Radiomics With Attribute Bagging for Breast Tumor Classification Using Multimodal Ultrasound Images

Abstract

Objectives We aimed to develop radiomics with attribute bagging, which leverages multimodal ultrasound (US) images to improve the classification accuracy of breast tumors. Methods A retrospective study was conducted. B‐mode US, shear wave elastographic, and contrast‐enhanced US images of 178 patients with 181 tumors (67 malignant and 114 benign) were included. Radiomics with attribute bagging consisted of extraction of 1226 radiomic features and analysis of them with attribute bagging. Histologic examination results acted as the reference standard. Radiomics with several feature selection algorithms were used for comparison. Cross‐validation and a holdout test were performed to evaluate their performances. Results The accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve of radiomics with attribute bagging with the multimodal US images were 84.12%, 92.86%, 78.80%, and 0.919, respectively, exceeding all the comparison methods. Conclusions Radiomics with attribute bagging combined with multimodal US images has the potential to be used for accurate diagnosis of breast tumors in the clinic.

Study Processes and Applications of Ultrasomics in Precision Medicine

“…Ultrasomics extracts high-throughput information and performs quantitative analysis with a CAD, which can objectively describe and explain the features of tumors. At present, studies have combined conventional 2D ultrasound images, shear-wave elastography (SWE) images, strain elastography images, and contrastenhanced ultrasound (CEUS) images with radiomics to detect and identify breast tumors (14,(20)(21)(22). These studies extracted high-throughput features to quantify tumor shape, hardness, and hardness heterogeneity to identify breast malignancies and benign tumors.…”

Radiomics Model Based on Shear-Wave Elastography Can Predict the Axillary Lymph Node Status in Early-Stage Breast Cancer

“…Because the contour of the lesion on SWE was indefinite, the same region on BMUS was copied and pasted to the corresponding SWE image, and was expanded to include the "stiff rim" sign if it existed. SWE is a combination of B-model image and pseudocolor elasticity layer, algorithms presented in previous studies were employed to produce clean quantitative images that mapping the tissue stiffness as grey levels [24][25][26]. The radiomic features were extracted automatically from each BMUS and SWE image by Pyradiomics (https://pyradiomics.readthedocs.io/en/latest/index.html) (Additional le 2, Supplemental Table 1…”

The Roles of Ultrasound-Based Radiomics In Precision Diagnosis and Treatment of Different Cancers: A Literature Review

“…Five studies have reported ultrasound-based radiomics models related to breast cancer. Those studies mainly focused on the prediction of biological behavior in invasive ductal carcinoma (IDC) [29] , the differential diagnosis between triple-negative breast cancer and fibroadenoma [30], differentiation of benign and malignant breast tumors [31,32], and the diagnosis of axillary lymph node metastasis in earlystage IDC.…”

“…d e v e l o p e d a r a d i o m i c s a p p r o a c h , leveraging multimodal ultrasound images to improve the classification accuracy of breast tumors. B-mode ultrasound, SWE, and contrast-enhanced ultrasound images of 178 patients with 181 tumors (67 malignant and 114 benign) were included [32]. A total of 1,226 radiomics features were extracted and analyzed with attribute bagging.…”