Predicting Response to Neoadjuvant Chemotherapy in Patients With Breast Cancer: Combined Statistical Modeling Using Clinicopathological Factors and FDG PET/CT Texture Parameters

Purpose The aim of this study was to develop a combined statistical model using both clinicopathological factors and texture parameters from 18F-FDG PET/CT to predict responses to neoadjuvant chemotherapy in patients with breast cancer. Materials and Methods A total of 435 patients with breast cancer were retrospectively enrolled. Clinical and pathological data were obtained from electronic medical records. Texture parameters were extracted from pretreatment FDG PET/CT images. The end point was pathological complete response, defined as the absence of residual disease or the presence of residual ductal carcinoma in situ without residual lymph node metastasis. Multivariable logistic regression modeling was performed using clinicopathological factors and texture parameters as covariates. Results In the multivariable logistic regression model, various factors and parameters, including HER2, histological grade or Ki-67, gradient skewness, gradient kurtosis, contrast, difference variance, angular second moment, and inverse difference moment, were selected as significant prognostic variables. The predictive power of the multivariable logistic regression model incorporating both clinicopathological factors and texture parameters was significantly higher than that of a model with only clinicopathological factors (P = 0.0067). In subgroup analysis, texture parameters, including gradient skewness and gradient kurtosis, were selected as independent prognostic factors in the HER2-negative group. Conclusions A combined statistical model was successfully generated using both clinicopathological factors and texture parameters to predict the response to neoadjuvant chemotherapy. Results suggest that addition of texture parameters from FDG PET/CT can provide more information regarding treatment response prediction compared with clinicopathological factors alone.

[1]  Daniel Birnbaum,et al.  A gene expression signature identifies two prognostic subgroups of basal breast cancer , 2011, Breast Cancer Research and Treatment.

[2]  D. Berry.  Chemotherapy is More Effective in Patients With Breast Cancer Not Expressing Steroid Hormone Receptors: A Study of Preoperative Treatment , 2006 .

[3]  F. Collins,et al.  A new initiative on precision medicine. , 2015, The New England journal of medicine.

[4]  L. Turnbull,et al.  Neoadjuvant chemotherapy in breast cancer: early response prediction with quantitative MR imaging and spectroscopy , 2006, British Journal of Cancer.

[5]  Zhou Wang,et al.  Why is image quality assessment so difficult? , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[6]  S. Jung,et al.  Value of 18F-FDG PET/CT for Early Prediction of Pathologic Response (by Residual Cancer Burden Criteria) of Locally Advanced Breast Cancer to Neoadjuvant Chemotherapy , 2014, Clinical nuclear medicine.

[7]  G. Hortobagyi,et al.  Prognosis of women with metastatic breast cancer by HER2 status and trastuzumab treatment: an institutional-based review. , 2010, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[8]  J. Ahn,et al.  Evaluation of ER and Ki-67 proliferation index as prognostic factors for survival following neoadjuvant chemotherapy with doxorubicin/docetaxel for locally advanced breast cancer , 2008, Cancer Chemotherapy and Pharmacology.

[9]  Bal Sanghera,et al.  Assessment of tumor heterogeneity: an emerging imaging tool for clinical practice? , 2012, Insights into Imaging.

[10]  T. Petit,et al.  Comparative value of tumour grade, hormonal receptors, Ki-67, HER-2 and topoisomerase II alpha status as predictive markers in breast cancer patients treated with neoadjuvant anthracycline-based chemotherapy. , 2004, European journal of cancer.

[11]  A. Elster,et al.  Recommendations on the Use of 18F-FDG PET in Oncology , 2009 .

[12]  S. Rodenhuis,et al.  Breast cancer subtyping by immunohistochemistry and histological grade outperforms breast cancer intrinsic subtypes in predicting neoadjuvant chemotherapy response , 2013, Breast Cancer Research and Treatment.

[13]  David S. Wishart,et al.  Applications of Machine Learning in Cancer Prediction and Prognosis , 2006, Cancer informatics.

[14]  Elena Provenzano,et al.  Neoadjuvant trials in early breast cancer: pathological response at surgery and correlation to longer term outcomes – what does it all mean? , 2015, BMC Medicine.

[15]  M. Hatt,et al.  Reproducibility of Tumor Uptake Heterogeneity Characterization Through Textural Feature Analysis in 18F-FDG PET , 2012, The Journal of Nuclear Medicine.

[16]  S. Son,et al.  Prognostic implication of intratumoral metabolic heterogeneity in invasive ductal carcinoma of the breast , 2014, BMC Cancer.

[17]  J. Stec,et al.  Gene expression profiles predict complete pathologic response to neoadjuvant paclitaxel and fluorouracil, doxorubicin, and cyclophosphamide chemotherapy in breast cancer. , 2004, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[18]  Lucila Ohno-Machado,et al.  Logistic regression and artificial neural network classification models: a methodology review , 2002, J. Biomed. Informatics.

[19]  T. Osako,et al.  Clinical significance of Ki-67 in neoadjuvant chemotherapy for primary breast cancer as a predictor for chemosensitivity and for prognosis , 2010, Breast cancer.

[20]  Gideon Blumenthal,et al.  Pathological complete response and long-term clinical benefit in breast cancer: the CTNeoBC pooled analysis , 2014, The Lancet.

[21]  J. Min,et al.  Intratumoral Metabolic Heterogeneity for Prediction of Disease Progression After Concurrent Chemoradiotherapy in Patients with Inoperable Stage III Non-Small-Cell Lung Cancer , 2014, Nuclear medicine and molecular imaging.

[22]  Risk stratification in patients with advanced‐stage breast cancer by pretreatment [18F]FDG PET/CT , 2015, Cancer.

[23]  Yong-il Kim,et al.  Usefulness of Combined Metabolic–Volumetric Indices of 18F-FDG PET/CT for the Early Prediction of Neoadjuvant Chemotherapy Outcomes in Breast Cancer , 2013, Nuclear Medicine and Molecular Imaging.

[24]  Z. Shao,et al.  Clinical and Pathological Response to Neoadjuvant Chemotherapy Based on Primary Tumor Reduction is Correlated to Survival in Hormone Receptor-Positive but not Hormone Receptor-Negative Locally Advanced Breast Cancer , 2014, Annals of Surgical Oncology.

[25]  Seunggyun Ha,et al.  Prediction of neoadjuvant radiation chemotherapy response and survival using pretreatment [18F]FDG PET/CT scans in locally advanced rectal cancer , 2016, European Journal of Nuclear Medicine and Molecular Imaging.

[26]  Patrick Granton,et al.  Radiomics: extracting more information from medical images using advanced feature analysis. , 2012, European journal of cancer.

[27]  E. Gontier,et al.  18F-FDG PET/CT to Predict Response to Neoadjuvant Chemotherapy and Prognosis in Inflammatory Breast Cancer , 2015, The Journal of Nuclear Medicine.

[28]  M. J. van de Vijver,et al.  Breast cancer response to neoadjuvant chemotherapy: predictive markers and relation with outcome , 2003, British Journal of Cancer.

[29]  M. Hatt,et al.  Intratumor Heterogeneity Characterized by Textural Features on Baseline 18F-FDG PET Images Predicts Response to Concomitant Radiochemotherapy in Esophageal Cancer , 2011, The Journal of Nuclear Medicine.

[30]  N. Dubrawsky.  Cancer statistics , 1989, CA: a cancer journal for clinicians.

[31]  B. Fraass,et al.  Stratifying triple-negative breast cancer prognosis using 18F-FDG-PET/CT imaging , 2015, Breast Cancer Research and Treatment.

[32]  M. Untch,et al.  Current and future role of neoadjuvant therapy for breast cancer. , 2014, Breast.

[33]  Yan Zhang,et al.  Molecular Prognostic Prediction for Locally Advanced Nasopharyngeal Carcinoma by Support Vector Machine Integrated Approach , 2012, PloS one.

[34]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[35]  P. Fasching,et al.  Definition and impact of pathologic complete response on prognosis after neoadjuvant chemotherapy in various intrinsic breast cancer subtypes. , 2012, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[36]  J. Karp,et al.  Performance of Philips Gemini TF PET/CT scanner with special consideration for its time-of-flight imaging capabilities. , 2007, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[37]  Dursun Delen,et al.  Predicting breast cancer survivability: a comparison of three data mining methods , 2005, Artif. Intell. Medicine.

[38]  A. Luini,et al.  Chemotherapy Is More Effective in Patients with Breast Cancer Not Expressing Steroid Hormone Receptors , 2004, Clinical Cancer Research.

[39]  S. Son,et al.  Whole-Body Metabolic Tumor Volume, as Determined by (18)F-FDG PET/CT, as a Prognostic Factor of Outcome for Patients With Breast Cancer Who Have Distant Metastasis. , 2015, AJR. American journal of roentgenology.

[40]  Yi Hu,et al.  Three immunomarker support vector machines-based prognostic classifiers for stage IB non-small-cell lung cancer. , 2009, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.