Research and Development of the Quantitative Method of Computer Aided Diagnosis using PET-CT images and the application to Companion Diagnostics

2017 Fiscal Year Final Research Report

• Project/Area Number: 15H02706
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Single-year Grants
• Section: 一般
• Research Field: Multimedia database
• Research Institution: Yokohama City University
• Principal Investigator: Arisawa Hiroshi 横浜市立大学, 医学研究科, 客員教授 (10092636)
• Co-Investigator(Kenkyū-buntansha): 井上 登美夫 横浜市立大学, 医学研究科, 教授 (80134295)
• Co-Investigator(Renkei-kenkyūsha): Nemoto AKINOBU 横浜市立大学, 医学部, 准教授 (20264666) ; SATO Takako 相模女子大学, 学芸学部, 准教授 (10401697)
• Project Period (FY): 2015-04-01 – 2018-03-31
• Keywords: 情報工学 / マルチメディア・データベース / マルチメディア情報処理 / 医療画像診断医療診断支援データベース

Outline of Final Research Achievements

This research aims to construct an innovative Computer Aided Diagnosis System (CAD) using PET (Positron Emission Tomography) and CT (Computed Tomography) Images. Key attributes of our CAD are: 1: the CAD turns not a specific organ but whole body into an object of medical analyses, and 2: the CAD can detect “abnormal possible areas (candidates of cancers)” with very high recall rate. Further, we propose a new technology “Quantitative CAD”, which can assign the “risk value” for each abnormal possible area based on characteristics of the region. This scheme will provide a useful tool to the field “Companion Diagnostics, CD)”. Because in CD, the curative effect (by medicine, radiation etc.) must be measured patient by patient strictly. And the above innovative CAD has the ability to quantify the risk (increase/decrease) values of each cancer region with firm method (algorithm in computer).

Free Research Field

マルチメディア・データベース