TY - JOUR ID - 13116 TI - Pseudo-CT Generation from Magnetic Resonance Imaging by fuzzy look up table algorithm JO - Iranian Journal of Medical Physics JA - IJMP LA - en SN - AU - Yousefi Moteghaed, Niloofar AU - Mostaar, Ahmad AD - Department of Biomedical Engineering and Medical Physics, Faculty of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran. Y1 - 2018 PY - 2018 VL - 15 IS - Special Issue-12th. Iranian Congress of Medical Physics SP - 427 EP - 427 KW - magnetic resonance imaging KW - Radiation Therapy KW - computer tomography KW - Treatment Planning DO - 10.22038/ijmp.2018.13116 N2 - Introduction: Despite growing interest in the use of magnetic resonance imaging (MRI) in the external radiotherapy design process (RT), Computer Tomography (CT) remains a gold standard and is regarded as a basic imaging modality in radiotherapy. MRI shows the high contrast in soft tissues without any radiation exposure to patients. As a result, MRI is used in functional tissue structures with registration on the CT images. Unfortunately, this causes systematic errors during the registration of MRI and CT images. The purpose of this study is to investigate the possibility of removing the CT simulator images and replacing it with pseudo-CT images (which created by MRI images) for the electron density calculation in radiotherapy treatment planning.   Materials and Methods: The pseudo-CT images were generated for 10 randomly chosen patients with brain disease. Data consisted of image voxels chosen within the segmented area of the brain in both MRI and CT images. The relation between MRI intensity and electron density was derived from HU converted model by fuzzy look up table algorithm.   Results: It was found that the MRI intensity value is related to the HU value within different parts such as skull bone, sinus, and brain. The mean prediction errors of the conversion model are -0.53, -0.082, 0.0145HU in brain, skull and air regions respectively. The mean absolute errors are 19.40 , 50.53,1.22 Conclusion: The proposed method enables generation of pseudo-CT data for the different segmented part of the brain from MRI series with appropriate mean prediction errors. UR - https://ijmp.mums.ac.ir/article_13116.html L1 - ER -