[image 01820] 多元計算解剖学セミナーのご案内 （5／31@岐阜大学）

[Fujita Hiroshi]

関係各位

　藤田＠岐阜大学大学院・知能イメージ情報分野 です．

　イリノイ工科大学の鈴木賢治先生をお迎えして，以下のようなセミナーを開催いたします．
　今回は，文部科学省新学術領域「多元計算解剖学」の多元計算解剖セミナーとして開催いたします．

　多数のご参加をお待ちしております．


-------------------------------------------------------------------------------------------------------------
多元計算解剖学セミナー

講演題目：
Image-Patch-based Machine Learning in Medical Image Processing,
Analysis and Diagnosis
（医用画像処理・解析・診断における画像パッチに基づく機械学習）

講演者：
Kenji Suzuki, Ph.D.
Associate Professor of Electrical and Computer Engineering,
Medical Imaging Research Center,
Pritzker Institute of Biomedical Science & Engineering,
Illinois Institute of Technology, USA

日時：　2016年5月31日（火）10:30-12:00
場所：　岐阜大学医学部棟８階多目的室
http://www.med.gifu-u.ac.jp/
http://www.fjt.info.gifu-u.ac.jp/guide/building.html

講演概要：


Machine leaning (ML) has become one of the most active areas of
research in medical imaging, because “learning from examples or data”
is crucial to handling a large amount of data (“Big data”) coming from
medical imaging systems. Recently, as the available computational
power increased dramatically, image-patch-based ML emerged in the
medical imaging field, which uses pixel values in image patches
directly, instead of features calculated from segmented objects as
input information. Image-patch-based ML is an end-to-end ML model that
enable a direct mapping from the raw input data to the desired
outputs, eliminating the need for hand-crafted features.
Image-patch-based ML is a versatile, powerful framework that can
acquire image-processing and analysis functions, including noise
reduction, lesion and organ enhancement, pattern separation,
segmentation, and classification, through training with image
examples. On the other hand, in the computer vision field, deep
learning that has a deep architecture drew enthusiastic attentions.
Deep learning learns high-level computer-vision tasks from patches in
images, which has a close relationship with image-patch-based ML. In
this talk, image-patch-based ML in medical image processing and
computer-aided diagnosis (CAD) of lesions in medical images is
overviewed, including separation of bones from soft tissue in chest
radiographs, radiation dose reduction in CT, lung nodule detection in
chest radiography and CT, polyp detection in CT colonography, and
detection of liver tumors in hepatic CT and MRI.  Relationships
between image-patch-based ML and deep learning (such as deep neural
networks) are also discussed.
　（ご講演は日本語での予定です）

-------------------------------------------------------------------------------------------------------------


-- 
　  岐阜大学 大学院  教授・分野主任
      藤田　広志 （Hiroshi Fujita）
      医学系研究科 知能イメージ情報分野
                    （工学研究科，工学部兼担）
　　  〒501-1194   岐阜市柳戸 1-1
　　     TEL: 058-230-6512，6513，
             FAX: 058-230-6514
　　　  e-mail:  fujita ＠ fjt.info.gifu-u.ac.jp
　　  研究室 HomePage:
             http://www.fjt.info.gifu-u.ac.jp/