Application of deep learning and XGBoost in predicting pathological staging of breast cancer MR images.

Autor: Miao, Yue, Tang, Siyuan, Zhang, Zhuqiang, Song, Jukun, Liu, Zhi, Chen, Qiang, Zhang, Miao
Předmět:
Zdroj: Journal of Supercomputing; May2024, Vol. 80 Issue 7, p8933-8953, 21p
Abstrakt: The methods of deep learning and traditional radiomics feature extraction were preliminarily discussed, and a multimodal data prediction model for breast cancer clinical stage was established. The MR images and clinical staging data of breast cancer were obtained from the official websites of the American Cancer Center TCGA and TCIA, respectively, with a total of 139 patient samples. The region of interest was delineated on the enhanced image of breast cancer MR, and then the feature extraction of radiomics and deep learning was performed, and 108 radiomics features and 1024 deep-learning features were extracted for each case. After feature screening and processing, clinical data were integrated, and a machine-learning model was used to predict clinical stage I and non-stage I. Results 26 radiomic features and 12 deep features related to staging were screened out by LASSO algorithm, and a classification model was constructed based on XGBoost machine learning. The patients were predicted with an accuracy rate of 80.00%, and the area under the curve of the receiver operating characteristic curve was 0.833. It is feasible to predict the clinical stage of breast cancer through radiomics and deep-learning feature extraction and machine-learning technology. The classification model based on multimodal data established by using machine-learning classifier can distinguish clinical stage I and non-stage I in breast cancer and have higher accuracy. This study confirms the feasibility and accuracy of combining data from different modalities to contribute to clinical staging prediction. The research contributions include demonstrating the superiority of deep-learning models for feature extraction and classification, as well as highlighting the potential of combining deep learning and traditional machine-learning algorithms for improved classification performance. [ABSTRACT FROM AUTHOR]
Databáze: Complementary Index
Externí odkaz: