Presentation 2007/5/11
Computer Automated Cancer Detection System from PET/CT images
Hiroshi ARISAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recently, medical data imaging (CT, MR, PET, and so on) are regarded as one of the key technologies in cancer detection. Among them, PET imaging is epoch-making method because the image can show us the exact position/area of abnormality occurred (i.e. candidate of cancer area and so on) directly. It is basically a set of 2D images each of which show the FDG density map (cross-section) of a patient. However, for the radiologists, it is very hard work to analyze FDG map and find out the all abnormal areas without missing. In order to support such diagnosis, we have been developing the Automated Cancer Detection (CAD) system by using an image-based inference system. It can point out the all abnormal accumulation of FDG thru all slices completely. We are developing both inference engine and the cancer detection algorithm based on the real radiologists knowledge and skill, and execute field tests for the future application.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) PET-CAD / PET image / Cancer Detection / Inference System
Paper # SSS2007-6
Date of Issue

Conference Information
Committee SSS
Conference Date 2007/5/11(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Safety (SSS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Computer Automated Cancer Detection System from PET/CT images
Sub Title (in English)
Keyword(1) PET-CAD
Keyword(2) PET image
Keyword(3) Cancer Detection
Keyword(4) Inference System
1st Author's Name Hiroshi ARISAWA
1st Author's Affiliation Graduate School of Environment and Information Sciences, Yokohama National University()
Date 2007/5/11
Paper # SSS2007-6
Volume (vol) vol.107
Number (no) 45
Page pp.pp.-
#Pages 4
Date of Issue