A perceptually-based algorithm provides effective visual feedback to radiologists searching for lung nodules

C. F. Nodine, E. A. Krupinski, H. L. Kundel

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Scopus citations

Abstract

The gaze durations of fixation clusters generated by radiologists searching for nodules in chest images varies according to the degree of interest in the local image structure. The authors present a computer algorithm that filters out short-duration clusters, feeding back only the image locations fixated for >1000 ms, measured during the initial search of the image. The feedback algorithm highlighted 72% of initially fixated nodules, and 34% of initially unreported nodules were correctly identified in a second view with feedback, compared with only 21% without feedback. This computer algorithm, based on the radiologist's gaze duration data, effectively localizes potential nodule sites for feedback and enhances diagnostic performance.

Original languageEnglish (US)
Title of host publicationProceedings of the First Conference on Visualization in Biomedical Computing
PublisherPubl by IEEE
Pages202-207
Number of pages6
ISBN (Print)0818620390
StatePublished - 1990
EventProceedings of the First Conference on Visualization in Biomedical Computing - VBC '90 - Atlanta, GA, USA
Duration: May 22 1990May 25 1990

Publication series

NameProceedings of the First Conference on Visualization in Biomedical Computing

Other

OtherProceedings of the First Conference on Visualization in Biomedical Computing - VBC '90
CityAtlanta, GA, USA
Period5/22/905/25/90

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'A perceptually-based algorithm provides effective visual feedback to radiologists searching for lung nodules'. Together they form a unique fingerprint.

Cite this