Pathologic response prediction to neoadjuvant chemotherapy utilizing pretreatment near-infrared imaging parameters and tumor pathologic criteria

Abstract

Introduction: The purpose of this study is to develop a prediction model utilizing tumor hemoglobin parameters measured by ultrasound-guided near-infrared optical tomography (US-NIR) in conjunction with standard pathologic tumor characteristics to predict pathologic response before neoadjuvant chemotherapy (NAC) is given.

Methods: Thirty-four patients' data were retrospectively analyzed using a multiple logistic regression model to predict response. These patients were split into 30 groups of training (24 tumors) and testing (12 tumors) for cross validation. Tumor vascularity was assessed using US-NIR measurements of total hemoglobin (tHb), oxygenated (oxyHb) and deoxygenated hemoglobin (deoxyHb) concentrations acquired before treatment. Tumor pathologic variables of tumor type, Nottingham score, mitotic index, the estrogen and progesterone receptors and human epidermal growth factor receptor 2 acquired before NAC in biopsy specimens were also used in the prediction model. The patients' pathologic response was graded based on the Miller-Payne system. The overall performance of the prediction models was evaluated using receiver operating characteristic (ROC) curves. The quantitative measures were sensitivity, specificity, positive and negative predictive values (PPV and NPV) and the area under the ROC curve (AUC).

Results: Utilizing tumor pathologic variables alone, average sensitivity of 56.8%, average specificity of 88.9%, average PPV of 84.8%, average NPV of 70.9% and average AUC of 84.0% were obtained from the testing data. Among the hemoglobin predictors with and without tumor pathological variables, the best predictor was tHb combined with tumor pathological variables, followed by oxyHb with pathological variables. When tHb was included with tumor pathological variables as an additional predictor, the corresponding measures improved to 79%, 94%, 90%, 86% and 92.4%, respectively. When oxyHb was included with tumor variables as an additional predictor, these measures improved to 77%, 85%, 83%, 83% and 90.6%, respectively. The addition of tHb or oxyHb significantly improved the prediction sensitivity, NPV and AUC compared with using tumor pathological variables alone.

Conclusions: These initial findings indicate that combining widely used tumor pathologic variables with hemoglobin parameters determined by US-NIR may provide a powerful tool for predicting patient pathologic response to NAC before the start of treatment.

Trial registration: ClincalTrials.gov ID: NCT00908609 (registered 22 May 2009).

Figures

Figure 1

Box-and-whisker plot of baseline total hemoglobin, oxygenated hemoglobin and deoxygenated hemoglobin of two responder groups. deoxyHb, Deoxygenated hemoglobin; MP, Miller-Payne grade; oxyHb, Oxygenated hemoglobin; tHb, Total hemoglobin.

Figure 2

Box-and-whisker plots of area under the receiver operating characteristic curves obtained from prediction models of 12 sets of predictor variables. (a) Training data. (b) Testing data. Char, Predictor variables of tumor characteristics of type, Nottingham score, mitotic count; Char+Rec, Predictor variables of tumor characteristics and receptor status of triple-negative, human epidermal growth factor receptor 2 (HER2), estrogen receptor (ER); tHb, oxyHb, deoxyHb: Predictor variables of pretreatment maximum total hemoglobin (tHb), oxygenated hemoglobin (oxyHb) and deoxygenated hemoglobin (deoxyHb), respectively; tHboxyHb, tHbdeoxyHb: Combined predictor variables of tHb and oxyHb, tHb and deoxyHb, respectively; Char+Rec+corresponding hemoglobin variables: Combined predictor variables of tumor characteristics, receptor status and corresponding hemoglobin predictors. ROC, Receiver operating characteristic.

Figure 3

Training data. Box-and-whisker plot of sensitivity (a), specificity (b), positive predictive value (c), and negative predictive value (d) obtained from 12 prediction models with predictor variables given along the x-axis. The predictor variables are the same as those given in Figure 2.

Figure 4

Testing data. Box-and-whisker plot of sensitivity (a), specificity (b), positive predictive value (c), and negative predictive value (d) obtained from 12 prediction models with predictor variables given along the x-axis. The predictor variables are the same as those given in Figure 2.

Figure 5

Typical example of receiver operating characteristic curves obtained with pathological variables. (a) Receiver operating characteristic curve (ROC) obtained from tumor pathological variables only. (b) ROC obtained from tumor tHb only. (c) ROC obtained from tHb with pathological variables. (d) ROC obtained from oxyHb only. (e) ROC obtained from oxyHb. The 95% confidence interval is also given in each figure.