Predicting Response to Neoadjuvant Chemotherapy Using 18F FDG PET-CT in Patients with Locally Advanced Breast Cancer

Innovations in Positron Emission Tomography and State of the Art in the Evaluation of Breast Cancer Treatment Response

The advent of hybrid Positron Emission Tomography/Computed Tomography (PET/CT) and PET/Magnetic Resonance Imaging (MRI) scanners resulted in an increased clinical relevance of nuclear medicine in oncology. The use of [18F]-Fluorodeoxyglucose ([18F]FDG) has also made it possible to study tumors (including breast cancer) from not only a dimensional perspective but also from a metabolic point of view. In particular, the use of [18F]FDG PET allowed early confirmation of the efficacy or failure of therapy. The purpose of this review was to assess the literature concerning the response to various therapies for different subtypes of breast cancer through PET. We start by summarizing studies that investigate the validation of PET/CT for the assessment of the response to therapy in breast cancer; then, we present studies that compare PET imaging (including PET devices dedicated to the breast) with CT and MRI, focusing on the identification of the most useful parameters obtainable from PET/CT. We also focus on novel non-FDG radiotracers, as they allow for the acquisition of information on specific aspects of the new therapies.

Breast Cancer—How Can Imaging Help?

Breast cancer is the most common malignant disease among women, causing death and suffering worldwide. It is known that, for the improvement of the survival rate and the psychological impact it has on patients, early detection is crucial. For this to happen, the imaging techniques should be used at their full potential. We selected and examined 44 articles that had as subject the use of a specific imaging method in breast cancer management (mammography, ultrasound, MRI, ultrasound-guided biopsy, PET-CT). After analyzing their data, we summarized and concluded which are the best ways to use each one of the mentioned techniques for a good outcome. We created a simplified algorithm with easy steps that can be followed by radiologists when facing this type of neoplasia.

Analysis of Cross-Combinations of Feature Selection and Machine-Learning Classification Methods Based on [18F]F-FDG PET/CT Radiomic Features for Metabolic Response Prediction of Metastatic Breast Cancer Lesions

Simple Summary

Breast cancer is a leading cause of morbidity and mortality worldwide. The metastatic disease is largely responsible for cancer patient deaths, and its treatment implies usually different therapies. In this context, the prediction of response to treatment or depiction of treatment-resistant phenotypes is essential in clinical practice, especially in the new era of precision medicine. In this study, we used several combinations of feature selection methods and machine-learning classifiers to construct predictive models of the metabolic response to the treatment of metastatic breast cancer lesions. These models were based on clinical variables and radiomic features extracted from 2-deoxy-2-[¹⁸F]fluoro-D-glucose positron emission tomography/computed tomography ([¹⁸F]F-FDG PET/CT) images, obtained prior to the treatment. Our main goal was to know if this prediction was feasible and to identify those combinations with better predictive performance. We found that several combinations were successful to predict the metabolic response to treatment, of which the least absolute shrinkage and selection operator (Lasso) + support vector machines (SVM) had the best mean performance in terms of area under the curve, in both training and validation cohorts. Model performances depended largely on the selected combinations.

Abstract

Background: This study aimed to identify optimal combinations between feature selection methods and machine-learning classifiers for predicting the metabolic response of individual metastatic breast cancer lesions, based on clinical variables and radiomic features extracted from pretreatment [¹⁸F]F-FDG PET/CT images. Methods: A total of 48 patients with confirmed metastatic breast cancer, who received different treatments, were included. All patients had an [¹⁸F]F-FDG PET/CT scan before and after the treatment. From 228 metastatic lesions identified, 127 were categorized as responders (complete or partial metabolic response) and 101 as non-responders (stable or progressive metabolic response), by using the percentage changes in SULpeak (peak standardized uptake values normalized for body lean body mass). The lesion pool was divided into training (n = 182) and testing cohorts (n = 46); for each lesion, 101 image features from both PET and CT were extracted (202 features per lesion). These features, along with clinical and pathological information, allowed the prediction model’s construction by using seven popular feature selection methods in cross-combination with another seven machine-learning (ML) classifiers. The performance of the different models was investigated with the receiver-operating characteristic curve (ROC) analysis, using the area under the curve (AUC) and accuracy (ACC) metrics. Results: The combinations, least absolute shrinkage and selection operator (Lasso) + support vector machines (SVM), or random forest (RF) had the highest AUC in the cross-validation, with 0.93 ± 0.06 and 0.92 ± 0.03, respectively, whereas Lasso + neural network (NN) or SVM, and mutual information (MI) + RF, had the higher AUC and ACC in the validation cohort, with 0.90/0.72, 0.86/0.76, and 87/85, respectively. On average, the models with Lasso and models with SVM had the best mean performance for both AUC and ACC in both training and validation cohorts. Conclusions: Image features obtained from a pretreatment [¹⁸F]F-FDG PET/CT along with clinical vaiables could predict the metabolic response of metastatic breast cancer lesions, by their incorporation into predictive models, whose performance depends on the selected combination between feature selection and ML classifier methods.

Contrast enhanced ultrasound quantitative parameters for assessing neoadjuvant chemotherapy response in patients with locally advanced breast cancer

OBJECTIVES

To evaluate the role of contrast-enhanced ultrasound (CEUS) quantitative parameters in predicting neoadjuvant chemotherapy (NACT) response in patients with locally advanced breast cancer (LABC).

METHODS

30 patients with histologically proven LABC scheduled for NACT were recruited. CEUS was performed using a contrast bolus of 4.8 ml and time intensity curves (TICs) were obtained by contrast dynamics software. CEUS quantitative parameters assessed were peak enhancement (PE), time-to-peak (TTP), area under the curve (AUC) and mean transit time (MTT). The parameters were documented on four consecutive instances: before NACT and 3 weeks after each of the three cycles. The gold-standard was pathological response using Miller Payne Score obtained pre NACT and post-surgery.

RESULTS

A decrease in mean values of PE and an increase in mean values of TTP and MTT was observed with each cycle of NACT among responders. Post each cycle of NACT (compared with baseline pre-NACT), there was a statistically significant difference in % change of mean values of PE, TTP and MTT between good responders and poor responders (p-value < 0.05). The diagnostic accuracy of TTP post-third cycle was 87.2% (p = 0.03), and MTT post--second and third cycle was 76.7% (p = 0.004) and 86.7% (p = 0.006) respectively.

CONCLUSION

In responders, a decrease in the tumor vascularity was reflected in the CEUS quantitative parameters as a reduction in PE, and a prolongation in TTP, MTT.

ADVANCES IN KNOWLEDGE

Prediction of NACT response by CEUS has the potential to serve as a diagnostic modality for modification of chemotherapy regimens during ongoing NACT among patients with LABC, thus affecting patient prognosis.