Intratumoral and peritumoral radiomics based on automated breast volume scanner for predicting human epidermal growth factor receptor 2 status

Abstract

Purpose: To develop an intratumoral and peritumoral radiomics model using Automated Breast Volume Scanner (ABVS) for noninvasive preoperative prediction of Human Epidermal Growth Factor Receptor 2 (HER2) status.

Methods: This retrospective study analyzed 384 lesions from 379 patients with pathologically confirmed breast cancer across four hospitals. Two tasks were defined: Task 1 to distinguish HER2-negative from HER2-positive cases and Task 2 to differentiate HER2-zero from HER2-low status. For each classification task, three models were built: Model 1 included radiomics features from the tumor region alone; Model 2 included features from both the tumor region and a 5mm peritumoral region; and Model 3 incorporated features from the tumor region, the 5mm peritumoral region, and the 5-10mm peritumoral region. The performance of the model was evaluated using receiver operating characteristic (ROC) curves, with key metrics including the area under the curve (AUC), sensitivity, specificity, and accuracy.

Results: In the classification tasks, Model 2 demonstrated superior predictive performance across multiple datasets. For Task 1, it achieved the highest AUC (0.844), exceptional sensitivity (0.955), and satisfactory accuracy (0.787) in the validation set, and outperformed other models in the test set with an AUC of 0.749 and sensitivity of 0.885, highlighting its robustness and clinical applicability. For Task 2, Model 2 exhibited the highest AUC (0.801), sensitivity (0.862), and accuracy (0.808) in the test set, with consistent performance across the training (AUC 0.850) and validation sets (AUC 0.801). Model 3, which combines intratumoral and peritumoral features, did not demonstrate significant improvements over the intratumoral-only model in the two classification tasks. These results underscore the value of incorporating peritumoral radiomics features, particularly within a 5mm margin, to enhance predictive performance compared to intratumoral-only models.

Conclusion: The radiomics model integrating intratumoral and appropriate peritumoral features significantly outperformed the model based on intratumoral features alone. This integrated approach holds strong potential for noninvasive, preoperative prediction of HER2 status.

Keywords: automated breast volume scanner; breast cancer; human epidermal growth factor receptor 2; peritumoral; radiomics.

Figure 1

Flowchart of patients and study design. ABVS, Automated Breast Volume scanner; Task 1, the distinction of HER2-positive from HER2-negative breast cancers. Task 2, the distinction of HER2-low from HER2-zero breast cancers.

Figure 2

Intratumoral and Peritumoral ROI segmentation workflow.

Figure 3

ROC curves and area under the curve for classification tasks. (A) Task 1 (Training Set); (B) Task 1 (Validation Set); (C) Task 1 (Test Set); (D) Task 2 (Training Set); (E) Task 2 (Validation Set); (F) Task 2 (Test Set).

Figure 4

DCA performance of three models in two classification tasks and calibration curve of model 2. (A) Decision curve for Task 1 test set; (B) Calibration curve for Model 2 in Task 1 test set; (C) Decision curve for Task 2 test set; (D) Calibration curve for Model 2 in Task 2 test set. The x-axis and y-axis show the threshold probability and the net benefit, respectively. The light black line shows the assumption that all breast cancer patients were HER2-negative or HER2-zero (the strategy of “treat all”). The bold black line shows the assumption that all breast cancer patients were HER2-negative or HER2-zero (the strategy of “treat none”).