volume | PIER Journals

Abstract

Objective: To enable direct joint prediction of tumor center coordinates and radius in non-imaging ultra-wideband (UWB) breast sensing, we propose an edge-fusion-based graph attention framework for learning from multi-channel backscattered signals without the need for image reconstruction. Methods: Breast models were generated using finite-difference time-domain (FDTD) simulations. Backscattered signals were preprocessed using the dual-tree complex wavelet transform (DTCWT). UWB measurement channels were reformulated as a graph, where each transmitter-receiver channel was treated as a node, and edges were defined by shared antennas. Edge features were fused into graph attention message passing to emphasize more tumor-relevant channels, followed by a multi-task regression head to predict tumor center coordinates and radius. Results: Across four breast density categories, mean center localization error (CLE) remained below 2.5 mm, and the mean of comprehensive overlap index (COI), area recall ratio (ARR), and area precision ratio (APR) exceeded 0.50 in all models. These results indicate effective joint localization and size estimation across heterogeneous breast models.

1. Bray, Freddie, Mathieu Laversanne, Hyuna Sung, Jacques Ferlay, Rebecca L. Siegel, Isabelle Soerjomataram, and Ahmedin Jemal, "Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries," CA: A Cancer Journal for Clinicians, Vol. 74, No. 3, 229-263, 2024.
doi:10.3322/caac.21834 Google Scholar

2. Hwang, E. Shelley, Daphne Y. Lichtensztajn, Scarlett Lin Gomez, Barbara Fowble, and Christina A. Clarke, "Survival after lumpectomy and mastectomy for early stage invasive breast cancer: The effect of age and hormone receptor status," Cancer, Vol. 119, No. 7, 1402-1411, 2013.
doi:10.1002/cncr.27795 Google Scholar

3. Giaquinto, Angela N., Hyuna Sung, Kimberly D. Miller, Joan L. Kramer, Lisa A. Newman, Adair Minihan, Ahmedin Jemal, and Rebecca L. Siegel, "Breast cancer statistics, 2022," CA: A Cancer Journal for Clinicians, Vol. 72, No. 6, 524-541, 2022.
doi:10.3322/caac.21754 Google Scholar

4. Lazebnik, Mariya, Dijana Popovic, Leah McCartney, Cynthia B. Watkins, Mary J. Lindstrom, Josephine Harter, Sarah Sewall, Travis Ogilvie, Anthony Magliocco, Tara M. Breslin, et al. "A large-scale study of the ultrawideband microwave dielectric properties of normal, benign and malignant breast tissues obtained from cancer surgeries," Physics in Medicine & Biology, Vol. 52, No. 20, 6093-6115, 2007.
doi:10.1088/0031-9155/52/20/002 Google Scholar

5. Lu, Min, Xia Xiao, Yanwei Pang, Guancong Liu, and Hong Lu, "Detection and localization of breast cancer using UWB microwave technology and CNN-LSTM framework," IEEE Transactions on Microwave Theory and Techniques, Vol. 70, No. 11, 5085-5094, Nov. 2022.
doi:10.1109/tmtt.2022.3209679 Google Scholar

6. Hagness, S. C., A. Taflove, and J. E. Bridges, "Two-dimensional FDTD analysis of a pulsed microwave confocal system for breast cancer detection: Fixed-focus and antenna-array sensors," IEEE Transactions on Biomedical Engineering, Vol. 45, No. 12, 1470-1479, 1998.
doi:10.1109/10.730440 Google Scholar

7. Lim, Hooi Been, Nguyen Thi Tuyet Nhung, Er-Ping Li, and Nguyen Duc Thang, "Confocal microwave imaging for breast cancer detection: Delay-multiply-and-sum image reconstruction algorithm," IEEE Transactions on Biomedical Engineering, Vol. 55, No. 6, 1697-1704, Jun. 2008.
doi:10.1109/tbme.2008.919716 Google Scholar

8. Miao, Zhenzhuang and Panagiotis Kosmas, "Multiple-frequency DBIM-TwIST algorithm for microwave breast imaging," IEEE Transactions on Antennas and Propagation, Vol. 65, No. 5, 2507-2516, 2017.
doi:10.1109/tap.2017.2679067 Google Scholar

9. Awasthi, Shruti and Priyanka Jain, "The application of a novel clutter removal algorithm to SAR beamforming in breast microwave imaging," Biomedical Signal Processing and Control, Vol. 100, 107017, 2025.
doi:10.1016/j.bspc.2024.107017 Google Scholar

10. Wang, Jingjing, Mengmeng Zhang, Yuxi Bai, Huaqing Xu, and Yucheng Fan, "Distance compensation-based dual adaptive artifact removal algorithm in microwave breast tumor imaging system," Biomedical Signal Processing and Control, Vol. 88, 105598, 2024.
doi:10.1016/j.bspc.2023.105598 Google Scholar

11. Karam, Seyyed Abbas Shah, Declan O'Loughlin, and Babak Mohammadzadeh Asl, "A novel sophisticated form of DMAS beamformer: Application to breast cancer detection," Biomedical Signal Processing and Control, Vol. 74, 103516, 2022.
doi:10.1016/j.bspc.2022.103516 Google Scholar

12. Franceschini, Stefano, Maria Maddalena Autorino, Michele Ambrosanio, Vito Pascazio, and Fabio Baselice, "A deep learning approach for diagnosis support in breast cancer microwave tomography," Diagnostics, Vol. 13, No. 10, 1693, 2023.
doi:10.3390/diagnostics13101693 Google Scholar

13. Zardi, Francesco, Luca Tosi, Marco Salucci, and Andrea Massa, "A physics-driven AI approach for microwave imaging of breast tumors," IEEE Transactions on Antennas and Propagation, Vol. 73, No. 7, 4661-4676, Jul. 2025.
doi:10.1109/tap.2025.3547392 Google Scholar

14. Liu, Guancong, Xia Xiao, Hang Song, and Takamaro Kikkawa, "Precise detection of early breast tumor using a novel EEMD-based feature extraction approach by UWB microwave," Medical & Biological Engineering & Computing, Vol. 59, No. 3, 721-731, 2021.
doi:10.1007/s11517-021-02339-5 Google Scholar

15. Conceição, Raquel C., Hugo Medeiros, Daniela M. Godinho, Martin O'Halloran, Diego Rodriguez-Herrera, Daniel Flores-Tapia, and Stephen Pistorius, "Classification of breast tumor models with a prototype microwave imaging system," Medical Physics, Vol. 47, No. 4, 1860-1870, 2020.
doi:10.1002/mp.14064 Google Scholar

16. Borghouts, Marijn, Michele Ambrosanio, Stefano Franceschini, Maria Maddalena Autorino, Vito Pascazio, and Fabio Baselice, "Microwave breast sensing via deep learning for tumor spatial localization by probability maps," Bioengineering, Vol. 10, No. 10, 1153, 2023.
doi:10.3390/bioengineering10101153 Google Scholar

17. Rana, Soumya Prakash, Maitreyee Dey, Riccardo Loretoni, Michele Duranti, Mohammad Ghavami, Sandra Dudley, and Gianluigi Tiberi, "Radiation-free microwave technology for breast lesion detection using supervised machine learning model," Tomography, Vol. 9, No. 1, 105-129, Jan. 2023.
doi:10.3390/tomography9010010 Google Scholar

18. Wang, Congjing, Yifei Wang, Pengju Ding, Shan Li, Xu Yu, and Bin Yu, "ML-FGAT: Identification of multi-label protein subcellular localization by interpretable graph attention networks and feature-generative adversarial networks," Computers in Biology and Medicine, Vol. 170, 107944, 2024.
doi:10.1016/j.compbiomed.2024.107944 Google Scholar

19. Tian, Yuchuan, Hanting Chen, Chao Xu, and Yunhe Wang, "Image processing GNN: Breaking rigidity in super-resolution," 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 24108-24117, Seattle, WA, USA, 2024.
doi:10.1109/CVPR52733.2024.02276

20. Yu, Haiyao, Changyang She, Yunkai Hu, Geng Wang, Rui Wang, Branka Vucetic, and Yonghui Li, "Floor-plan-aided indoor localization: Zero-shot learning framework, data sets, and prototype," IEEE Journal on Selected Areas in Communications, Vol. 42, No. 9, 2472-2486, Sep. 2024.
doi:10.1109/jsac.2024.3413994 Google Scholar

21. Vrahatis, Aristidis G., Konstantinos Lazaros, and Sotiris Kotsiantis, "Graph attention networks: A comprehensive review of methods and applications," Future Internet, Vol. 16, No. 9, 318, 2024.
doi:10.3390/fi16090318 Google Scholar

22. Lazebnik, Mariya, Michal Okoniewski, John H. Booske, and Susan C. Hagness, "Highly accurate Debye models for normal and malignant breast tissue dielectric properties at microwave frequencies," IEEE Microwave and Wireless Components Letters, Vol. 17, No. 12, 822-824, 2007.
doi:10.1109/lmwc.2007.910465 Google Scholar

23. Zastrow, Earl, Shakti K. Davis, Mariya Lazebnik, Frederick Kelcz, Barry D. Van Veen, and Susan C. Hagness, "Development of anatomically realistic numerical breast phantoms with accurate dielectric properties for modeling microwave interactions with the human breast," IEEE Transactions on Biomedical Engineering, Vol. 55, No. 12, 2792-2800, 2008.
doi:10.1109/tbme.2008.2002130 Google Scholar

24. Scarselli, Franco, Marco Gori, Ah Chung Tsoi, Markus Hagenbuchner, and Gabriele Monfardini, "The graph neural network model," IEEE Transactions on Neural Networks, Vol. 20, No. 1, 61-80, Jan. 2009.
doi:10.1109/tnn.2008.2005605 Google Scholar

25. Kingsbury, Nick, "The dual-tree complex wavelet transform: A new efficient tool for image restoration and enhancement," 9th European Signal Processing Conference (EUSIPCO 1998), 1-4, Rhodes, Greece, 1998.

26. Veličković, Petar, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio, "Graph attention networks," arXiv preprint arXiv:1710.10903, 2017.
doi:10.48550/arXiv.1710.10903 Google Scholar

27. Lu, Min, Xia Xiao, Guancong Liu, and Hong Lu, "Microwave breast tumor localization using wavelet feature extraction and genetic algorithm-neural network," Medical Physics, Vol. 48, No. 10, 6080-6093, 2021.
doi:10.1002/mp.15198 Google Scholar

28. Bayat, İbrahim Halil, İbrahim Akduman, and Semih DoĞu, "Convolutional neural network for joint detection and material classification of breast tumors," 2025 9th International Symposium on Innovative Approaches in Smart Technologies (ISAS), 1-4, Gaziantep, Turkiye, 2025.
doi:10.1109/ISAS66241.2025.11101770

Ms. Hongchao Xie

Professor Xia Xiao

Dr. Yu Liu

Dr. Min Lu