Part 2. Automated change detection and characterization applied to serial MR of brain tumors may detect progression earlier than human experts

Julia Patriarche, Bradley Erickson

Research output: Contribution to journalArticle

11 Scopus citations

Abstract

An algorithm was developed which compares serial MRI brain examinations of brain tumor patients and judges them as either "stable" or "progressing". A set of 88 serial MR cases were obtained, consisting of cases which were stable and remained stable for at least 8 months, cases which were stable but progressed in less than 8 months, and cases which were progressing. The algorithm was run and its output was compared to the original clinical interpretation. Of the exam pairs which were judged stable and which remained stable at least 8 months after the later examination, the algorithm diagnosed 45/46 as stable. For exam pairs judged to be progressing, the algorithm judged 15/17 to be progressing. Of the exam pairs which were judged stable, but which went on to progress less than 8 months after the later of the pair, 16/25 were judged by the algorithm to be progressing.

Original languageEnglish (US)
Pages (from-to)321-328
Number of pages8
JournalJournal of Digital Imaging
Volume20
Issue number4
DOIs
StatePublished - Dec 1 2007

    Fingerprint

Keywords

  • Brain tumor
  • Change detection
  • Computer aided diagnosis
  • Serial imaging

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Science Applications

Cite this