Heather M Whitney1, Nathan S Taylor2, Karen Drukker3, Alexandra V Edwards3, John Papaioannou3, David Schacht3, Maryellen L Giger4. 1. Department of Radiology, The University of Chicago, 5841 S. Maryland Avenue, MC 2026 Chicago, IL 60637; Department of Physics, Wheaton College, 501 College Avenue, Wheaton, IL 60187. Electronic address: hwhitney@uchicago.edu. 2. Department of Physics, Wheaton College, 501 College Avenue, Wheaton, IL 60187. 3. Department of Radiology, The University of Chicago, 5841 S. Maryland Avenue, MC 2026 Chicago, IL 60637. 4. Department of Radiology, The University of Chicago, 5841 S. Maryland Avenue, MC 2026 Chicago, IL 60637. Electronic address: m-giger@uchicago.edu.
Abstract
RATIONALE AND OBJECTIVES: The objective of this study was to demonstrate improvement in distinguishing between benign lesions and luminal A breast cancers in a large clinical breast magnetic resonance imaging database by using quantitative radiomics over maximum linear size alone. MATERIALS AND METHODS: In this retrospective study, 264 benign lesions and 390 luminal A breast cancers were automatically segmented from dynamic contrast-enhanced breast magnetic resonance images. Thirty-eight radiomic features were extracted. Tenfold cross validation was performed to assess the ability to distinguish between lesions and cancers using maximum linear size alone and lesion signatures obtained with stepwise feature selection and a linear discriminant analysis classifier including and excluding size features. Area under the receiver operating characteristic curve (AUC) was used as the figure of merit. RESULTS: For maximum linear size alone, AUC and 95% confidence interval was 0.684 (0.642, 0.724) compared to 0.728 (0.687, 0.766) (P = 0.005) and 0.729 (0.689, 0.767) (P = 0.005) for lesion signature feature selection protocols including and excluding size features, respectively. The features of irregularity and entropy were chosen in all folds when size features were included and excluded. AUC for the radiomic signature using feature selection from all features was statistically equivalent to using feature selection from all features excluding size features, within an equivalence margin of 2%. CONCLUSIONS: Inclusion of multiple radiomic features, automatically extracted from magnetic resonance images, in a lesion signature significantly improved the ability to distinguish between benign lesions and luminal A breast cancers, compared to using maximum linear size alone. The radiomic features of irregularity and entropy appear to play an important but not a solitary role within the context of feature selection and computer-aided diagnosis.
RATIONALE AND OBJECTIVES: The objective of this study was to demonstrate improvement in distinguishing between benign lesions and luminal A breast cancers in a large clinical breast magnetic resonance imaging database by using quantitative radiomics over maximum linear size alone. MATERIALS AND METHODS: In this retrospective study, 264 benign lesions and 390 luminal A breast cancers were automatically segmented from dynamic contrast-enhanced breast magnetic resonance images. Thirty-eight radiomic features were extracted. Tenfold cross validation was performed to assess the ability to distinguish between lesions and cancers using maximum linear size alone and lesion signatures obtained with stepwise feature selection and a linear discriminant analysis classifier including and excluding size features. Area under the receiver operating characteristic curve (AUC) was used as the figure of merit. RESULTS: For maximum linear size alone, AUC and 95% confidence interval was 0.684 (0.642, 0.724) compared to 0.728 (0.687, 0.766) (P = 0.005) and 0.729 (0.689, 0.767) (P = 0.005) for lesion signature feature selection protocols including and excluding size features, respectively. The features of irregularity and entropy were chosen in all folds when size features were included and excluded. AUC for the radiomic signature using feature selection from all features was statistically equivalent to using feature selection from all features excluding size features, within an equivalence margin of 2%. CONCLUSIONS: Inclusion of multiple radiomic features, automatically extracted from magnetic resonance images, in a lesion signature significantly improved the ability to distinguish between benign lesions and luminal A breast cancers, compared to using maximum linear size alone. The radiomic features of irregularity and entropy appear to play an important but not a solitary role within the context of feature selection and computer-aided diagnosis.
Authors: Sebastian Bickelhaupt; Daniel Paech; Philipp Kickingereder; Franziska Steudle; Wolfgang Lederer; Heidi Daniel; Michael Götz; Nils Gählert; Diana Tichy; Manuel Wiesenfarth; Frederik B Laun; Klaus H Maier-Hein; Heinz-Peter Schlemmer; David Bonekamp Journal: J Magn Reson Imaging Date: 2017-02-02 Impact factor: 4.813
Authors: Elizabeth S Burnside; Karen Drukker; Hui Li; Ermelinda Bonaccio; Margarita Zuley; Marie Ganott; Jose M Net; Elizabeth J Sutton; Kathleen R Brandt; Gary J Whitman; Suzanne D Conzen; Li Lan; Yuan Ji; Yitan Zhu; Carl C Jaffe; Erich P Huang; John B Freymann; Justin S Kirby; Elizabeth A Morris; Maryellen L Giger Journal: Cancer Date: 2015-11-30 Impact factor: 6.860
Authors: Hui Li; Yitan Zhu; Elizabeth S Burnside; Erich Huang; Karen Drukker; Katherine A Hoadley; Cheng Fan; Suzanne D Conzen; Margarita Zuley; Jose M Net; Elizabeth Sutton; Gary J Whitman; Elizabeth Morris; Charles M Perou; Yuan Ji; Maryellen L Giger Journal: NPJ Breast Cancer Date: 2016-05-11
Authors: William Rogers; Sithin Thulasi Seetha; Turkey A G Refaee; Relinde I Y Lieverse; Renée W Y Granzier; Abdalla Ibrahim; Simon A Keek; Sebastian Sanduleanu; Sergey P Primakov; Manon P L Beuque; Damiënne Marcus; Alexander M A van der Wiel; Fadila Zerka; Cary J G Oberije; Janita E van Timmeren; Henry C Woodruff; Philippe Lambin Journal: Br J Radiol Date: 2020-02-26 Impact factor: 3.039