Automated detection of breast carcinomas not detected in a screening program
- PMID: 9577496
- DOI: 10.1148/radiology.207.2.9577496
Automated detection of breast carcinomas not detected in a screening program
Abstract
Purpose: To investigate the possibility of automated detection of early signs of cancer that were not detected in a breast cancer screening program.
Materials and methods: A set of 75 mammograms (in 65 women) with subtle circumscribed masses, stellate lesions, and architectural distortions that were not detected in a screening program by two radiologists was assembled and extended with 142 normal mammograms (contralateral mammograms in the same 65 women). An automated system for the detection of circumscribed masses and stellate lesions was applied to this set.
Results: In 22 (34%) of 65 cases, an early sign of cancer was detected at a specificity of one false-positive finding per image. At a specificity of three false-positive findings per image, 39 (60%) of the cancers were detected. Of the tumors that were classified as screening errors, seven (50%) were found at a specificity of 0.5 false-positive finding per image.
Conclusion: A substantial proportion of cancers that were missed in a screening program, despite double reading, were found with this detection method at less than one false-positive finding per image.
Similar articles
-
Testing the effect of computer-assisted detection on interpretive performance in screening mammography.AJR Am J Roentgenol. 2006 Dec;187(6):1475-82. doi: 10.2214/AJR.05.0940. AJR Am J Roentgenol. 2006. PMID: 17114540
-
Computer-aided detection schemes: the effect of limiting the number of cued regions in each case.AJR Am J Roentgenol. 2004 Mar;182(3):579-83. doi: 10.2214/ajr.182.3.1820579. AJR Am J Roentgenol. 2004. PMID: 14975949
-
[Breast carcinoma diagnosed in mammographic screening incidentally. Research on the radiologic signs in prior mammograms].Radiol Med. 1999 Nov;98(5):342-6. Radiol Med. 1999. PMID: 10780212 Italian.
-
[Reading screening mammograms with the help of neural networks].Ned Tijdschr Geneeskd. 1999 Nov 6;143(45):2232-6. Ned Tijdschr Geneeskd. 1999. PMID: 10578420 Review. Dutch.
-
Computer-assisted reading of mammograms.Eur Radiol. 1997;7(5):743-8. doi: 10.1007/BF02742937. Eur Radiol. 1997. PMID: 9166576 Review.
Cited by
-
Sparseness of the trabecular pattern on dental radiographs: visual assessment compared with semi-automated measurements.Br J Radiol. 2012 Aug;85(1016):e455-60. doi: 10.1259/bjr/32962542. Epub 2012 Feb 28. Br J Radiol. 2012. PMID: 22374281 Free PMC article.
-
Anniversary paper: History and status of CAD and quantitative image analysis: the role of Medical Physics and AAPM.Med Phys. 2008 Dec;35(12):5799-820. doi: 10.1118/1.3013555. Med Phys. 2008. PMID: 19175137 Free PMC article. Review.
-
Evaluating computer-aided detection algorithms.Med Phys. 2007 Jun;34(6):2024-38. doi: 10.1118/1.2736289. Med Phys. 2007. PMID: 17654906 Free PMC article.
-
Dual system approach to computer-aided detection of breast masses on mammograms.Med Phys. 2006 Nov;33(11):4157-68. doi: 10.1118/1.2357838. Med Phys. 2006. PMID: 17153394 Free PMC article.
-
New technologies in screening for breast cancer: a systematic review of their accuracy.Br J Cancer. 2004 Jun 1;90(11):2118-22. doi: 10.1038/sj.bjc.6601836. Br J Cancer. 2004. PMID: 15150556 Free PMC article. Review.
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources
Other Literature Sources
Medical