International Journal of Bioelectronics

Artificial Intelligence in Microwave Ablation for Cancer Treatment

Abstract

Microwave ablation (MWA) is a minimally invasive medical technique used in cancer treatment, particularly for hepatocellular carcinoma (HCC) and lung tumors. With the integration of artificial intelligence (AI), MWA has achieved significant advancements in precision, planning, and treatment monitoring. This article explores how AI optimizes medical image segmentation, improves recurrence prediction, and adjusts real-time parameters to enhance procedure efficacy and safety. Models such as convolutional neural networks, XGBoost, and U-Net have demonstrated accuracy rates exceeding 90% in tumor identification and treatment planning. Additionally, we discuss the impact of AI on personalized medicine, risk reduction, and resource optimization, along with remaining challenges such as the need for further clinical validation and model interpretability.

Keywords: Artificial intelligence, microwave ablation, cancer, image segmentation, machine learning, neural networks.

Introduction

Microwave ablation uses electromagnetic energy to generate heat and destroy malignant tissues and has proven effective for several cancers (e.g., HCC, lung, and breast). Recent advances in AI are elevating precision and effectiveness across planning, intraoperative guidance, and postoperative analysis.

Highlights

• Personalized planning: XGBoost and RNNs analyze clinical histories to predict early recurrence (AUC > 0.75).
• Segmentation & guidance: U-Net/ResLU-Net achieve >90% accuracy in tumor delineation, reducing local recurrence.
• Energy optimization: Real-time control near sensitive structures reduces recurrence and energy use.
• Safety & failure detection: ML/LLM-based analysis helps anticipate device issues and adverse events.

Conclusion

AI-driven MWA enables more precise, personalized, and efficient therapies by improving segmentation, planning, energy delivery, and safety monitoring, with promising implications for clinical outcomes and cost reduction.

References

1. Segura Félix K, Guerrero López GD, Cepeda Rubio MFJ, Hernández Jacquez JI, Flores García FG, Hernández AV, Salas LL, Orozco Ruiz de la Peña EC. Computational FEM Model and Phantom Validation of Microwave Ablation for Segmental Microcalcifications in Breasts Using a Coaxial Double-Slot Antenna. Biomed Res Int. 2021;2021:8858822. doi:10.1155/2021/8858822.
2. Mahmoodian N, et al. Lung and Lung Tumor Segmentation of CT Images During MWA Therapy Using AI Algorithm. SciMedicine Journal. 2023;5(1):1–12. doi:10.28991/SciMedJ-2023-05-01-01.
3. Gopalakrishnan K, et al. Applications of Microwaves in Medicine Leveraging Artificial Intelligence: Future Perspectives. Electronics. 2023;12:1101. doi:10.3390/electronics12051101.
4. An C, et al. A Machine Learning Model Based on Health Records for Predicting Recurrence After Microwave Ablation of Hepatocellular Carcinoma. Journal of Hepatocellular Carcinoma. 2022:671–684. doi:10.2147/JHC.S358197.
5. Ding W, et al. Artificial intelligence system improved the microwave ablation effect of hepatocellular carcinoma for less-experienced doctors. Preprint. SSRN-4487128.
6. Xu S, Qi J, Li B, Bie ZX, Li YM, Li XG. Risk prediction of pleural effusion in lung malignancy patients treated with CT-guided percutaneous microwave ablation: a nomogram and artificial neural network model. Int J Hyperthermia. 2021;38(1):220–228. doi:10.1080/02656736.2021.1885755.
7. Singh SK, Yadav AN. Machine Learning Approach in Optimal Localization of Tumor Using a Novel SIW-Based Antenna for Improvement of Ablation Zone in HCC. IEEE Access. 2023;11:26964–26978. doi:10.1109/ACCESS.2023.3257869.
8. Brunese L, Mercaldo F, Santone A, Vanoli GP. Thermal Ablation Treatment Detection by means of Machine Learning. IJCNN 2021, Shenzhen, China. doi:10.1109/IJCNN52387.2021.9533696.
9. An C, Yang H, Yu X, Han Z, Cheng Z, Liu F, Dou J, Li B, Li Y, Li Y, Yu J, Liang P. A Machine Learning Model Based on Electronic Health Records for Predicting Recurrence after Microwave Ablation of Hepatocellular Carcinoma. SSRN. doi:10.2139/ssrn.3901789.
10. Pellat A, Barat M, Coriat R, Soyer P, Dohan A. Artificial intelligence: A review of current applications in hepatocellular carcinoma imaging. Diagn Interv Imaging. 2023;104(1):24–36. doi:10.1016/j.diii.2022.10.001.

© 2024 International Journal of Bioelectronics (IJBIOE). Article licensed under CC BY 4.0.