinnard LM, Myers KJ, Petrick N. Noncalcified lung nodules: volumetric assessment with thoracic CT. Radiology. 2009 Apr;251(1):26-37.
Hastie T, Tibshirani R, Friedman J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. New York, NY : Springer, 2009.
Kim, K.G., Goo, J.M., Kim, J.H., Lee, H.J., Min, B.G., Bae, K.T., Im, J.G.: Computer-aided Diagnosis of Localized Ground-Glass Opacity in the Lung at CT: Initial Experience. Radiology 237, 657–661 (2005)
Klein A, Hirsch J., Mindboggle: a scatterbrained approach to automate brain labeling. Neuroimage. 2005 Jan 15;24(2):261-80.
McWilliams A, Tammemagi MC, Mayo JR, Roberts H, Liu G, Soghrati K, Yasufuku K, Martel S, Laberge F, Gingras M, Atkar-Khattra S, Berg CD, Evans K, Finley R, Yee J, English J, Nasute P, Goffin J, Puksa S, Stewart L, Tsai S, Johnston MR, Manos D, Nicholas G, Goss GD, Seely JM, Amjadi K, Tremblay A, Burrowes P, MacEachern P, Bhatia R, Tsao MS, Lam S. Probability of cancer in pulmonary nodules detected on first screening CT. N Engl J Med. 2013 Sep 5;369(10):910-9. doi: 10.1056/NEJMoa1214726.
Naidich DP, Bankier AA, MacMahon H, et al. Recommendations for the management of subsolid pulmonary nodules detected at CT: a statement from the Fleischner Society. Radiology 2013;266(1):304–317.
Park CM, Goo JM, Lee HJ, Lee CH, Chun EJ, Im JG. Nodular ground-glass opacity at thin-section CT: histologic correlation and evaluation of change at follow-up. Radiographics. 2007 Mar-Apr;27(2):391-408.
Pathak S, Criminisi A, White S, Munasinghe I, Sparks B, Robertson D, and Siddiqui K, “Automatic semantic annotation and validation of anatomy in DICOM CT images,” in SPIE Medical Imaging, 7967, 2011.
Suzuki K, Li F, Sone S, Doi K. Computer-aided diagnostic scheme for distinction between benign and malignant nodules in thoracic low-dose CT by use of massive training artificial neural network. IEEE Trans Med Imaging 2005;24(9):1138-1150.
Tsou CH, Lor KL, Chang YC, and Chen CM., Region-based graph cut using hierarchical structure with application to ground-glass opacity pulmonary nodules segmentation. Proc. SPIE 8669, Medical Imaging 2013: Image Processing, 866906 (March 13, 2013).
Webb WR, Muller NL, Naidich DP. High Resolution CT of the Lung. Second edition, Lippincott-Raven Publishers, Philadelphia, 1996.
Wu, D., Lu, L., Bi, J., Shinagawa, Y., Boyer, K., Krishnan, A., Salganicoff, M.: Stratified learning of local anatomical context for lung nodules in CT images. In: CVPR, pp. 2791–2798 (2010)
Yanagawa M, Tanaka Y, Leung AN, Morii E, Kusumoto M, Watanabe S, Watanabe H, Inoue M, Okumura M, Gyobu T, Ueda K, Honda O, Sumikawa H, Johkoh T, Tomiyama N. Prognostic Importance of Volumetric Measurements in Stage I Lung Adenocarcinoma. Radiology. 2014 Apr 6:131903.
Zheng, Y., Kambhamettu, C., Bauer, T., Steiner, K.: Estimation of Ground-Glass Opacity Measurement in CT Lung Images. In: Metaxas, D. et al. (eds.) MICCAI 2008, Part II, LNCS, vol. 5242, pp. 238–245. Springer, Heidelberg (2008)