No abstract

No abstract

No abstract

Focused ultrasound (FUS) therapy has emerged as a promising non-invasive solution for tumor ablation. Accurate monitoring and guidance of ultrasound energy is crucial for effective FUS treatment. Although ultrasound (US) imaging is a well-suited modality for FUS monitoring, US-guided FUS (USgFUS) faces challenges in achieving precise monitoring, leading to unpredictable ablation shapes and a lack of quantitative measurement. To address these challenges, we propose an artificial intelligence (AI)-assisted USgFUS framework that integrates an AI segmentation framework with ultrasound B-mode imaging for quantitative and real-time monitoring of FUS treatment. The AI framework can accurately identify and label ablated areas in the B-mode images captured during and after each FUS sonication procedure in real-time. To assess the feasibility of our proposed method, we developed an AI segmentation framework based on the Swin-Unet architecture and conducted an in vitro experimental study using a USgFUS setup and chicken breast tissue. The results indicated that the developed AI segmentation framework could immediately label the ablated tissue areas with \(93\%\) accuracy. These findings suggest that AI-assisted ultrasound monitoring can significantly improve the precision and accuracy of FUS treatments, suggesting a crucial advancement towards the development of more effective FUS treatment strategies.