As a receptor of breast cancer prognosis and treatment, human epidermal growth factor receptor 2 (HER-2) is closely associated with breast cancer occurrence and progression. Breast cancer lesions are characterized by irregular shapes, small lesion targets, and possible multi-target lesions with overlapping boundaries. Existing algorithms have partly improved the detection accuracy of breast cancer detection model. However, it still suffers from the issues of insufficient detection accuracy and slow detection speed of small and multi-target lesions and requires a huge mass of sample data for iteration during model training, which is demanding on datasets. To address this problem, an improved model is proposed in this paper based on YOLOv10. The model introduces VanillaNet, a lightweight backbone network that can significantly improve detection accuracy by reducing the network depth of the model to equalize detection speed and performance. In addition, the RefConv module is embedded into the C2f structure to further reduce channel redundancy and smooth out lossy situations. In the feature fusion network part, the introduction of a lightweight up-sampling operator content-aware feature reorganization CARAFE module enhances the quality and richness of output features, which effectively improves detection accuracy and speed. The accuracy of the improved model is 98.8%. Thus, the improved model is a significant advantage over mainstream models such as traditional faster region-based convolutional neural network (RCNN), YOLOv5, YOLOv7, YOLOv8, YOLOv10, and YOLOv12.

1. [1] D. Xavier, I. Miyawaki, C. A. C. Jorge et al., “Artificial intelligence for triaging of breast cancer screening mammograms and workload reduction: A meta-analysis of a deep learning software,” J. of Medical Screening, Vol.31, No.3, pp. 157-165, 2024. https://doi.org/10.1177/09691413231219952
2. [2] H. S. Rugo et al., “185O Trastuzumab deruxtecan (T-DXd) vs treatment of physician’s choice (TPC) in patients (pts) with HER2-low unresectable and/or metastatic breast cancer (mBC): A detailed safety analysis of the randomized, phase III DESTINY-Breast04 trial,” ESMO Open, Vol.8, No.1, Article No.101374, 2023. https://doi.org/10.1016/j.esmoop.2023.101374
3. [3] Y. Yang et al., “A new nomogram for predicting the malignant diagnosis of breast imaging reporting and data system (BI-RADS) ultrasonography category 4A lesions in women with dense breast tissue in the diagnostic setting,” Quant. Imaging Med. Surg., Vol.11, No.7, pp. 3005-3017, 2021. https://doi.org/10.21037/qims-20-1203
4. [4] S. Ren et al., “Faster R-CNN: Towards real-time object detection with region proposal networks,” Proc. of the 29th Int. Conf. on Neural Information Processing Systems, pp. 91-99, 2015.
5. [5] J. Xu, H. Ren, S. Cai, and X. Zhang, “An improved faster R-CNN algorithm for assisted detection of lung nodules,” Computers in Biology and Medicine, Vol.153, Article No.106470, 2023. https://doi.org/10.1016/j.compbiomed.2022.106470
6. [6] J. Redmon, S. Cdivvala, R. Cgirshick et al., “You Only Look Once: Unified, real-time object detection,” Proc. of 2016 IEEE Conf. on Computer Vision and Pattern Recognition, pp. 779-788, 2016. https://doi.org/10.1109/CVPR.2016.91
7. [7] C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, “YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors,” 2023 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 7464-7475, 2023. https://doi.org/10.1109/CVPR52729.2023.00721
8. [8] Y. Tian, Q. Ye, and D. Doermann, “YOLOv12: Attention-Centric Real-Time Object Detector,” arXiv:2502.12524, 2025. https://doi.org/10.48550/arXiv.2502.12524
9. [9] M. Lei, S. Li, Y. Wu, H. Hu, Y. Zhou, X. Zheng, G. Ding, S. Du, Z. Wu, and Y. Gao, “YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception,” arXiv:2506.17733, 2025. https://doi.org/10.48550/arXiv.2506.17733
10. [10] L. Sun, Y. Zhang, T. Liu et al., “A collaborative multi-task learning method for BI-RADS category 4 breast lesion segmentation and classification of MRI images,” Computer Methods and Programs in Biomedicine, Vol.240, Article No.107705, 2023. https://doi.org/10.1016/j.cmpb.2023.107705
11. [11] F. Rajeena P.P and S. Tehsin, “A Framework for Breast Cancer Classification with Deep Features and Modified Grey Wolf Optimization,” Mathematics, Vol.13, No.8, Article No.1236, 2025. https://doi.org/10.3390/math13081236
12. [12] M. Epimack, M. He, and M. Palme, “Deep learning mammography classification with a small set of data,” Current Medical Imaging, Vol.20, Article No.e110823219688, 2024. https://doi.org/10.2174/1573405620666230811142718
13. [13] T. Yang, L. Yang, M. Yang et al., “Study on the application of YOLO algorithm based on improved YOLO network in the detection of ultrasound image for breast tumor,” China Medical Equipment, Vol.21, No.9, pp. 23-27, 2024.
14. [14] A. Alaa and S. A. Aly, “Acute lymphoblastic leukemia diagnosis employing YOLOv11, YOLOv8, ResNet50, and inception-ResNet-v2 deep learning models,” arXiv:2502.09804v1, 2025. https://doi.org/10.48550/arXiv.2502.09804
15. [15] A. Wang, H. Chen, L. H. Liu et al., “YOLOv10: Real time end-to-end object detection,” arXiv:2405.14458, 2024. https://doi.org/10.48550/arXiv.2405.14458
16. [16] J. Terven, D.-M. Córdova-Esparza, J.-A. Romero-González et al., “A comprehensive review of YOLO architectures in computer vision: From YOLOv1 to YOLOv8 and YOLO-NAS,” Machine Learning and Knowledge Extraction, Vol.5, No.4, pp. 1680-1716, 2023. https://doi.org/10.3390/make5040083
17. [17] H. Chen, Y. Wang, J. Guo, and D. Tao, “VanillaNet: The power of minimalism in deep learning,” arXiv:2305.12972, 2023. https://doi.org/10.48550/arXiv.2305.12972
18. [18] M. Bachhawat, “Generalizing GradCAM for embedding networks,” arXiv:2402.00909, 2024. https://doi.org/10.48550/arXiv.2402.00909
19. [19] X. Qiu, Y. Chen, W. Cai, M. Niu, and J. Li, “LD-YOLOv10: A Lightweight Target Detection Algorithm for Drone Scenarios Based on YOLOv10,” Electronics, Vol.13, No.16, Article No.3269, 2024. https://doi.org/10.3390/electronics13163269
20. [20] Y. Si, X. Du, and Z. Su, “Research on improved YOLOv10 object detection algorithm,” Computer & Telecommunication, Vol.11, pp. 1-5, 2024.
21. [21] Z. Cai, X. Ding, Q. Shen and X. Cao, “RefConv: Reparameterized refocusing convolution for powerful ConvNets,” IEEE Trans. on Neural Networks and Learning Systems, Vol.36, No.6, pp. 11617-11631, 2025. https://doi.org/10.1109/TNNLS.2025.3552654