Intratumoral and Peritumoral Radiomics Based on Functional Parametric Maps from Breast DCE‐MRI for Prediction of HER‐2 and Ki‐67 Status

Abstract

Background Radiomics has been applied to breast magnetic resonance imaging (MRI) for gene status prediction. However, the features of peritumoral regions were not thoroughly investigated. Purpose To evaluate the use of intratumoral and peritumoral regions from functional parametric maps based on breast dynamic contrast‐enhanced MRI (DCE‐MRI) for prediction of HER‐2 and Ki‐67 status. Study Type Retrospective. Population A total of 351 female patients (average age, 51 years) with pathologically confirmed breast cancer were assigned to the training (n = 243) and validation (n = 108) cohorts. Field Strength/Sequence 3.0T, T1 gradient echo. Assessment Radiomic features were extracted from intratumoral and peritumoral regions on six functional parametric maps calculated using time‐intensity curves of DCE‐MRI. The intraclass correlation coefficients (ICCs) were used to determine the reproducibility of feature extraction. Based on the intratumoral, peritumoral, and combined intra‐ and peritumoral regions, three radiomics signatures (RSs) were built using the least absolute shrinkage and selection operator (LASSO) logistic regression model, respectively. Statistical Tests Wilcoxon rank‐sum test, minimum redundancy maximum relevance, LASSO, receiver operating characteristic curve (ROC) analysis, and DeLong test. Results The intratumoral and peritumoral RSs for prediction of HER‐2 and Ki‐67 status achieved areas under the ROC (AUCs) of 0.683 (95% confidence interval [CI], 0.574–0.793) and 0.690 (95% CI, 0.577–0.804), and 0.714 (95% CI, 0.616–0.812) and 0.692 (95% CI, 0.590–0.794) in the validation cohort, respectively. The combined RSs yielded AUCs of 0.713 (95% CI, 0.604–0.823) and 0.749 (95% CI, 0.656–0.841), respectively. There were no significant differences in prediction performance among intratumoral, peritumoral, and combined RSs. Most (69.7%) of the features had good agreement (ICCs >0.8). Data Conclusion Radiomic features of intratumoral and peritumoral regions on functional parametric maps based on breast DCE‐MRI had the potential to identify HER‐2 and Ki‐67 status. Level of Evidence: 3 Technical Efficacy Stage: 2

Radiomics Nomogram Based on Radiomics Score from Multiregional Diffusion-Weighted MRI and Clinical Factors for Evaluating HER-2 2+ Status of Breast Cancer

“…The ROC curve indicated that the com-rad-score yielded a higher AUC score than intra-and peri-rad-scores in both the training and validation cohorts. The results were in agreement with those of several recent studies, which indicated that a radiomics model including intra-and peritumoral features could improve the diagnostic performance for predicting the pathological outcome in BC [29,30,37].…”

“…The features used to calculate the three rad-scores were mainly Law and Gabor features, which may reflect intra-and peritumor heterogeneity. Gabor features can detect the wavelike patterns of intensity variation across different spatial scales in different orientations, and Law features can capture the patterns of inconsistent enhancement and abnormal structure [26,29,31]. However, detailed intraand peritumor features are usually difficult to detect using the naked eye, whereas they can be easily detected by radiomics analysis.…”

“…Five categories of features were extracted from three images (DWI b0 , DWI b800 , and ADC) according to previous radiomic studies [26,[29][30][31]: (i) shape features, (ii) first-order statistics features, (iii) gray-level co-occurrence matrix (GLCM) features, (iv) Laws features, and (v) Gabor features. Detailed descriptions of these radiomic features are provided in Table 1.…”

Intra- and Peritumoral Radiomics Model Based on Early DCE-MRI for Preoperative Prediction of Molecular Subtypes in Invasive Ductal Breast Carcinoma: A Multitask Machine Learning Study

“…Wang et al found that the radiomics features extracted from the 3-mm peritumoral region could differentiate benign and malignant breast lesions on contrast-enhanced mammography (25). Li et al extracted intratumoral and 4-mm peritumoral radiomics features to predict the expression of HER2 and Ki-67 in breast cancer, and their models achieved good performance (26). In our study, 6 mm was determined as the optimal peritumoral size in tasks 1, 3, and 4, and 8 mm was determined as the optimal peritumoral size in task 2.…”

“…Several studies have explored the radiomics features in the peritumoral areas based on various image types, such as mammography, ultrasound, and MRI, and had preliminary results in tumor diagnosis, biological indicator prediction, and prognosis evaluation (23)(24)(25). Li et al recently reported that the radiomics features in the intra-/peritumoral regions based on DCE-MRI are able to identify the HER2 and Ki-67 status in breast cancer (26). In Li's study, the peritumoral region was set as 4 mm from the tumor boundary; however, the optimal peritumoral size for breast cancer has rarely been studied.…”