Multi-Disease Multi-Organ CAD System

Objective: The spatial and the time resolutions of medical images have become extremely fine and structures of human body less than 1mm in size can be visible on the image. It means that the number of slice images is too many for radiologists to read each of them carefully and information contained in the images is not fully utilized for diagnosis. The state of the art of the computer aided diagnosis system is quite limited in ability. The objective of this research project is to develop an advanced computer aided diagnosis system which makes full use of anatomical knowledge on human body and diagnostic knowledge on various kinds of diseases. The product of this research project will contribute to realize accurate and reliable diagnosis.

Research Topics:

- Simultaneous segmentation of multiple organs in multi-dimensional medical image

- Computational modeling of organ structures

- Intelligent CAD based on anatomical classification

- Intelligent CAD based on localized pathological morphology

- Intelligent CAD based on normal structure recognition of the human body

- Intelligent CAD based on quantitative analysis of spatio-temporal changes in medical image sequences

- Navigation-based diagnosis system as an intelligent CAD system

- Integration of multi-modal medical images for CAD

- Evaluation of signal and noise and exposure in medical images for CAD

Organization: The organization of this project is here.

This website is administered by Kobatake Lab at Tokyo Univ. of Agri. & Tech.

2-24-26, Naka-tyou, Koganei-shi, Tokyo, 184-8588, Japan.

E_mail: kobatake@cc.tuat.ac.jp