Automatic detection and quantification of calcium objects from clinical images for risk level assessment of coronary disease

R. Priyatharshini*, S. Chitrakala

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

Abstract

Medical diagnosis is often challenging, owing to the diversity of medical information sources. Significant advancements in healthcare technologies, potentially improving the benefits of diagnosis, may also result in data overload while the obtained information is being processed. From the beginning of time, humans have been susceptible to a surplus of diseases. Of the innumerable life-threatening diseases around, heart disease has garnered a great deal of consideration from medical researchers. Coronary Heart Disease is indubitably the commonest manifestation of Cardiovascular Disease (CVD), representing some 50% of the whole range of cardiovascular events. Medical imaging plays a key role in modern-day health care. Automatic detection and quantification of lesions from clinical images is quite an active research area where the challenge to obtain high accuracy rates is an ongoing process. This chapter presents an approach for mining the disease patterns from Cardiac CT (Computed Tomography) to assess the risk level of an individual with suspected coronary disease.

Original languageEnglish
Title of host publicationAdvances in Soft Computing and Machine Learning in Image Processing
PublisherSpringer Verlag
Pages213-225
Number of pages13
DOIs
Publication statusPublished - 15 Oct 2017
Externally publishedYes

Publication series

NameStudies in Computational Intelligence
Volume730
ISSN (Print)1860-949X

Keywords

  • Active contour model
  • Calcium object detection
  • Coronary disease diagnosis
  • Image segmentation
  • Risk level categorization

Cite this