Prediction of Chemotherapy Response in Locally Advanced Breast Cancer Patients at Pre-Treatment Using CT Textural Features and Machine Learning: Comparison of Feature Selection Methods

Abstract

Rationale: Neoadjuvant chemotherapy (NAC) is a key element of treatment for locally advanced breast cancer (LABC). Predicting the response of NAC for patients with LABC before initiating treatment would be valuable to customize therapies and ensure the delivery of effective care.

Objective: Our objective was to develop predictive measures of tumor response to NAC prior to starting for LABC using machine learning and textural computed tomography (CT) features in different level of frequencies.

Materials and methods: A total of 851 textural biomarkers were determined from CT images and their wavelet coefficients for 117 patients with LABC to evaluate the response to NAC. A machine learning pipeline was designed to classify response to NAC treatment for patients with LABC. For training predictive models, three models including all features (wavelet and original image features), only wavelet and only original-image features were considered. We determined features from CT images in different level of frequencies using wavelet transform. Additionally, we conducted a comparison of feature selection methods including mRMR, Relief, Rref QR decomposition, nonnegative matrix factorization and perturbation theory feature selection techniques.

Results: Of the 117 patients with LABC evaluated, 82 (70%) had clinical-pathological response to chemotherapy and 35 (30%) had no response to chemotherapy. The best performance for hold-out data splitting was obtained using the KNN classifier using the Top-5 features, which were obtained by mRMR, for all features (accuracy = 77%, specificity = 80%, sensitivity = 56%, and balanced-accuracy = 68%). Likewise, the best performance for leave-one-out data splitting could be obtained by the KNN classifier using the Top-5 features, which was obtained by mRMR, for all features (accuracy = 75%, specificity = 76%, sensitivity = 62%, and balanced-accuracy = 72%).

Conclusions: The combination of original textural features and wavelet features results in a greater predictive accuracy of NAC response for LABC patients. This predictive model can be utilized to predict treatment outcomes prior to starting, and clinicians can use it as a recommender system to modify treatment.

Keywords: CT imaging; LABC; NAC; machine learning; textural features.

Figure 1

This figure shows the method to extract features, concatenating features from original image and wavelet decomposition, and training machine learning with these features to predict treatment response. In wavelet decomposition, coefficient (A) represents approximation of image, coefficient (B) represents horizontal detail, coefficient (C) represents vertical of image and coefficient (D) represents diagonal detail of image.

Figure 2

This figure illustrates the frequency of selected features for 50 times runs. It shows the frequency of selected features for extracted radiomic features from original image and each wavelet coefficients (LLH, LHL, LHH, HLL, LLH, HHL, HHH, LLL).

Figure 3

Parametric maps for the two response groups: Representative CT images and parametric overlaid map for a responding and a non-responding patient. The parametric maps demonstrate first order Kurtosis original image (Feature 1 with range [0–4]), GLRLM grey level variance of original image (Feature 2 with range [0–35]), first order robust mean absolute deviation HLL (Feature 3 with range [0–18]), Wavelet-LLH-GLDM- Dependence Entropy (Feature 4 with range [0–4]) and GLCM cluster shade LLL (Feature 5 with range [−14,000–0]).