Development of the methods for detecting organ and lesion from medical image using image context

2014 Fiscal Year Final Research Report

• Project/Area Number: 23300076
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Single-year Grants
• Section: 一般
• Research Field: Perception information processing/Intelligent robotics
• Research Institution: Chukyo University
• Principal Investigator: MEKADA Yoshito 中京大学, 工学部, 教授 (00282377)
• Co-Investigator(Kenkyū-buntansha): HASEGAWA Jun-ichi 中京大学, 工学部, 教授 (30126891) ; MURASE Hiroshi 名古屋大学大学院, 情報科学研究科, 教授 (90362293) ; KITASAKA Takayuki 愛知工業大学, 経営情報学部, 准教授 (00362294)
• Project Period (FY): 2011-04-01 – 2015-03-31
• Keywords: 医用画像 / パターン認識 / 映像分類

Outline of Final Research Achievements

In this research project, we developed some methods to extract context of the medical data and image recognition methods using such context. The robust methods to find some events that happen rarely, such as cancerous region in the medical image and bleeding while surgical operation, are much desired. We utilized the past events (lesion, image sequence of medical treatment) as the context to find particular medical events. Concretely, proposed scheme is applied to extract liver region, simultaneous extraction of rare event and frequently-occurred event from long-sustained laparoscope surgical operation, and generating rare-occurred disease image for machine learning.

Free Research Field

画像パターン認識