Robustness of Radiomic Features of Benign Breast Lesions and Hormone Receptor Positive/HER2-negative Cancers Across DCE-MR Magnet Strengths

Overview

Journal Magn Reson Imaging

Publisher Elsevier

Specialty Radiology

Date 2021 Jun 26

PMID 34174331

Authors

Heather M Whitney

Karen Drukker

Alexandra Edwards

John Papaioannou

Milica Medved

Gregory Karczmar

Maryellen L Giger

Affiliations

Soon will be listed here.

Abstract

Radiomic features extracted from breast lesion images have shown potential in diagnosis and prognosis of breast cancer. As medical centers transition from 1.5 T to 3.0 T magnetic resonance (MR) imaging, it is beneficial to identify potentially robust radiomic features across field strengths because images acquired at different field strengths could be used in machine learning models. Dynamic contrast-enhanced MR images of benign breast lesions and hormone receptor positive/HER2-negative (HR+/HER2-) breast cancers were acquired retrospectively, yielding 612 unique cases: 150 and 99 benign lesions imaged at 1.5 T and 3.0 T, and 223 and 140 HR+/HER2- cancerous lesions imaged at 1.5 T and 3.0 T, respectively. In addition, an independent set of seven lesions imaged at both field strengths, three benign lesions and four HR+/HER2- cancers, was analyzed separately. Lesions were automatically segmented using a 4D fuzzy c-means method; thirty-eight radiomic features were extracted. Feature value distributions were compared by cancer status and imaging field strength using the Kolmogorov-Smirnov test. Features that did not demonstrate a statistically significant difference were considered to be potentially robust. The area under the receiver operating characteristic curve (AUC), for the task of classifying lesions as benign or HR+/HER2- cancer, was determined for each feature at each field strength. Three features were found to be both potentially robust across field strength and of high classification performance, i.e., AUCs statistically greater than 0.5 in the classification task: one shape feature (irregularity), one texture feature (sum average) and one enhancement variance kinetics features (enhancement variance increasing rate). In the demonstration set of lesions imaged at both field strengths, two of the three potentially robust features showed qualitative agreement across field strength. These findings may contribute to the development of computer-aided diagnosis models that are robust across field strength for this classification task.

References

Chen W, Giger M, Bick U, Newstead G . Automatic identification and classification of characteristic kinetic curves of breast lesions on DCE-MRI. Med Phys. 2006; 33(8):2878-87. DOI: 10.1118/1.2210568. View

Antropova N, Huynh B, Giger M . A deep feature fusion methodology for breast cancer diagnosis demonstrated on three imaging modality datasets. Med Phys. 2017; 44(10):5162-5171. PMC: 5646225. DOI: 10.1002/mp.12453. View

Shen Y, Goerner F, Snyder C, Morelli J, Hao D, Hu D . T1 relaxivities of gadolinium-based magnetic resonance contrast agents in human whole blood at 1.5, 3, and 7 T. Invest Radiol. 2015; 50(5):330-8. DOI: 10.1097/RLI.0000000000000132. View

Guggenbuhl P, Chappard D, Garreau M, Bansard J, Chales G, Rolland Y . Reproducibility of CT-based bone texture parameters of cancellous calf bone samples: influence of slice thickness. Eur J Radiol. 2007; 67(3):514-20. DOI: 10.1016/j.ejrad.2007.08.003. View

Fusco R, Sansone M, Filice S, Granata V, Catalano O, Amato D . Integration of DCE-MRI and DW-MRI Quantitative Parameters for Breast Lesion Classification. Biomed Res Int. 2015; 2015:237863. PMC: 4538369. DOI: 10.1155/2015/237863. View

Hu Q, Whitney H, Giger M . Radiomics methodology for breast cancer diagnosis using multiparametric magnetic resonance imaging. J Med Imaging (Bellingham). 2020; 7(4):044502. PMC: 7444714. DOI: 10.1117/1.JMI.7.4.044502. View

Metz C, Herman B, Shen J . Maximum likelihood estimation of receiver operating characteristic (ROC) curves from continuously-distributed data. Stat Med. 1998; 17(9):1033-53. DOI: 10.1002/(sici)1097-0258(19980515)17:9<1033::aid-sim784>3.0.co;2-z. View

Kousi E, Borri M, Dean J, Panek R, Scurr E, Leach M . Quality assurance in MRI breast screening: comparing signal-to-noise ratio in dynamic contrast-enhanced imaging protocols. Phys Med Biol. 2015; 61(1):37-49. PMC: 5390950. DOI: 10.1088/0031-9155/61/1/37. View

van Griethuysen J, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V . Computational Radiomics System to Decode the Radiographic Phenotype. Cancer Res. 2017; 77(21):e104-e107. PMC: 5672828. DOI: 10.1158/0008-5472.CAN-17-0339. View

10.

Pineda F, Medved M, Fan X, Ivancevic M, Abe H, Shimauchi A . Comparison of dynamic contrast-enhanced MRI parameters of breast lesions at 1.5 and 3.0 T: a pilot study. Br J Radiol. 2015; 88(1049):20150021. PMC: 4628483. DOI: 10.1259/bjr.20150021. View

11.

Jansen S, Shimauchi A, Zak L, Fan X, Wood A, Karczmar G . Kinetic curves of malignant lesions are not consistent across MRI systems: need for improved standardization of breast dynamic contrast-enhanced MRI acquisition. AJR Am J Roentgenol. 2009; 193(3):832-9. PMC: 2938789. DOI: 10.2214/AJR.08.2025. View

12.

Chen W, Giger M, Bick U . A fuzzy c-means (FCM)-based approach for computerized segmentation of breast lesions in dynamic contrast-enhanced MR images. Acad Radiol. 2006; 13(1):63-72. DOI: 10.1016/j.acra.2005.08.035. View

13.

Dietrich O, Reiser M, Schoenberg S . Artifacts in 3-T MRI: physical background and reduction strategies. Eur J Radiol. 2007; 65(1):29-35. DOI: 10.1016/j.ejrad.2007.11.005. View

14.

Savio S, Harrison L, Luukkaala T, Heinonen T, Dastidar P, Soimakallio S . Effect of slice thickness on brain magnetic resonance image texture analysis. Biomed Eng Online. 2010; 9:60. PMC: 2970603. DOI: 10.1186/1475-925X-9-60. View

15.

Whitney H, Taylor N, Drukker K, Edwards A, Papaioannou J, Schacht D . Additive Benefit of Radiomics Over Size Alone in the Distinction Between Benign Lesions and Luminal A Cancers on a Large Clinical Breast MRI Dataset. Acad Radiol. 2018; 26(2):202-209. PMC: 9392156. DOI: 10.1016/j.acra.2018.04.019. View

16.

Whitney H, Drukker K, Edwards A, Papaioannou J, Giger M . Effect of biopsy on the MRI radiomics classification of benign lesions and luminal A cancers. J Med Imaging (Bellingham). 2022; 6(3):031408. PMC: 6378704. DOI: 10.1117/1.JMI.6.3.031408. View

17.

Kuhl C, Jost P, Morakkabati N, Zivanovic O, Schild H, Gieseke J . Contrast-enhanced MR imaging of the breast at 3.0 and 1.5 T in the same patients: initial experience. Radiology. 2006; 239(3):666-76. DOI: 10.1148/radiol.2392050509. View

18.

Leithner D, Horvat J, Marino M, Bernard-Davila B, Jochelson M, Ochoa-Albiztegui R . Radiomic signatures with contrast-enhanced magnetic resonance imaging for the assessment of breast cancer receptor status and molecular subtypes: initial results. Breast Cancer Res. 2019; 21(1):106. PMC: 6739929. DOI: 10.1186/s13058-019-1187-z. View

19.

Vymazal J, Brooks R, Zak O, McRill C, Shen C, DI CHIRO G . T1 and T2 of ferritin at different field strengths: effect on MRI. Magn Reson Med. 1992; 27(2):368-74. DOI: 10.1002/mrm.1910270218. View

20.

Vovk U, Pernus F, Likar B . A review of methods for correction of intensity inhomogeneity in MRI. IEEE Trans Med Imaging. 2007; 26(3):405-21. DOI: 10.1109/TMI.2006.891486. View