Circulating tumor DNA and magnetic resonance imaging to predict neoadjuvant chemotherapy response and recurrence risk

Abstract

We investigated whether serial measurements of circulating tumor DNA (ctDNA) and functional tumor volume (FTV) by magnetic resonance imaging (MRI) can be combined to improve prediction of pathologic complete response (pCR) and estimation of recurrence risk in early breast cancer patients treated with neoadjuvant chemotherapy (NAC). We examined correlations between ctDNA and FTV, evaluated the additive value of ctDNA to FTV-based predictors of pCR using area under the curve (AUC) analysis, and analyzed the impact of FTV and ctDNA on distant recurrence-free survival (DRFS) using Cox regressions. The levels of ctDNA (mean tumor molecules/mL plasma) were significantly correlated with FTV at all time points (p < 0.05). Median FTV in ctDNA-positive patients was significantly higher compared to those who were ctDNA-negative (p < 0.05). FTV and ctDNA trajectories in individual patients showed a general decrease during NAC. Exploratory analysis showed that adding ctDNA information early during treatment to FTV-based predictors resulted in numerical but not statistically significant improvements in performance for pCR prediction (e.g., AUC 0.59 vs. 0.69, p = 0.25). In contrast, ctDNA-positivity after NAC provided significant additive value to FTV in identifying patients with increased risk of metastatic recurrence and death (p = 0.004). In this pilot study, we demonstrate that ctDNA and FTV were correlated measures of tumor burden. Our preliminary findings based on a limited cohort suggest that ctDNA at surgery improves FTV as a predictor of metastatic recurrence and death. Validation in larger studies is warranted.

Conflict of interest statement

The following authors are employees of Natera, Inc. (E.K., A.A. and B.Z.). L.V.V. is co-founder, stockholder and part-time employee of Agendia NV. The rest of the authors declare no potential conflicts of interest.

Figures

Fig. 1. Pretreatment functional tumor volume (FTV) and association with clinicopathologic characteristics.

P values were calculated using Mann–Whitney (2 groups) or Kruskal–Wallis test (3 groups). For each box plot, the center line, the boundaries of the box, the ends of the whiskers and points beyond the whiskers represent the median value, the interquartile range, the minimum and maximum values, and the outliers, respectively.

Fig. 2. Relationship between ctDNA and FTV at different time points.

a Scatterplot for all patients with paired data at different time points to show correlation between ctDNA and MRI-based FTV as measures of tumor burden. b ctDNA-positivity and tumor burden by MRI-based FTV. Box plots showing distribution of FTV according to ctDNA status (ctDNA-positive or ctDNA-negative) at different time points. T0: pretreatment; T1: 3 weeks after initiation of paclitaxel-based treatment; T2: between paclitaxel and anthracycline regimens; T3: after NAC prior to surgery. For each box plot, the center line, the boundaries of the box, the ends of the whiskers and points beyond the whiskers represent the median value, the interquartile range, the minimum and maximum values, and the outliers, respectively.

Fig. 3. Correlation between ctDNA and MRI-based FTV dynamics during NAC.

a Mean levels of ctDNA (mean tumor molecules per mL plasma, MTM) and FTV (cm3) across time points. The error bars represent standard deviation. The vertical lines represent standard deviation. b Schematic for calculating the mean Pearson correlation for actual data and means for simulated datasets using Monte Carlo method. The right panel is histogram showing the distribution of simulated means of Fisher z-transformed Pearson’s correlation coefficient. The red line corresponds to the mean Fisher z-transformed Pearson’s correlation coefficient calculated based on the actual data. c Plots showing ctDNA (mean tumor molecules per mL plasma, MTM) and FTV (cm3) levels across time points in 4 representative cases. Unfilled dot at T3 in patient 4 indicates ctDNA below the limit of detection. T0: pretreatment; T1: 3 weeks after initiation of paclitaxel-based treatment; T2: between paclitaxel and anthracycline regimens; T3: after NAC prior to surgery.

Fig. 4. Additive value of ctDNA to FTV-based predictors of pCR at T1.

a Area under the curve (AUC) for prediction of pCR early during NAC (T1: 3 weeks after initiation treatment) for FTV alone and FTV + ctDNA treated as a continuous variable. b Positive predictive value (PPV), negative predictive value (NPV) and accuracy for prediction of pCR of FTV alone and FTV + ctDNA treated as a dichotomous variable.

Fig. 5. Study schema showing time points for collection of MRI-based functional tumor volume (FTV) and circulating tumor DNA (ctDNA) data during neoadjuvant chemotherapy (NAC).

Patients received paclitaxel-based treatment followed by anthracycline-based chemotherapy. Data and biospecimens were collected at pretreatment (T0), 3 weeks after initiation of paclitaxel-based treatment (T1), between paclitaxel and anthracycline regimens (T2), and after NAC prior to surgery (T3). Pathologic complete response (pCR), the primary endpoint of this study, was assessed at surgical time point.