Soft computing based brain MR angiography image analysis for preventing
                                cerebellar stroke

                                                        Syoji Kobashi
                                         University of Hyogo/Osaka University, Japan




                         Abstract                                Congress in 2000, the IEEE EMBS Japan Young Investiga-
A rupture of intracranial aneurysms may cause serious cere-      tors Competition from IEEE EMBS Japan Chapter in 2003,
bral diseases such as cerebral stroke. Since it is hard to re-   the Franklin V. Taylor Memorial Award at 2009 IEEE In-
cover completely from stroke, finding unruptured aneurysms       ternational Conference on Systems, Man, and Cybernetics
and medical and/or surgical treatment before rupture are ef-     in 2009, Outstanding Contribution Award at World Automa-
ficient to patients. Magnetic resonance angiography (MRA),       tion Congress in 2010, and others. Dr. Kobashi is an asso-
an imaging protocol using magnetic resonance imaging             ciate editor of International Journal on Intelligent Comput-
(MRI), can provide detailed section images of cerebral ar-       ing in Medical Sciences and Image Processing, and of Au-
teries noninvasively. However, image diagnosis using MRA         tosoft Journal, and a guest editor of journals. He is also serv-
is very time-consuming and labor-intensive for radiologists      ing as the chair of International Forum on Multimedia and
because few hundreds sectional images per subject are ac-        Image Processing, World Automation Congress 2012 and
quired to take the whole cerebrum. In addition, many peo-        2014, and the workshop chair of MISA2013, the PC Chair of
ple take MRA test on their health examination in Japan.          ICIEV2014, RVSP2013, ICETET2013, ICETET2012, and
Thus, computer-aided diagnosis (CAD) system for MRA              others. He is a board member of Japan Society for Clini-
images is desired in order to increase the quality of diag-      cal Biomechanics, and is a member of the Japan Society for
nosis and to automate the examination. This lecture intro-       Medical and Biological Engineering, the Biomedical Fuzzy
duces a fully automated aneurysm extraction method from          Systems Association, the Japan Society for Fuzzy Theory
MRA images. Principal components of the method are iden-         and Systems, the Organization of Human Brain Mapping,
tification of aneurysm candidates (= ROIs; regions of inter-     the Japan Society of Medical Imaging Technology, and the
est) from MRA images and estimation of a fuzzy degree for        IEEE.
each aneurysm candidate based on a case-based reasoning
(CBR). The fuzzy degree indicates whether a candidate is                          Contact Information
true aneurysm. The method is applied to 15 subjects with 19      Address: 2167 Shosha Himeji Hyogo, 671-2280, JAPAN
aneurysms. The experimental results indicate that this CAD       TEL/FAX: +81 79 267 4989
system detected all aneurysms except a fusiform aneurysm,        E-mail: kobashi@eng.u-hyogo.ac.jp
and gave high fuzzy degrees and high priorities for the de-
tected aneurysms.
    This work was partially supported by JSPS KAK-
ENHI Grant-in-Aid for Scientific Research(A) Grant num-
ber 13370832.

                        Short Bio.
Syoji Kobashi received his B.E. in electronics (1995), M.E.
(1997) and D.E. (2000) all from the Himeji Institute of
Technology, Japan. He is currently an associate professor in
Graduate School of Engineering at the University of Hyogo,
Japan, a Guest Associate Professor in WPI Immunology
Frontier Research Center at Osaka University, Japan, and a
Visiting Scholar in Department of Radiology at University
of Pennsylvania, USA. His research interests include soft
computing aided medical signal/image processing. He pub-
lished 6 book chapters, 53 Journal papers, and 250+ con-
ference proceeding papers. He received the Joseph F. En-
gelberger Best Paper Award at the 2nd World Automation