摘要
Segmentation of medical images is a challenging task. A myriad of different methods have been proposed and implemented in recent years. In spite of the huge effort invested in this problem, there is no single approach that can generally solve the problem of segmentation for the large variety of image modalities existing today. In this paper, first we introduce the ITK architecture and installation under Windows operating system and configuration using python language. Secondly, we introduce the main image segmentation algorithms of ITK through experiments, including Region Growing (Connected Threshold, Neighborhood Connected, Confidence Connected, Isolated Connected), Segmentation Based on Watersheds (Watershed Filter, Fast Marching Segmentation, Shape Detection Segmentation, Threshold Level Set Segmentation). Finally, we give the calculation process and experimental results.
延伸閱讀
- Zhou, Z. H., & Wen, X. J. (2019). A Survey of Registration Algorithms Based on ITK. 電腦學刊, 30(2), 192-201. https://doi.org/10.3966/199115992019043002018
- 林昀葦（2021）。A Study of Algorithms for Deriving Frequent Itemsets〔碩士論文，國立宜蘭大學〕。華藝線上圖書館。https://doi.org/10.6820/niu202100200
- Chen, Y. A. (2018). Vision Based User Interface Segmentation Algorithm [master's thesis, National Taiwan University]. Airiti Library. https://doi.org/10.6342/NTU201802030
- Ho, N. L. (2004). Algorithms on constrained sequence alignment [master's thesis, The University of Hong Kong]. Airiti Library. https://www.airitilibrary.com/Article/Detail?DocID=U0029-1812201200004416
- 鄧國壽、曾正雄（2003）。A Study on the Simplification Algorithms for Cartographic Generalization。地圖 ： 中華民國地圖學會會刊，(13)，57-74。https://doi.org/10.30006/JC.200309.0005