Machine learning for predicting the response of breast cancer to neoadjuvant chemotherapy

Abstract

Objective: To employ machine learning methods to predict the eventual therapeutic response of breast cancer patients after a single cycle of neoadjuvant chemotherapy (NAC).

Materials and methods: Quantitative dynamic contrast-enhanced MRI and diffusion-weighted MRI data were acquired on 28 patients before and after one cycle of NAC. A total of 118 semiquantitative and quantitative parameters were derived from these data and combined with 11 clinical variables. We used Bayesian logistic regression in combination with feature selection using a machine learning framework for predictive model building.

Results: The best predictive models using feature selection obtained an area under the curve of 0.86 and an accuracy of 0.86, with a sensitivity of 0.88 and a specificity of 0.82.

Discussion: With the numerous options for NAC available, development of a method to predict response early in the course of therapy is needed. Unfortunately, by the time most patients are found not to be responding, their disease may no longer be surgically resectable, and this situation could be avoided by the development of techniques to assess response earlier in the treatment regimen. The method outlined here is one possible solution to this important clinical problem.

Conclusions: Predictive modeling approaches based on machine learning using readily available clinical and quantitative MRI data show promise in distinguishing breast cancer responders from non-responders after the first cycle of NAC.

Keywords: DCE-MRI; breast cancer; diffusion MRI; machine learning; neoadjuvant chemotherapy; predictive modeling.

Figure 1

Illustrative dynamic contrast enhanced MRI (DCE-MRI) and diffusion weighted MRI (DW-MRI) data at the three time points for a patient who achieved complete pathological response (a–f) and a patient who was a non-responder (g–l). Panels a–c display the k_ep map from the Tofts–Kety model, while panels d–f display the apparent diffusion coefficient (ADC) map. Similar data are presented for the non-responder in panels g–l. Observe how, in the responding patient, there is a 21% decrease in k_ep from t₁ to t₂ as well as a 38% increase in ADC between these two time points. Conversely, in the non-responding patient there is a 27% increase in k_ep and a 25% decrease in the ADC between these two time points.

Figure 2

A general schema for predictive model building and evaluation showing that model evaluation is performed using test data that are not used for model building. pCR, pathological complete response.