Title: Novel approaches for the microcalcification problem of non-palpable lesions

Authors: Walker H. Land Jr., Elizabeth A. Verheggen

Addresses: Department of Bioengineering, Binghamton University, Binghamton, NY 13903-6000, USA. ' Department of Systems Science, Binghamton University, Binghamton, NY 13903-6000, USA

Abstract: Fusion of hard and soft information using correlation pattern recognition and fuzzy logic in an integrated detection/classification system based on the DDSM database of pleomorphic microcalcifications provides a detection rate of 0.47 false positives per image at 100% sensitivity using classical matched filter methods on wavelet denoised full mammograms. Advanced correlation filtering yields 0.85 and 0.58 false positives per image at 100% and 87% sensitivity. Classification results generalisable to unseen images at 71.4% specificity for 100% and 96% sensitivity are in a range likely to be clinically acceptable, based on human vision performance of 73.3% specificity at 97.6% sensitivity.

Keywords: lacunarity; fractal abundance; CPR; correlation pattern recognition; correlation plane; fuzzy logic; pleomorphic microcalcification; CADe/CADx; computer aided detection; computer aided diagnosis; mammograms; false positives; classification; non-palpable lesions.

DOI: 10.1504/IJFIPM.2009.022835

International Journal of Functional Informatics and Personalised Medicine, 2009 Vol.2 No.1, pp.1 - 44

Available online: 27 Jan 2009 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article