Radiomics Analysis on Ultrasound for Prediction of Biologic Behavior in Breast Invasive Ductal Carcinoma

• Published in: Clinical breast cancer 2018-06, Vol.18 (3), p.e335-e344
• Main Authors: Guo, Yi, Hu, Yuzhou, Qiao, Mengyun, Wang, Yuanyuan, Yu, Jinhua, Li, Jiawei, Chang, Cai
• Format: Article
• Language: English
• Subjects: Adult; Biopsy; Breast - diagnostic imaging; Breast - pathology; Breast - surgery; Breast IDC; Breast Neoplasms - diagnostic imaging; Breast Neoplasms - pathology; Breast Neoplasms - surgery; Carcinoma, Ductal, Breast - diagnostic imaging; Carcinoma, Ductal, Breast - pathology; Carcinoma, Ductal, Breast - surgery; Feasibility Studies; Female; High-throughput features; Hormone receptor; Humans; Image Processing, Computer-Assisted - methods; Middle Aged; Molecular subtypes; Neoplasm Grading; Prognosis; Receptor, ErbB-2 - metabolism; Receptors, Estrogen - metabolism; Receptors, Progesterone - metabolism; Retrospective Studies; Support Vector Machine; Ultrasonography; Ultrasonography, Mammary - methods
• ISSN: 1526-8209; 1938-0666
• DOI: 10.1016/j.clbc.2017.08.002

This study illustrates that tumor characteristics can be captured by medical images at the genetic and cellular levels. The data from 215 patients with breast invasive ductal carcinoma were analyzed. An automatic radiomics approach was proposed to assess the associations between quantitative ultrasound features and biologic characteristics. The results indicated a strong correlation. This application will be helpful for an accurate prognosis at an early stage. In current clinical practice, invasive ductal carcinoma is always screened using medical imaging techniques and diagnosed using immunohistochemistry. Recent studies have illustrated that radiomics approaches provide a comprehensive characterization of entire tumors and can reveal predictive or prognostic associations between the images and medical outcomes. To better reveal the underlying biology, an improved understanding between objective image features and biologic characteristics is urgently required. A total of 215 patients with definite histologic results were enrolled in our study. The tumors were automatically segmented using our phase-based active contour model. The high-throughput radiomics features were designed and extracted using a breast imaging reporting and data system and further selected using Student's t test, interfeature coefficients and a lasso regression model. The support vector machine classifier with threefold cross-validation was used to evaluate the relationship. The radiomics approach demonstrated a strong correlation between receptor status and subtypes (P < .05; area under the curve, 0.760). The appearance of hormone receptor-positive cancer and human epidermal growth factor receptor 2–negative cancer on ultrasound scans differs from that of triple-negative cancer. Our approach could assist clinicians with the accurate prediction of prognosis using ultrasound findings, allowing for early medical management and treatment.