S A Waugh1, C A Purdie2, L B Jordan2, S Vinnicombe3, R A Lerski4, P Martin5, A M Thompson6. 1. Department of Medical Physics, Ninewells Hospital and Medical School, Ninewells Avenue, Dundee, DD1 9SY, UK. shelley.waugh@nhs.net. 2. Department of Pathology, Ninewells Hospital and Medical School, Dundee, DD1 9SY, UK. 3. Division of Imaging and Technology, Ninewells Hospital and Medical School, University of Dundee, Dundee, DD1 9SY, UK. 4. Department of Medical Physics, Ninewells Hospital and Medical School, Ninewells Avenue, Dundee, DD1 9SY, UK. 5. Department of Clinical Radiology, Ninewells Hospital and Medical School, Dundee, DD1 9SY, UK. 6. Department of Surgical Oncology, University of Texas MD Anderson Cancer Center, 1400 Pressler Street, Houston, TX, 77030, USA.
Abstract
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.
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.
Entities:
Keywords:
Breast cancer; Classification; Histological subtypes and immunohistochemical profiles; Magnetic Resonance Imaging (MRI); Texture analysis (TA)
Authors: Marius E Mayerhoefer; Pavol Szomolanyi; Daniel Jirak; Andrzej Materka; Siegfried Trattnig Journal: Med Phys Date: 2009-04 Impact factor: 4.071
Authors: S Sinha; F A Lucas-Quesada; N D DeBruhl; J Sayre; D Farria; D P Gorczyca; L W Bassett Journal: J Magn Reson Imaging Date: 1997 Nov-Dec Impact factor: 4.813
Authors: Elizabeth J Sutton; Brittany Z Dashevsky; Jung Hun Oh; Harini Veeraraghavan; Aditya P Apte; Sunitha B Thakur; Elizabeth A Morris; Joseph O Deasy Journal: J Magn Reson Imaging Date: 2016-01-12 Impact factor: 4.813
Authors: D Leithner; G J Wengert; T H Helbich; S Thakur; R E Ochoa-Albiztegui; E A Morris; K Pinker Journal: Clin Radiol Date: 2017-12-09 Impact factor: 2.350
Authors: Katja Pinker; Fuki Shitano; Evis Sala; Richard K Do; Robert J Young; Andreas G Wibmer; Hedvig Hricak; Elizabeth J Sutton; Elizabeth A Morris Journal: J Magn Reson Imaging Date: 2017-11-02 Impact factor: 4.813