PURPOSE: This work is to provide a direct, quantitative comparison of image features measured by film and full-field digital mammography (FFDM). The purpose is to investigate whether there is any systematic difference between film and FFDM in terms of quantitative image features and their influence on the performance of a computer-aided diagnosis (CAD) system. METHODS: The authors make use of a set of matched film-FFDM image pairs acquired from cadaver breast specimens with simulated microcalcifications consisting of bone and teeth fragments using both a GE digital mammography system and a screen-film system. To quantify the image features, the authors consider a set of 12 textural features of lesion regions and six image features of individual microcalcifications (MCs). The authors first conduct a direct comparison on these quantitative features extracted from film and FFDM images. The authors then study the performance of a CAD classifier for discriminating between MCs and false positives (FPs) when the classifier is trained on images of different types (film, FFDM, or both). RESULTS: For all the features considered, the quantitative results show a high degree of correlation between features extracted from film and FFDM, with the correlation coefficients ranging from 0.7326 to 0.9602 for the different features. Based on a Fisher sign rank test, there was no significant difference observed between the features extracted from film and those from FFDM. For both MC detection and discrimination of FPs from MCs, FFDM had a slight but statistically significant advantage in performance; however, when the classifiers were trained on different types of images (acquired with FFDM or SFM) for discriminating MCs from FPs, there was little difference. CONCLUSIONS: The results indicate good agreement between film and FFDM in quantitative image features. While FFDM images provide better detection performance in MCs, FFDM and film images may be interchangeable for the purposes of training CAD algorithms, and a single CAD algorithm may be applied to either type of images.
PURPOSE: This work is to provide a direct, quantitative comparison of image features measured by film and full-field digital mammography (FFDM). The purpose is to investigate whether there is any systematic difference between film and FFDM in terms of quantitative image features and their influence on the performance of a computer-aided diagnosis (CAD) system. METHODS: The authors make use of a set of matched film-FFDM image pairs acquired from cadaver breast specimens with simulated microcalcifications consisting of bone and teeth fragments using both a GE digital mammography system and a screen-film system. To quantify the image features, the authors consider a set of 12 textural features of lesion regions and six image features of individual microcalcifications (MCs). The authors first conduct a direct comparison on these quantitative features extracted from film and FFDM images. The authors then study the performance of a CAD classifier for discriminating between MCs and false positives (FPs) when the classifier is trained on images of different types (film, FFDM, or both). RESULTS: For all the features considered, the quantitative results show a high degree of correlation between features extracted from film and FFDM, with the correlation coefficients ranging from 0.7326 to 0.9602 for the different features. Based on a Fisher sign rank test, there was no significant difference observed between the features extracted from film and those from FFDM. For both MC detection and discrimination of FPs from MCs, FFDM had a slight but statistically significant advantage in performance; however, when the classifiers were trained on different types of images (acquired with FFDM or SFM) for discriminating MCs from FPs, there was little difference. CONCLUSIONS: The results indicate good agreement between film and FFDM in quantitative image features. While FFDM images provide better detection performance in MCs, FFDM and film images may be interchangeable for the purposes of training CAD algorithms, and a single CAD algorithm may be applied to either type of images.
Authors: S Suryanarayanan; A Karellas; S Vedantham; S J Glick; C J D'Orsi; S P Baker; R L Webber Journal: Acad Radiol Date: 2000-12 Impact factor: 3.173
Authors: John A Shepherd; Karla M Kerlikowske; Rebecca Smith-Bindman; Harry K Genant; Steve R Cummings Journal: Radiology Date: 2002-05 Impact factor: 11.105
Authors: Wei T Yang; Chao-Jen Lai; Gary J Whitman; William A Murphy; Mark J Dryden; Anne C Kushwaha; Aysegul A Sahin; Dennis Johnston; Peter J Dempsey; Chris C Shaw Journal: AJR Am J Roentgenol Date: 2006-12 Impact factor: 3.959
Authors: Lothar Häberle; Florian Wagner; Peter A Fasching; Sebastian M Jud; Katharina Heusinger; Christian R Loehberg; Alexander Hein; Christian M Bayer; Carolin C Hack; Michael P Lux; Katja Binder; Matthias Elter; Christian Münzenmayer; Rüdiger Schulz-Wendtland; Martina Meier-Meitinger; Boris R Adamietz; Michael Uder; Matthias W Beckmann; Thomas Wittenberg Journal: Breast Cancer Res Date: 2012-04-10 Impact factor: 6.466
Authors: Serghei Malkov; John A Shepherd; Christopher G Scott; Rulla M Tamimi; Lin Ma; Kimberly A Bertrand; Fergus Couch; Matthew R Jensen; Amir P Mahmoudzadeh; Bo Fan; Aaron Norman; Kathleen R Brandt; V Shane Pankratz; Celine M Vachon; Karla Kerlikowske Journal: Breast Cancer Res Date: 2016-12-06 Impact factor: 6.466
Authors: Jacky D Luiten; Ernest J T Luiten; Maurice J C van der Sangen; Willem Vreuls; Lucien E M Duijm; Vivianne C G Tjan-Heijnen; Adri C Voogd Journal: Breast Cancer Res Treat Date: 2021-01-01 Impact factor: 4.872