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.
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.
Authors: Georgia Vasileiou; Maria J Costa; Christopher Long; Iris R Wetzler; Juliane Hoyer; Cornelia Kraus; Bernt Popp; Julius Emons; Marius Wunderle; Evelyn Wenkel; Michael Uder; Matthias W Beckmann; Sebastian M Jud; Peter A Fasching; Alexander Cavallaro; André Reis; Matthias Hammon Journal: BMC Med Imaging Date: 2020-07-29 Impact factor: 1.930
Authors: Ashley M Mendez; Lauren K Fang; Claire H Meriwether; Summer J Batasin; Stéphane Loubrie; Ana E Rodríguez-Soto; Rebecca A Rakow-Penner Journal: Front Oncol Date: 2022-07-08 Impact factor: 5.738
Authors: Doris Leithner; Marius E Mayerhoefer; Danny F Martinez; Maxine S Jochelson; Elizabeth A Morris; Sunitha B Thakur; Katja Pinker Journal: J Clin Med Date: 2020-06-14 Impact factor: 4.241