Premium
Target image enhancement using representative line in MR cholangiography images
Author(s) -
Kobashi Syoji,
Kondo Katsuya,
Hata Yutaka
Publication year - 2004
Publication title -
international journal of imaging systems and technology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.359
H-Index - 47
eISSN - 1098-1098
pISSN - 0899-9457
DOI - 10.1002/ima.20015
Subject(s) - computer science , artificial intelligence , imaging phantom , pancreatic duct , segmentation , computer vision , radiology , medicine , pancreatitis , surgery
Abstract MR cholangiography (MRC) is a commonly used imaging method for diagnosing the pancreatic duct. This article proposes a novel method for enhancing medical images called target image enhancement using representative line (TIER), and its application to MRC images. Our method first finds the representative line (RL) of the pancreatic duct using a fuzzy if‐then rule. TIER presumes the approximate region of the pancreatic duct using the obtained RL, and then emphasizes the intensity in the approximate region. Therefore, our method does not require any segmentation procedures, which often may be hard work. We evaluated the ability to find the RL and to estimate the approximate region of the pancreatic duct by applying the proposed method to computer‐simulated data and MRI phantom data. We also show the image‐enhanced images for normal and abnormal patients. © 2004 Wiley Periodicals, Inc. Int J Imaging Syst Technol 14, 122–130, 2004; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ima.20015