Immunohistochemical index prediction of breast tumor based on multi-dimension features in contrast-enhanced ultrasound

Breast cancer is the leading killer of Chinese women. Immunohistochemistry index has great significance in the treatment strategy selection and prognosis analysis for breast cancer patients. Currently, histopathological examination of the tumor tissue through surgical biopsy is the gold standard to determine immunohistochemistry index. However, this examination is invasive and commonly causes discomfort in patients. There has been a lack of noninvasive method capable of predicting immunohistochemistry index for breast cancer patients. This paper proposes a machine learning method to predict the immunohistochemical index of breast cancer patients by using noninvasive contrast-enhanced ultrasound. A total of 119 breast cancer patients were included in this retrospective study. Each patient implemented the pathological examination of immunohistochemical expression and underwent contrast-enhanced ultrasound imaging of breast tumor. The multi-dimension features including 266 three-dimension features and 837 two-dimension dynamic features were extracted from the contrast-enhanced ultrasound sequences. Using the machine learning prediction method, 21 selected multi-dimension features were integrated to generate a model for predicting the immunohistochemistry index noninvasively. The immunohistochemical index of human epidermal growth factor receptor-2 (HER2) was predicted based on multi-dimension features in contrast-enhanced ultrasound sequence with the sensitivity of 71%, and the specificity of 79% in the testing cohort. Therefore, the noninvasive contrast-enhanced ultrasound can be used to predict the immunohistochemical index. To our best knowledge, no studies have been reported about predicting immunohistochemical index by using contrast-enhanced ultrasound sequences for breast cancer patients. Our proposed method is noninvasive and can predict immunohistochemical index by using contrast-enhanced ultrasound in several minutes, instead of relying totally on the invasive and biopsy-based histopathological examination. Graphical abstract Immunohistochemical index prediction of breast tumor based on multi-dimension features in contrast-enhanced ultrasound.

[1]  A. Makris,et al.  Evaluation of ER, PgR, HER-2 and Ki-67 as predictors of response to neoadjuvant anthracycline chemotherapy for operable breast cancer , 2004, British Journal of Cancer.

[2]  Chung-Han Lee,et al.  Mammography and ultrasound features of triple-negative breast cancer , 2011 .

[3]  Yutaka Satoh,et al.  Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet? , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[4]  Corinne Balleyguier,et al.  New potential and applications of contrast-enhanced ultrasound of the breast: Own investigations and review of the literature. , 2009, European journal of radiology.

[5]  Guofu Huang,et al.  Role of multi-mode ultrasound in the diagnosis of level 4 BI-RADS breast lesions and Logistic regression model. , 2015, International journal of clinical and experimental medicine.

[6]  A. Pelayo,et al.  Immunohistochemical prognostic index for breast cancer in young women , 2003, Molecular pathology : MP.

[7]  M. Burkard,et al.  Adjuvant therapy for HER2+ breast cancer: practice, perception, and toxicity , 2011, Breast Cancer Research and Treatment.

[8]  Q. Hu,et al.  Meta-analysis of contrast-enhanced ultrasound for the differentiation of benign and malignant breast lesions , 2015, Acta radiologica.

[9]  E. Pisano,et al.  Assessing the role of ultrasound in predicting the biological behavior of breast cancer. , 2013, AJR. American journal of roentgenology.

[10]  Fabian Kiessling,et al.  Radiomic analysis of contrast-enhanced ultrasound data , 2018, Scientific Reports.

[11]  M. Andersson,et al.  HER2-targeted therapy in breast cancer. Monoclonal antibodies and tyrosine kinase inhibitors. , 2009, Cancer treatment reviews.

[12]  G. Hortobagyi,et al.  Prognostic significance of HER‐2 status in women with inflammatory breast cancer , 2008, Cancer.

[13]  I. Ellis,et al.  An overview of assessment of prognostic and predictive factors in breast cancer needle core biopsy specimens , 2006, Journal of Clinical Pathology.

[14]  N. Klauber-DeMore,et al.  Tumor biology of breast cancer in young women. , 2005, Breast disease.

[15]  B. Luo,et al.  Diagnosis of sub-centimetre breast lesions: combining BI-RADS-US with strain elastography and contrast-enhanced ultrasound—a preliminary study in China , 2017, European Radiology.

[16]  Eun Sook Ko,et al.  Triple-negative breast cancer: correlation between imaging and pathological findings , 2010, European Radiology.

[17]  S. Simm,et al.  Recurrence and therapeutic problems in cervical dysplasia and in situ cancer , 1963, Cancer.

[18]  The Clinical Significance of Real-Time Contrast-Enhanced Ultrasonography in the Differential Diagnosis of Breast Tumor , 2012, Cell Biochemistry and Biophysics.

[19]  R. Gelber,et al.  Prognostic significance of tumor grade in clinical trials of adjuvant therapy for breast cancer with axillary lymph node metastasis , 1986, Cancer.

[20]  Barbara L. Smith,et al.  Breast cancer subtype approximated by estrogen receptor, progesterone receptor, and HER-2 is associated with local and distant recurrence after breast-conserving therapy. , 2008, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[21]  Fabian Kiessling,et al.  Semi-Automated Segmentation of the Tumor Vasculature in Contrast-Enhanced Ultrasound Data. , 2018, Ultrasound in medicine & biology.

[22]  I. O. Ellis,et al.  Sonographic correlations with the new molecular classification of invasive breast cancer , 2009, European Radiology.

[23]  M. Helvie,et al.  Triple receptor-negative breast cancer: imaging and clinical characteristics. , 2012, AJR. American journal of roentgenology.

[24]  E. Tokunaga,et al.  Trastuzumab and breast cancer: developments and current status , 2006, International Journal of Clinical Oncology.

[25]  K. Kamei,et al.  Investigation of contrast-enhanced ultrasound findings for the differential diagnosis of small breast lesions , 2019, Ultrasound in Medicine & Biology.

[26]  S. Takekoshi,et al.  Estrogen receptor-negative and human epidermal growth factor receptor 2-negative breast cancer tissue have the highest Ki-67 labeling index and EGFR expression: gene amplification does not contribute to EGFR expression. , 2005, Oncology reports.

[27]  T. Wong,et al.  AI for medical imaging goes deep , 2018, Nature Medicine.

[28]  Funda Meric-Bernstam,et al.  High risk of recurrence for patients with breast cancer who have human epidermal growth factor receptor 2-positive, node-negative tumors 1 cm or smaller. , 2009, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[29]  P. Lambin,et al.  Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach , 2014, Nature Communications.

[30]  Lajos Pusztai,et al.  Targeted Therapy in Breast Cancer , 2004, Molecular & Cellular Proteomics.

[31]  D. Hicks,et al.  HER2+ breast cancer: review of biologic relevance and optimal use of diagnostic tools. , 2008, American journal of clinical pathology.

[32]  R. Ma,et al.  Qualitative, quantitative and combination score systems in differential diagnosis of breast lesions by contrast-enhanced ultrasound. , 2016, European journal of radiology.

[33]  J. Baselga,et al.  How to treat hormone receptor-positive, human epidermal growth factor receptor 2-amplified breast cancer. , 2009, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[34]  S. Modi,et al.  HER2 breast cancer therapies: a review , 2009, Biologics : targets & therapy.

[35]  Henry Zhu,et al.  Diagnostic Value of Contrast-Enhanced Ultrasound Parametric Imaging in Breast Tumors , 2013, Journal of Breast Cancer.

[36]  Mingkui Li,et al.  Values of contrast-enhanced ultrasound combined with BI-RADS in differentiating benign and malignant breast lesions , 2018 .

[37]  I. Ellis,et al.  Preoperative assessment of prognostic factors in breast cancer , 2001, Journal of clinical pathology.

[38]  Zhiyuan Wang,et al.  Tumor size of breast invasive ductal cancer measured with contrast-enhanced ultrasound predicts regional lymph node metastasis and N stage. , 2014, International journal of clinical and experimental pathology.

[39]  Ying Wang,et al.  Identifying ultrasound and clinical features of breast cancer molecular subtypes by ensemble decision , 2015, Scientific Reports.

[40]  B. Szabó,et al.  Differentiation between benign and malignant breast tumors using kinetic features of real-time harmonic contrast-enhanced ultrasound , 2012, Acta radiologica.

[41]  H. Tsunoda,et al.  Mammography and ultrasound features of triple-negative breast cancer , 2011, Breast cancer.