Keynote Speakers

Keynote Speaker I

Prof. Hyoungseop Kim received his B.A. degree in electrical engineering from Kyushu Institute of Technology in 1994, the Masters and Ph.D. degree from Kyushu Institute of Technology in 1996 and 2001, respectively. He is a professor in the department of control engineering at Kyushu Institute of Technology. His research interests are focused on medical application of image analysis.

Title of Speech: "Image Registration Techniques and Its Application for Computer Aided Diagnosis in Medical Field"

Abstract: For reducing the load to radiologist and improving of detection accuracy, a CAD (Computer Aided Diagnosis) system is expected from medical fields. In the medical image processing fields, many related works are reported to develop the CAD system as helpful technical issues. On the other hand, detection of subtle lesions on CT images is a difficult task for radiologists, because subtle shadows tend to have low contrast, and a large number of CT images be interpreted in a limited time. A temporal subtraction image, which is obtained by subtraction of a previous image from a current one, can be used for enhancing interval changes, such as difference in the size of a tumor, on medical images by removing most of the normal structures. For detection of lesions in chest radiographs, the temporal subtraction technique has been applied successfully to clinical cases. Although the overall performance of the temporal subtraction technique was relatively good, registration errors still remained. In this talk, we propose a new non-rigid image warping technique for accurate registration and subtraction of two thoracic MDCT images.

Keynote Speaker II

Prof. Hiroshi Fujita received the B.S. and M.S. degrees in electrical engineering from Gifu University, Japan, in 1976 and 1978, respectively, and Ph.D. degree from Nagoya University in 1983. He became a research associate in 1978 and an associate professor in 1986 at Gifu National College of Technology. He was a visiting researcher at the K. Rossmann Radiologic Image Laboratory, University of Chicago, in 1983-1986. He became an associate professor in 1991 and a professor in 1995 in the Faculty of Engineering, Gifu University. He has been a professor and chair of intelligent image information since 2002 at the Graduate School of Medicine, Gifu University. He is a member of the Society for Medical Image Information (President), the Institute of Electronics, Information and Communication Engineers (Fellow), its Technical Groups on Medical Image (Adviser), the Japan Society for Medical Image Engineering (Director), and some other societies such as IEEE and SPIE. He has been also served as scientific committee or program committee members, such as in International Workshop on Digital Mammography, SPIE Medical Imaging, and Computer Assisted Radiology and Surgery (CARS). He was worked as a General co-chair of Asian Forum on Medical Imaging 2007 held in Cheju National University, Korea, and as a General Chair of International Workshop for Breast Imaging (IWDM2014, Gifu). He has also worked as a Guest Editor-in-Chief in Special Section Editorial Committee for Medical Imaging, issued in April, 2013, from IEICE Society in Japan. His research interests include computer-aided diagnosis system, image analysis and processing, and image evaluation in medicine. He has published over 1000 papers in Journals, Proceedings, Book chapters and Scientific Magazines.

Title of Speech: State-of-the-Art of Computer-Aided Medical Image Diagnosis

Abstract: Computer-aided detection/diagnosis (CAD) has become one of the major research subjects in medical imaging and diagnostic radiology. CAD may be defined as diagnosis made by a physician who takes into account the computer output as a “second opinion”. The purpose of CAD is to improve the quality and productivity of physicians in their interpretation of medical images. Some pioneer studies are dated back to the 1960s. In 1988, the first U.S. FDA (Food and Drug Administration) approved commercial CAD system, a film-digitized mammography (breast X-ray image) system, was launched by R2 Technologies, Inc. (Hologic at present). The success was quickly repeated by a number of companies. FDA-approved CAD products in the field of breast imaging (mammography, ultrasonography and breast MRI), chest imaging (conventional radiography and CT), and CT colonoscopy can be seen until now. In this presentation, the status of the CAD developments and commercialization is reviewed along with some new CAD technologies including AI (artificial intelligence) and deep learning, and also recent topics and results from a CAD-related project called “Multidisciplinary Computational Anatomy” (http://wiki.tagen-compana.org/mediawiki/index.php/Main_Page) will be introduced.

Speech of Title

 

Keynote Speaker III

Prof. Kiyoshi Hoshino received two doctor's degrees; one in Medical Science in 1993, and the other in Engineering in 1996, from the University of Tokyo respectively. From 1993 to 1995, he was an assistant professor at Tokyo Medical and Dental University School of Medicine. From 1995 to 2002, he was an associate professor at University of the Ryukyus. From 2002, he was an associate professor at the Biological Cybernetics Lab of University of Tsukuba. He is now a professor. From 1998 to 2001, he was jointly appointed as a senior researcher of the PRESTO "Information and Human Activity" project of the Japan Science and Technology Agency (JST). From 2002 to 2005, he was a project leader of a SORST project of JST. His research interests include biomedical measurement and modelling, medical engineering, motion capture, computer vision, and humanoid robot design.

Title of Speech: "Measurement of Rotational Eye Movements in the Dark Environment"

Abstract: Car sickness, visually-induced motion sickness (VIMS), stereoimage-induced sickness and their accompanying dizziness and sickness feeling are associated with rotational eye movement. This presentation therefore introduces the method for measuring rotational eye movement at a high speed and with a high accuracy, especially in the dark environment. The author first focuses on the blood vessel image of the sclera (white of the eyeball) which is not affected by the variation of the diameter of the pupil, and second uses weak blue light irradiation in addition to infrared light to enhance contrast on the blood vessel images. The system proposed traces the images. The experimental evaluation shows that rotational eye movement is measured at a processing speed of 78 fps with the average of estimated accuracy of equal to lower than 0.24 degrees in the dark environment where the diameter of the pupil varies differently depending on changes in the ambient environment of lighting and/or image contents observed. No user bothers the blue light irradiation to his/her eyeballs.

Plenary Speaker I

Prof. Hidetaka Arimura received a BS in 1989 and an MS in 1991 in electronics and information engineering, and his PhD in engineering from Kyoto Institute of Technology in 1996. He used to work for Shimadzu Corporation from 1991 to 1996, Tokyo Women’s Medical University from 1996 to 1998, Hiroshima International University from 1998 to 2002, and the University of Chicago from 2002 to 2004. He is currently working as a professor in Division of Quantum Radiation Science, Department of Health Sciences, Faculty of Medical Sciences, Kyushu University, and also he is a certificated medical physicist in Japan. His research interests include computer-aided diagnosis and image assisted radiation therapy based on medical image analysis and pattern recognition. Recently, he published “Image-Based Computer-Assisted Radiation Therapy” (Springer, 2017) as an editor.

Title of Speech: "Physics-based Radiotherapy to Radiomics-based Radiotherapy"

Abstract: Major requirements in conventional radiation therapy from a physics point of view are: (1) high conformity and homogeneity of the dose distributions to the tumor regions, and (2) accurate tumor localization and patient positioning. On the other hand, from global point of view, medicine is moving toward “precision medicine (PM),” which is a novel concept for disease treatment and prevention that takes into account individual variability (patient or tumor heterogeneity) in environment, lifestyle and genes for each person. However, the issues in PM are invasive biopsy, high cost and slow throughput for examination of gene mutations. Further, since tumors are heterogeneous, a small part of a tumor obtained by a biopsy could not be reliable for PM, and thus it could be difficult to incorporate PM into the radiation therapy. Therefore, radiomics concept has emerged in this field for practically performing PM. The radiomics is the novel field, which massively and comprehensively analyzes a large number of medical images, and extracts mineable data that can make it possible to carry out PM. In the lecture, the author will describe the background and basic concept of the radiomics and its applications including achievements in the author’s laboratory.

Plenary Speaker II

Dr. Guangxu Li received his B.E. and M.E. degrees in automation engineering from Liaoning University of Technology in 2006 and 2009, the Ph.D. degree from Kyushu Institute of Technology in 2013, respectively. He is a lecturer in the school of electronics and information engineering at Tianjin Polytechnic University. His research interests are focused on medical image processing and image-guided surgical system.

Title of Speech: "Fractional Statistical Shape Model Method for Multiple Organs Segmentation"

Abstract: Due to utilizing the priori information of shapes, Statistical Shaped Model (SSM) methods are concise, yet powerful tools for image segmentation, analyzing and interpreting anatomical objects from medical datasets in Computer Aided Diagnosis (CAD) system. Many objects of interest in images can be represented as deformed versions of some average structure. The talk will include an short overview of model building and automated segmentation pipeline based on SSMs. I will also discuss our recent work to Fractional Statistical Shape Model (FSSM), which aims to build statistical models of the ambiguous boundaries between organs in medical images. We will start from the construction of mesh-based FSSM, especially the registration method of fractional surfaces, up to the segmentation strategy for multiple structures.