Search

Background: Breast cancer (BC) is among the most common cancers worldwide. Machine learning–based radiomics model could predict axillary lymph node metastasis (ALNM) of BC accurately. Purpose: The purpose is to develop a machine learning model to predict ALNM of BC by focusing on the radiomics features of axillary lymphatic node (ALN). Methods: A group of 398 BC patients with 800 ALNs were retrospectively collected. A set of patient characteristics were obtained to form clinical factors. Three hundred and twenty‐six radiomics features were extracted from each region of interest for ALN in contrast‐enhanced computed tomography (CECT) image. A framework composed of four feature selection methods and 14 machine learning classification algorithms was systematically applied. A clinical model, a radiomics model, and a combined model were developed using a cross‐validation approach and compared. Metrics of the area under the curve (AUC), accuracy, sensitivity, and specificity were calculated to evaluate the performance of these models in the prediction of ALNM in BC. Results: Among the 800 cases of ALNs, there were 388 cases of positive metastasis (48.50%) and 412 cases of negative metastasis (51.50%). The baseline clinical model achieved the performance with an AUC = 0.8998 (95% CI [0.8540, 0.9457]). The radiomics model achieved an AUC = 0.9081 (95% CI [0.8640, 0.9523]). The combined model using the clinical factors and radiomics features achieved the best results with an AUC = 0.9305 (95% CI [0.8928, 0.9682]). Conclusions: Combinations of feature selection methods and machine learning‐based classification algorithms can develop promising predictive models to predict ALNM in BC using CECT features. The combined model of clinical factors and radiomics features outperforms both the clinical model and the radiomic model. [ABSTRACT FROM AUTHOR]

• Based on image feature extraction technology to build aggregate feature data set. • A fusion feature importance analysis method is proposed. • Establish a random forest and XGBoost aggregate shape classification model. • The ability to recognize the 3D features of aggregates in 2D images are improved. Aggregate plays the role of skeleton filling in asphalt pavements. The shape of the aggregate affects the embedded structure between the aggregates, thus affecting the performance of asphalt concrete. In this study, extreme gradient boosting (XGBoost) classification is used to study the automatic shape classification of aggregates. The expression of main and microscopic features of aggregate was improved by transforming aggregate images into data, and a feature importance analysis method based on method fusion is proposed to select the feature parameters of aggregate morphology. Based on cross-validation, the XGBoost classification model was trained by optimizing the super parameter combination to complete the classification of aggregate shapes. Compared with the random forest model, the results show that the proposed method can effectively classify aggregate shapes. It is also proved that the two-dimensional images can reflect the three-dimensional features of the aggregate to some extent. This method provides a certain theoretical basis for the automatic classification of aggregate, and simultaneously it has important practical significance to promote the intelligent production of asphalt mixtures. [ABSTRACT FROM AUTHOR]