부산대학교 도서관

Simple Summary: A Machine Learning-based radiomics approach applied to hybrid 18F-FDG PET/MRI might predict axillary lymph node involvement in breast cancer based on the analysis of primary cancer lesions. Indeed, the depiction of tumor heterogeneity through the extraction of radiomics features for both morphological and functional images can be representative of tumor aggressiveness and propensity to invasion. In light of the new personalized treatment options, such as neoadjuvant systemic treatments or the possibility of omitting sentinel lymph node biopsy in patients with a clinically negative axilla, such an approach could result in a better preoperative stratification and also make hybrid 18F-FDG PET/MRI a comprehensive tool for both local and node (N) staging in breast cancer. In this prospective study, 117 female patients (mean age = 53 years) with 127 histologically proven breast cancer lesions (lymph node (LN) positive = 85, LN negative = 42) underwent simultaneous 18F-FDG PET/MRI of the breast. Quantitative parameters were calculated from dynamic contrast-enhanced (DCE) imaging (tumor Mean Transit Time, Volume Distribution, Plasma Flow), diffusion-weighted imaging (DWI) (tumor ADCmean), and PET (tumor SUVmax, mean and minimum, SUVmean of ipsilateral breast parenchyma). Manual whole-lesion segmentation was also performed on DCE, T2-weighted, DWI, and PET images, and radiomic features were extracted. The dataset was divided into a training (70%) and a test set (30%). Multi-step feature selection was performed, and a support vector machine classifier was trained and tested for predicting axillary LN status. 13 radiomic features from DCE, DWI, T2-weighted, and PET images were selected for model building. The classifier obtained an accuracy of 79.8 (AUC = 0.798) in the training set and 78.6% (AUC = 0.839), with sensitivity and specificity of 67.9% and 100%, respectively, in the test set. A machine learning-based radiomics model comprising 18F-FDG PET/MRI radiomic features extracted from the primary breast cancer lesions allows high accuracy in non-invasive identification of axillary LN metastasis. [ABSTRACT FROM AUTHOR]