Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/9182
標題: 利用螞蟻群落最佳化之貝氏網路進行非侵入之肝硬化評估
LiFiBay: Noninvasive Evaluation of Liver Fibrosis by Using Bayesian Networks with Ant Colony Optimization
作者: 張傑帆
Chang, Jie-Fan
關鍵字: 肝硬化
Liver fibrosis
貝氏網路
卡方分佈
螞蟻群落最佳化
Ant colony optimization
ACO
Bayesian network
BN
Bayesian belief network
BBN
Chi-square
出版社: 電機工程學系所
引用: [1] G. Fattovich, G. Giustina, F. Degos, F. Tremolada, G. Diodati, P. Almasio, F. Nevens, A. Solinas, D. Mura, J. Brouwer et al., “Morbidity and mortality in compensated cirrhosis type c: a retrospective follow-up study of 384 patients,” Gastroenterology, vol. 112, no. 2, pp. 463–472, 1997. [2] J. Cadranel, P. Rufat, and F. Degos, “Practices of liver biopsy in france: results of a prospective nationwide survey,” Hepatology, vol. 32, no. 3, pp. 477–481, 2000. [3] A. Colli, M. Fraquelli, M. Andreoletti, B. Marino, E. Zuccoli, and D. Conte, “Severe liver fibrosis or cirrhosis: Accuracy of us for detectionanalysis of 300 cases1,” Radiology, vol. 227, no. 1, pp. 89–94, 2003. [4] L. Sandrin, B. Fourquet, J. Hasquenoph, S. Yon, C. Fournier, F. Mal, C. Christidis, M. Ziol, B. Poulet, F. Kazemi et al., “Transient elastography: a new noninvasive method for assessment of hepatic fibrosis,” Ultrasound in medicine & biology, vol. 29, no. 12, pp. 1705–1713, 2003. [5] A. Loaeza-del Castillo, F. Paz-Pineda, E. Oviedo-Cardenas, F. Sanchez-Avila, and F. Vargas-Vorackova, “Ast to platelet ratio index (apri) for the noninvasive evaluation of liver fibrosis,” Ann Hepatol, vol. 7, no. 4, pp. 350–7, 2008. [6] X. Forns, S. Ampurdan`es, J. Llovet, J. Aponte, L. Quint’o, E. Mart’ınez-Bauer, M. Bruguera, J. S’anchez-Tapias, and J. Rod’es, “Identification of chronic hepatitis c patients without hepatic fibrosis by a simple predictive model,” Hepatology, vol. 36, no. 4, pp. 986–992, 2002. [7] S. Arain, Q. Jamal, and A. Omair, “” liverscore” is predictive of both liver fibrosis and activity in chronic hepatitis c,” World Journal of Gastroenterology: WJG, vol. 17, no. 41, p. 4607, 2011. [8] A. Vallet-Pichard, V. Mallet, B. Nalpas, V. Verkarre, A. Nalpas, V. Dhalluin- Venier, H. Fontaine, and S. Pol, “Fib-4: An inexpensive and accurate marker of fibrosis in hcv infection. comparison with liver biopsy and fibrotest,” Hepatology, vol. 46, no. 1, pp. 32–36, 2007. [9] L. Bo and G. Xiaoguang, “Bayesian networks for intelligent decision of airborne weapon system,” in Innovative Computing, Information and Control, 2006. ICICIC''06. First International Conference on, vol. 3. IEEE, 2006, pp. 390– 393. [10] S. Mirarab, A. Hassouna, and L. Tahvildari, “Using bayesian belief networks to predict change propagation in software systems,” in Program Comprehension, 2007. ICPC''07. 15th IEEE International Conference on. IEEE, 2007, pp. 177–188. [11] R. Sterritt, A. Marshall, C. Shapcott, and S. McClean, “Exploring dynamic bayesian belief networks for intelligent fault management systems,” in Systems, Man, and Cybernetics, 2000 IEEE International Conference on, vol. 5. IEEE, 2000, pp. 3646–3652. [12] C. Arsene and P. Lisboa, “Bayesian neural network applied in medical survival analysis of primary biliary cirrhosis,” in Computer Modelling and Simulation (UKSim), 2012 UKSim 14th International Conference on. IEEE, 2012, pp. 81–85. [13] D. Nikovski, “Constructing bayesian networks for medical diagnosis from incomplete and partially correct statistics,” Knowledge and Data Engineering, IEEE Transactions on, vol. 12, no. 4, pp. 509–516, 2000. [14] D. Chickering, D. Geiger, D. Heckerman et al., “Learning bayesian networks is np-hard,” Citeseer, Tech. Rep., 1994. [15] P. Pinto, A. Nagele, M. Dejori, T. Runkler, and J. Sousa, “Using a local discovery ant algorithm for bayesian network structure learning,” Evolutionary Computation, IEEE Transactions on, vol. 13, no. 4, pp. 767–779, 2009. [16] C. Wai, J. Greenson, R. Fontana, J. Kalbfleisch, J. Marrero, H. Conjeevaram, and A. Lok, “A simple noninvasive index can predict both significant fibrosis and cirrhosis in patients with chronic hepatitis c,” Hepatology, vol. 38, no. 2, pp. 518–526, 2003. [17] R. Sterling, E. Lissen, N. Clumeck, R. Sola, M. Correa, J. Montaner, M. S Sulkowski, F. Torriani, D. Dieterich, D. Thomas et al., “Development of a simple noninvasive index to predict significant fibrosis in patients with hiv/hcv coinfection,” Hepatology, vol. 43, no. 6, pp. 1317–1325, 2006. [18] D. Thabut, M. Simon, R. Myers, D. Messous, V. Thibault, F. Imbert-Bismut, and T. Poynard, “Noninvasive prediction of fibrosis in patients with chronic hepatitis c,” Hepatology, vol. 37, no. 5, pp. 1220–1221, 2003. [19] M. Idrees and S. Riazuddin, “Frequency distribution of hepatitis c virus genotypes in different geographical regions of pakistan and their possible routes of transmission,” BMC Infectious Diseases, vol. 8, no. 1, p. 69, 2008. [20] G. Li and X. Zhang, “Mining biomedical knowledge using chi-square association rule,” in Granular Computing (GrC), 2010 IEEE International Conference on. IEEE, 2010, pp. 283–285. [21] H. JorngTzong, C. WenFu et al., “Predicting regulatory elements in repetitive sequences using transcription factor binding sites.” EJB, Electronic Journal of Biotechnology, vol. 3, no. 3, pp. 1–10, 2000. [22] M. Dorigo, E. Bonabeau, and G. Theraulaz, “Ant algorithms and stigmergy,” Future Generation Computer Systems, vol. 16, no. 8, pp. 851–871, 2000. [23] M. Dorigo, V. Maniezzo, and A. Colorni, “Ant system: optimization by a colony of cooperating agents,” Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on, vol. 26, no. 1, pp. 29–41, 1996. [24] S. Pimont and C. Solnon, “A generic ant algorithm for solving constraint satisfaction problems,” in Abstract proceedings of ANTS, 2000, pp. 100–108. [25] R. Sethuram and M. Parashar, “Ant colony optimization and its application to boolean satisfiability for digital vlsi circuits,” in Advanced Computing and Communications, 2006. ADCOM 2006. International Conference on. IEEE, 2006, pp. 507–512. [26] M. Dorigo and L. Gambardella, “Ant colony system: A cooperative learning approach to the traveling salesman problem,” Evolutionary Computation, IEEE Transactions on, vol. 1, no. 1, pp. 53–66, 1997. [27] J. Bell and P. McMullen, “Ant colony optimization techniques for the vehicle routing problem,” Advanced Engineering Informatics, vol. 18, no. 1, pp. 41–48, 2004. [28] J. Handl and B. Meyer, “Improved ant-based clustering and sorting in a document retrieval interface,” Parallel Problem Solving from NaturePPSN VII, pp. 913–923, 2002. [29] J. Zhang, X. Hu, X. Tan, J. Zhong, and Q. Huang, “Implementation of an ant colony optimization technique for job shop scheduling problem,” Transactions of the Institute of Measurement and Control, vol. 28, no. 1, pp. 93–108, 2006. [30] L. De Campos, J. Fernandez-Luna, J. G’amez, and J. Puerta, “Ant colony optimization for learning bayesian networks,” International Journal of Approximate Reasoning, vol. 31, no. 3, pp. 291–311, 2002. [31] P. Bedossa and T. Poynard, “The metavir cooperative study group: An algorithm for the grading of activity in chronic hepatitis c,” Hepatology, vol. 24, no. 2, 1996. [32] S. Alvarez, “Chi-squared computation for association rules: preliminary results,” Comput. Sci. Dept., Boston College, Chestnut Hill, MA, Tech. Rep. BC-CS-2003-01, 2003. [33] J. Pearl, Probabilistic reasoning in intelligent systems: networks of plausible inference. Morgan Kaufmann, 1988. [34] Y. Wu, J. McCall, and D. Corne, “Two novel ant colony optimization approaches for bayesian network structure learning,” in Proceedings of the 2010 world congress on computational intelligence, IEEE Press, Piscataway, NJ, USA, 2010, pp. 4473–4479.
摘要: 使用血液生化指標(biochemical markers)來進行肝硬化程度檢測的研究已行之有年,在我們的研究中,貝氏網路(Bayesian network)被使用來進行肝硬化程度的檢測。 我們研究出來的方法不但與傳統的肝切片(Liver biopsy)檢測相比之下顯得較為簡單、經濟、方便,只需透過驗血即可得的血液生化指標便可進行檢測;且與現有同樣利用生化指標來進行肝硬化程度評估的非侵入式檢測法APRI 與 FIB-4相較之下,我們的方法有著較高的正確率。 卡方分佈(Chi-square)被用來量測兩個生化指標之間的關聯性強度,且在建立貝氏網路時可用此關聯性來建立點(node)與點之間的連結(link, arc, edge)。然而,兩指標間的相依性乃是對等的,無法明確得知各對相互關聯的指標於貝氏網路中哪些指標為親節點(parent node)或子節點,且每個親節點對子節點的最佳切分點(division point)也是未知的,為此,使用蟻群最佳化演算法在有限的時間內來尋找最佳且切分點適當的貝式網路模型以用來進行肝硬化程度的檢測。
Noninvasive evaluation which uses biochemical data for assessing the degree of liver fibrosis has been studied for many years. In our research, Bayesian network can be used to assess the degree of liver fibrosis well. Our method, not only comparing to traditional invasive evaluation method, Liver biopsy, is simpler, more economy and convenient, but also comparing to current noninvasive method, which also uses biochemical markers-APRI and FIB-4 is more accurate. Chi-square has been used to estimate the degree of relations between each pair of biochemical markers and build links between nodes of Bayesian network according to these relations. However, the dependency examinations between markers are symmetric-which nodes are parent nodes or sub nodes of each pair of related nodes in Bayesian network can not be known with certainty, and suitable division points for parent nodes are also unknown. For the reasons mentioned above, Ant Colony Optimization can be used to search for an optimized Bayesian network model with suitable division points of each parent nodes in limited time.
URI: http://hdl.handle.net/11455/9182
其他識別: U0005-2301201316354400
文章連結: http://www.airitilibrary.com/Publication/alDetailedMesh1?DocID=U0005-2301201316354400
Appears in Collections:電機工程學系所

文件中的檔案:

取得全文請前往華藝線上圖書館



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.