PET/CT-based radiomics analysis may help to predict neoadjuvant chemotherapy outcomes in breast cancer

Abstract

BackgroundThe aim of this study was to evaluate the clinical usefulness of radiomics signature-derived 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography–computed tomography (PET-CT) for the early prediction of neoadjuvant chemotherapy (NAC) outcomes in patients with (BC).MethodsA total of 124 patients with BC who underwent pretreatment PET-CT scanning and received NAC between December 2016 and August 2019 were studied. The dataset was randomly assigned in a 7:3 ratio to either the training or validation cohort. Primary tumor segmentation was performed, and radiomics signatures were extracted from each PET-derived volume of interest (VOI) and CT-derived VOI. Radiomics signatures associated with pathological treatment response were selected from within a training cohort (n = 85), which were then applied to generate different classifiers to predict the probability of pathological complete response (pCR). Different models were then independently tested in the validation cohort (n = 39) regarding their accuracy, sensitivity, specificity, and area under the curve (AUC).ResultsThirty-five patients (28.2%) had pCR to NAC. Twelve features consisting of five PET-derived signatures, four CT-derived signatures, and three clinicopathological variables were candidates for the model’s development. The random forest (RF), k-nearest neighbors (KNN), and decision tree (DT) classifiers were established, which could be utilized to predict pCR to NAC with AUC ranging from 0.819 to 0.849 in the validation cohort.ConclusionsThe PET/CT-based radiomics analysis might provide efficient predictors of pCR in patients with BC, which could potentially be applied in clinical practice for individualized treatment strategy formulation.

Prediction of pathological response after neoadjuvant chemotherapy using baseline FDG PET heterogeneity features in breast cancer

“…From the IMH features reported in the reviewed literature, 11,20,22,23,26,28,29 an association with prediction of response to NAST was suggested for coefficient of variation, 11 skewness, 11 QRobust mean absolute deviation 29 and kurtosis. 26 The other analysed IMH features (in particular entropy, range, standard deviation, uniformity, variance and SUVmean/SUVmax ratio) were not considered to be associated with response to NAST in any study.…”

“…Table 3 shows the results of the analysis of texture-based features in the prediction of response to NAST. From the reviewed literature, the majority of the studies (Ha et al, 11 Molina-García et al, 19 Yoon et al, 20 Lee et al, 21 Li et al, 22 Roy et al, 29 Umutlu et al 25 and Yang et al 26 ) suggested FDG PET texture-based features may predict response to NAST. However, none of the predictive texture-based features was the same in these studies.…”

Deep learning-based predictive model for pathological complete response to neoadjuvant chemotherapy in breast cancer from biopsy pathological images: a multicenter study

“…Primarily, pathologic images and clinicopathologic parameters alone provide only limited information in predicting pCR. If multimodal data are added, such as ultrasound ( Cui et al, 2021 ), CT ( Moghadas-Dastjerdi et al, 2021 ), MRI ( Huang et al, 2023 ; Shi et al, 2023 ), PET-CT ( Yang et al, 2022 ) examination data, or even genetic testing data, the predictive efficacy of the model can be further improved and the uncertainty of model application can be reduced. Secondly, the number of enrolled cases and the number of clinicopathologic features also affect the uncertainty of model application.…”