Machine Learning-Based A Priori Chemotherapy Response Prediction in Breast Cancer Patients using Textural CT Biomarkers*

Early prediction of cancer response to neoadjuvant chemotherapy (NAC) could permit personalized treatment adjustments for patients, which would improve treatment outcomes and patient survival. For the first time, the efficiency of quantitative computed tomography (qCT) textural and second derivative of textural (SDT) features were investigated and compared in this study. It was demonstrated that intra-tumour heterogeneity can be probed through these biomarkers and used as chemotherapy tumour response predictors in breast cancer patients prior to the start of treatment. These features were used to develop a machine learning approach which provided promising results with cross-validated AUC0.632+, accuracy, sensitivity and specificity of 0.86, 81%, 74% and 88%, respectively.Clinical Relevance— The results obtained in this study demonstrate the potential of textural CT biomarkers as response predictors of standard NAC before treatment initiation.

[1]  B. Tromberg,et al.  Predicting response to breast cancer neoadjuvant chemotherapy using diffuse optical spectroscopy , 2007, Proceedings of the National Academy of Sciences.

[2]  A. Jemal,et al.  Cancer statistics, 2018 , 2018, CA: a cancer journal for clinicians.

[3]  B. Cheson,et al.  Positron-emission tomography and assessment of cancer therapy. , 2006, The New England journal of medicine.

[4]  J. Ioannidis,et al.  Neoadjuvant versus adjuvant systemic treatment in breast cancer: a meta-analysis. , 2005, Journal of the National Cancer Institute.

[5]  Wilfrido Gómez-Flores,et al.  Improving classification performance of breast lesions on ultrasonography , 2015, Pattern Recognit..

[6]  Anna L. Brown,et al.  Effect of preoperative chemotherapy on the outcome of women with operable breast cancer. , 1998, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[7]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[8]  F. Blankenberg,et al.  Imaging cell death in vivo. , 2003, The quarterly journal of nuclear medicine : official publication of the Italian Association of Nuclear Medicine (AIMN) [and] the International Association of Radiopharmacology.

[9]  Isabelle Bedrosian,et al.  Underuse of trimodality treatment affects survival for patients with inflammatory breast cancer: an analysis of treatment and survival trends from the National Cancer Database. , 2014, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[10]  G. Hortobagyi.  Breast cancer survival in the US and Europe: a CONCORD high-resolution study , 2013 .

[11]  Michael C. Kolios,et al.  Low-frequency quantitative ultrasound imaging of cell death in vivo. , 2013, Medical Physics (Lancaster).

[12]  Vivek Verma,et al.  Response rates and pathologic complete response by breast cancer molecular subtype following neoadjuvant chemotherapy , 2018, Breast Cancer Research and Treatment.

[13]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Wei Huang,et al.  Early Prediction and Evaluation of Breast Cancer Response to Neoadjuvant Chemotherapy Using Quantitative DCE-MRI1 , 2016, Translational oncology.

[15]  Gregory J. Czarnota,et al.  Non-invasive evaluation of breast cancer response to chemotherapy using quantitative ultrasonic backscatter parameters , 2015, Medical Image Anal..

[16]  F. Cardoso,et al.  Management of locally advanced breast cancer—perspectives and future directions , 2015, Nature Reviews Clinical Oncology.

[17]  Abbas Samani,et al.  Lung CT image based automatic technique for COPD GOLD stage assessment , 2017, Expert Syst. Appl..

[18]  Lubomir M. Hadjiiski,et al.  Classifier performance prediction for computer-aided diagnosis using a limited dataset. , 2008, Medical physics.

[19]  Abbas Samani,et al.  Towards computer based lung disease diagnosis using accurate lung air segmentation of CT images in exhalation and inhalation phases , 2017, Expert Syst. Appl..

[20]  Yoav Freund,et al.  Boosting a weak learning algorithm by majority , 1995, COLT '90.

[21]  Ali Sadeghi-Naini,et al.  Predicting breast cancer response to neoadjuvant chemotherapy using pretreatment diffuse optical spectroscopic texture analysis , 2017, British Journal of Cancer.

[22]  R. Tibshirani,et al.  Improvements on Cross-Validation: The 632+ Bootstrap Method , 1997 .

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

[24]  G. Hortobagyi,et al.  Mastectomy following preoperative chemotherapy. Strict operative criteria control operative morbidity. , 1991, Annals of surgery.