Preliminary Study on Molecular Subtypes of Breast Cancer Based on Magnetic Resonance Imaging Texture Analysis.
J Comput Assist Tomogr 2018;
42:531-535. [PMID:
29659431 DOI:
10.1097/rct.0000000000000738]
[Citation(s) in RCA: 18] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/31/2022]
Abstract
OBJECTIVE
The aim of the study was to investigate the molecular subtypes of breast cancer based on the texture features derived from magnetic resonance images (MRIs).
METHODS
One hundred seven patients with preoperative confirmed breast cancer were recruited. One hundred eight breast lesions were divided into 4 subtypes according to the status of estrogen receptor, progesterone receptor, human epidermal growth factor receptor type 2, and Ki67. Fisher discriminant analysis was performed on the texture features that extracted from the enhanced high-resolution T1-weighted images and diffusion weighted images to establish the classification model of molecular subtypes.
RESULTS
The differentiation accuracies of Fisher discriminant analysis on the enhanced high-resolution T1-weighted images were 82.8% and 86.4% for 1.5T and 3.0T imaging. Fisher discriminant analysis on diffusion weighted imaging texture features were achieved with a classification ability of 73.4% and 88.6%. The combined discriminant results for 2 kinds magnetic resonance images were 95.0%, 97.7% in 1.5T and 3.0T imaging, respectively.
CONCLUSIONS
The fine results indicated a promising approach to predict the molecular subtypes of breast cancer.
Collapse