MRI-Based Radiomics Analysis for the Pretreatment Prediction of Pathologic Complete Tumor Response to Neoadjuvant Systemic Therapy in Breast Cancer Patients: A Multicenter Study.

Abstract

Simple SummaryThe prediction of pathologic complete response (pCR) to neo-adjuvant systemic therapy (NST) based on radiological assessment of pretreatment MRI exams in breast cancer patients is not possible to date. In this study, we investigated the value of pretreatment MRI-based radiomics analysis for the prediction of pCR to NST. Radiomics, clinical, and combined models were developed and validated based on MRI exams containing 320 tumors collected from two hospitals. The clinical models significantly outperformed the radiomics models for the prediction of pCR to NST and were of similar or better performance than the combined models. This indicates poor performance of the radiomics features and that in these scenarios the radiomic features did not have an added value for the clinical models developed. Due to previous and current work, we tentatively attribute the lack of significant improvement in clinical models following the addition of radiomics features to the effects of variations in acquisition and reconstruction parameters. The lack of reproducibility data meant this effect could not be analyzed. These results indicate the need for reproducibility studies to preselect reproducible features in order to properly assess the potential of radiomics.This retrospective study investigated the value of pretreatment contrast-enhanced Magnetic Resonance Imaging (MRI)-based radiomics for the prediction of pathologic complete tumor response to neoadjuvant systemic therapy in breast cancer patients. A total of 292 breast cancer patients, with 320 tumors, who were treated with neo-adjuvant systemic therapy and underwent a pretreatment MRI exam were enrolled. As the data were collected in two different hospitals with five different MRI scanners and varying acquisition protocols, three different strategies to split training and validation datasets were used. Radiomics, clinical, and combined models were developed using random forest classifiers in each strategy. The analysis of radiomics features had no added value in predicting pathologic complete tumor response to neoadjuvant systemic therapy in breast cancer patients compared with the clinical models, nor did the combined models perform significantly better than the clinical models. Further, the radiomics features selected for the models and their performance differed with and within the different strategies. Due to previous and current work, we tentatively attribute the lack of improvement in clinical models following the addition of radiomics to the effects of variations in acquisition and reconstruction parameters. The lack of reproducibility data (i.e., test-retest or similar) meant that this effect could not be analyzed. These results indicate the need for reproducibility studies to preselect reproducible features in order to properly assess the potential of radiomics.