Abstract
Breast cancer is molecularly heterogeneous and categorized into four molecular subtypes: Luminal-A, Luminal-B, HER2-amplified and Triple-negative. In this study, we aimed to apply an ensemble decision approach to identify the ultrasound and clinical features related to the molecular subtypes. We collected ultrasound and clinical features from 1,000 breast cancer patients and performed immunohistochemistry on these samples. We used the ensemble decision approach to select unique features and to construct decision models. The decision model for Luminal-A subtype was constructed based on the presence of an echogenic halo and post-acoustic shadowing or indifference. The decision model for Luminal-B subtype was constructed based on the absence of an echogenic halo and vascularity. The decision model for HER2-amplified subtype was constructed based on the presence of post-acoustic enhancement, calcification, vascularity and advanced age. The model for Triple-negative subtype followed two rules. One was based on irregular shape, lobulate margin contour, the absence of calcification and hypovascularity, whereas the other was based on oval shape, hypovascularity and micro-lobulate margin contour. The accuracies of the models were 83.8%, 77.4%, 87.9% and 92.7%, respectively. We identified specific features of each molecular subtype and expanded the scope of ultrasound for making diagnoses using these decision models.
Highlights
Ultrasound, with its high level of safety and low cost, is becoming the preferred method for both physicians and patients
Irshad et al found that posterior shadowing is strongly associated with Estrogen Receptor-positive (ER+ ) and low-grade tumours, whereas posterior enhancement is strongly associated with high-grade tumours and a moderate risk of being receptor negativity[9]
We propose the ensemble decision approach that integrated multiple decision trees based on an ensemble decision theory to select the special features of each subtype[13]
Summary
Ultrasound, with its high level of safety and low cost, is becoming the preferred method for both physicians and patients. Reports have indicated that improvements in ultrasound technologies might make it possible to highly sensitively differentiate malignant solid breast masses from benign ones based on their different ultrasound features[8]. To accurately detect the different features of breast cancer molecular subtypes, efficient statistical methods and computational algorithms for analysing the massive amount of clinical data available need to be developed. We obtained multiple feature sets from the training sets by a resampling technique, and integrated the multiple feature sets to produce a combination of features of each subtype by the ensemble decision approach. We constructed the models and obtained high accuracy with the models, and considered that the ensemble decision approach might have significant utility for ultrasound diagnosis of breast cancer in the future
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call