Magnetic resonance imaging texture analysis classification of primary breast cancer.

Autor: Waugh SA; Department of Medical Physics, Ninewells Hospital and Medical School, Ninewells Avenue, Dundee, DD1 9SY, UK. shelley.waugh@nhs.net., Purdie CA; Department of Pathology, Ninewells Hospital and Medical School, Dundee, DD1 9SY, UK., Jordan LB; Department of Pathology, Ninewells Hospital and Medical School, Dundee, DD1 9SY, UK., Vinnicombe S; Division of Imaging and Technology, Ninewells Hospital and Medical School, University of Dundee, Dundee, DD1 9SY, UK., Lerski RA; Department of Medical Physics, Ninewells Hospital and Medical School, Ninewells Avenue, Dundee, DD1 9SY, UK., Martin P; Department of Clinical Radiology, Ninewells Hospital and Medical School, Dundee, DD1 9SY, UK., Thompson AM; Department of Surgical Oncology, University of Texas MD Anderson Cancer Center, 1400 Pressler Street, Houston, TX, 77030, USA.
Jazyk: angličtina
Zdroj: European radiology [Eur Radiol] 2016 Feb; Vol. 26 (2), pp. 322-30. Date of Electronic Publication: 2015 Jun 12.
DOI: 10.1007/s00330-015-3845-6
Abstrakt: Objectives: Patient-tailored treatments for breast cancer are based on histological and immunohistochemical (IHC) subtypes. Magnetic Resonance Imaging (MRI) texture analysis (TA) may be useful in non-invasive lesion subtype classification.
Methods: Women with newly diagnosed primary breast cancer underwent pre-treatment dynamic contrast-enhanced breast MRI. TA was performed using co-occurrence matrix (COM) features, by creating a model on retrospective training data, then prospectively applying to a test set. Analyses were blinded to breast pathology. Subtype classifications were performed using a cross-validated k-nearest-neighbour (k = 3) technique, with accuracy relative to pathology assessed and receiver operator curve (AUROC) calculated. Mann-Whitney U and Kruskal-Wallis tests were used to assess raw entropy feature values.
Results: Histological subtype classifications were similar across training (n = 148 cancers) and test sets (n = 73 lesions) using all COM features (training: 75%, AUROC = 0.816; test: 72.5%, AUROC = 0.823). Entropy features were significantly different between lobular and ductal cancers (p < 0.001; Mann-Whitney U). IHC classifications using COM features were also similar for training and test data (training: 57.2%, AUROC = 0.754; test: 57.0%, AUROC = 0.750). Hormone receptor positive and negative cancers demonstrated significantly different entropy features. Entropy features alone were unable to create a robust classification model.
Conclusion: Textural differences on contrast-enhanced MR images may reflect underlying lesion subtypes, which merits testing against treatment response.
Key Points: • MR-derived entropy features, representing heterogeneity, provide important information on tissue composition. • Entropy features can differentiate between histological and immunohistochemical subtypes of breast cancer. • Differing entropy features between breast cancer subtypes implies differences in lesion heterogeneity. • Texture analysis of breast cancer potentially provides added information for decision making.
Databáze: MEDLINE
Externí odkaz: