Improvement in specificity of ultrasonography for diagnosis of breast tumors bv means of artificial intelligence

Victor Goldbera, Armando Manduca, John J. Gisvold, James F. Greenleaf, Daniel L. Ewert

Research output: Contribution to journalArticle

77 Scopus citations

Abstract

A set of ultrasonograms of lesions from 200 patients between the ages of 14 and 93 years who underwent mammography followed by ultrasonographic examination and excisional biopsy has been studied with computer vision techniques to improve the ultrasonographic specificity of the diagnosis. Selected features representing the texture of the lesion were calculated and then classified by an artificial neural network. This network was biased toward correctly classifying all the malignant cases at the expense of some misclassification of the benign cases. The network diagnosed the malignant cases with 100% sensitivity and 40% specificity (compared with 0% specificity for the radiologists diagnosing the same set of cases in the breast imaging setting), and tests performed with a leave-one-out technique indicate that the network will generalize well to new cases. This suggests that methods based on neural network classification of texture features show promise for potentially decreasing the number of unnecessary biopsies by a significant amount in patients with sonographically identifiable lesions.

Original languageEnglish (US)
Pages (from-to)1475-1481
Number of pages7
JournalMedical physics
Volume19
Issue number6
DOIs
StatePublished - Nov 1992

Keywords

  • neural networks
  • sonomammography
  • texture analysis

ASJC Scopus subject areas

  • Biophysics
  • Radiology Nuclear Medicine and imaging

Fingerprint Dive into the research topics of 'Improvement in specificity of ultrasonography for diagnosis of breast tumors bv means of artificial intelligence'. Together they form a unique fingerprint.

  • Cite this