Research Article Automatic Detection and Quantification of Acute Cerebral Infarct by Fuzzy Clustering and Histographic Characterization on Diffusion Weighted MR Imaging and Apparent Diffusion Coefficient Map Jang-Zern Tsai, 1 Syu-Jyun Peng, 1 Yu-Wei Chen, 2,3,4 Kuo-Wei Wang, 1,5 Hsiao-Kuang Wu, 2 Yun-Yu Lin, 3 Ying-Ying Lee, 3 Chi-Jen Chen, 6 Huey-Juan Lin, 7 Eric Edward Smith, 8 Poh-Shiow Yeh, 7 and Yue-Loong Hsin 9,10,11 1 Department of Electrical Engineering, National Central University, Jhongli City, Taoyuan County 32001, Taiwan 2 Department of Computer Science and Information Engineering, National Central University, Jhongli City, Taoyuan County 32001, Taiwan 3 Department of Neurology, Landseed Hospital, Pingzhen City, Taoyuan County 32449, Taiwan 4 Department of Neurology, National Taiwan University Hospital, Taipei City 10002, Taiwan 5 Department of Medical Imaging, Landseed Hospital, Pingzhen City, Taoyuan County 32449, Taiwan 6 Department of Radiology, Taipei Medical University-Shuang Ho Hospital, New Taipei City 23561, Taiwan 7 Department of Neurology, Chi-Mei Medical Center, Tainan City 71004, Taiwan 8 Department of Clinical Neurosciences and Hotchkiss Brain Institute, University of Calgary, Calgary, AB, Canada T2N 1N4 9 Epilepsy Center, Buddhist Tzu Chi General Hospital, Hualian City, Hualian County 97002, Taiwan 10 Biomedical Electronics Translational Research Center, National Chiao Tung University, Hsinchu City 30010, Taiwan 11 Department of Neurology, Chung Shan Medical University Hospital, Taichung City 40201, Taiwan Correspondence should be addressed to Yu-Wei Chen; yuwchen@gmail.com Received 5 November 2013; Revised 31 December 2013; Accepted 9 January 2014; Published 12 March 2014 Academic Editor: George Pengas Copyright © 2014 Jang-Zern Tsai et al. his is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Determination of the volumes of acute cerebral infarct in the magnetic resonance imaging harbors prognostic values. However, semiautomatic method of segmentation is time-consuming and with high interrater variability. Using difusion weighted imaging and apparent difusion coeicient map from patients with acute infarction in 10 days, we aimed to develop a fully automatic algorithm to measure infarct volume. It includes an unsupervised classiication with fuzzy C-means clustering determination of the histographic distribution, deining self-adjusted intensity thresholds. he proposed method attained high agreement with the semiautomatic method, with similarity index 89.9 ± 6.5%, in detecting cerebral infarct lesions from 22 acute stroke patients. We demonstrated the accuracy of the proposed computer-assisted prompt segmentation method, which appeared promising to replace the laborious, time-consuming, and operator-dependent semiautomatic segmentation. 1. Introduction Cerebrovascular disease is one of the leading causes of acute mortality and chronic disability [1]. he volume of infarct is associated with severity of acute ischemic stroke and corre- lates with clinical prognosis and the efect of endovascular therapy [2–4]. A rapid and reliable method of determination of volume of acute infarct will help predict the prognosis and facilitate further investigation. he difusion weighted imaging (DWI) is more sensitive than other magnetic resonance imaging (MRI) modalities to small water difusion changes in the acute ischemic brain, especially within 48 hours of the ictus [5–9]. Hindawi Publishing Corporation BioMed Research International Volume 2014, Article ID 963032, 13 pages http://dx.doi.org/10.1155/2014/963032