Takayoshi Uematsu1. 1. Department of Breast Imaging and Breast Intervention, Breast Center and Department of Clinical Physiology, Shizuoka Cancer Center Hospital, Naga-Izumi, Shizuoka, 411-8777, Japan. t.uematsu@scchr.jp
Abstract
PURPOSE: The purpose of this study was to determine the effects of a commercially available postprocessing algorithm on the detection of masses and microcalcifications of breast cancer by soft-copy reading. MATERIALS AND METHODS: The study included 64 digital mammograms with 16 histologically proven abnormal findings (eight masses and eight microcalcifications) and 48 normal breasts. Two image-processing algorithms were applied to the digital images, which were acquired using General Electric units. The commercially available advanced and standard postprocessed digital mammograms were evaluated in a localization receiver operating characteristic (ROC) curve experiment involving seven mammography radiographers. RESULTS: The mean area under the ROC curve was 0.921 +/- 0.022 for the commercially available advanced postprocessed digital mammograms session and 0.904 +/- 0.026 for the standard postprocessed digital mammograms session (P = 0.1953). Observer agreement among the readers was better for the advanced postprocessed digital mammograms than for the standard postprocessed digital mammograms. CONCLUSION: During soft-copy reading, the interpretation accuracy might be influenced by the postprocessing algorithm.
PURPOSE: The purpose of this study was to determine the effects of a commercially available postprocessing algorithm on the detection of masses and microcalcifications of breast cancer by soft-copy reading. MATERIALS AND METHODS: The study included 64 digital mammograms with 16 histologically proven abnormal findings (eight masses and eight microcalcifications) and 48 normal breasts. Two image-processing algorithms were applied to the digital images, which were acquired using General Electric units. The commercially available advanced and standard postprocessed digital mammograms were evaluated in a localization receiver operating characteristic (ROC) curve experiment involving seven mammography radiographers. RESULTS: The mean area under the ROC curve was 0.921 +/- 0.022 for the commercially available advanced postprocessed digital mammograms session and 0.904 +/- 0.026 for the standard postprocessed digital mammograms session (P = 0.1953). Observer agreement among the readers was better for the advanced postprocessed digital mammograms than for the standard postprocessed digital mammograms. CONCLUSION: During soft-copy reading, the interpretation accuracy might be influenced by the postprocessing algorithm.
Authors: Etta D Pisano; Elodia B Cole; Emily O Kistner; Keith E Muller; Bradley M Hemminger; Mary L Brown; R Eugene Johnston; Cherie M Kuzmiak; M Patricia Braeuning; Rita I Freimanis; Mary Scott Soo; J A Baker; Ruth Walsh Journal: Radiology Date: 2002-05 Impact factor: 11.105
Authors: J M Lewin; R E Hendrick; C J D'Orsi; P K Isaacs; L J Moss; A Karellas; G A Sisney; C C Kuni; G R Cutter Journal: Radiology Date: 2001-03 Impact factor: 11.105
Authors: Etta D Pisano; Constantine Gatsonis; Edward Hendrick; Martin Yaffe; Janet K Baum; Suddhasatta Acharyya; Emily F Conant; Laurie L Fajardo; Lawrence Bassett; Carl D'Orsi; Roberta Jong; Murray Rebner Journal: N Engl J Med Date: 2005-09-16 Impact factor: 91.245
Authors: John M Lewin; Carl J D'Orsi; R Edward Hendrick; Lawrence J Moss; Pamela K Isaacs; Andrew Karellas; Gary R Cutter Journal: AJR Am J Roentgenol Date: 2002-09 Impact factor: 3.959
Authors: Lucy M Warren; Alistair Mackenzie; Julie Cooke; Rosalind M Given-Wilson; Matthew G Wallis; Dev P Chakraborty; David R Dance; Hilde Bosmans; Kenneth C Young Journal: Med Phys Date: 2012-06 Impact factor: 4.071
Authors: Su Min Ha; Hak Hee Kim; Eunhee Kang; Bo Kyoung Seo; Nami Choi; Tae Hee Kim; You Jin Ku; Jong Chul Ye Journal: Taehan Yongsang Uihakhoe Chi Date: 2021-12-11