Application of machine learning method to diagnosis of alzheimer diseases using SPECT brain image

M. Takahashi, T. Idani, H. Fukuda, R. Kawashima, M. Kitamura

Research output: Contribution to conferencePaperpeer-review

Abstract

The automatic diagnosis system for dementia with SPECT brain image has been developed. Previous work had analyzed the average of blood flow with respect to each functional region. However, the accuracy of diagnosis was lower than that of expert radiologists'. This is partially because that previous work couldn't retrieve some of important information for discrimination from SPECT images. In the present study, new attribute values have been added, which are symmetry index of cerebral flow and rate of blood flow change in the functional regions based on the diagnostic strategy of the expert radiologists'. The accuracy has been improved by introducing these additional attributes.

Original languageEnglish
Pages2420-2423
Number of pages4
Publication statusPublished - 2005 Dec 1
EventSICE Annual Conference 2005 - Okayama, Japan
Duration: 2005 Aug 82005 Aug 10

Other

OtherSICE Annual Conference 2005
CountryJapan
CityOkayama
Period05/8/805/8/10

Keywords

  • Diagnosis support
  • Dimentia
  • Functional brain image
  • SPECT

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Application of machine learning method to diagnosis of alzheimer diseases using SPECT brain image'. Together they form a unique fingerprint.

Cite this