AI-powered ultrasonic thermometry for HIFU therapy in deep organ

IF 8.7 1区化学 Q1 ACOUSTICS

Ultrasonics Sonochemistry Pub Date : 2024-11-12 DOI:10.1016/j.ultsonch.2024.107154

Shunyao Luan , Yongshuo Ji , Yumei Liu , Linling Zhu , Hong Zhao , Haoyu Zhou , Ke Li , Weizhen Zhu , Benpeng Zhu

{"title":"AI-powered ultrasonic thermometry for HIFU therapy in deep organ","authors":"Shunyao Luan , Yongshuo Ji , Yumei Liu , Linling Zhu , Hong Zhao , Haoyu Zhou , Ke Li , Weizhen Zhu , Benpeng Zhu","doi":"10.1016/j.ultsonch.2024.107154","DOIUrl":null,"url":null,"abstract":"<div><div>High-intensity focused ultrasound (HIFU) is considered as an important non-invasive way for tumor ablation in deep organs. However, accurate real-time monitoring of the temperature field within HIFU focal area remains a challenge. Although ultrasound technology, compared with other approaches, is a good choice for noninvasive and real-time monitoring on the temperature distribution, traditional ultrasonic thermometry mainly relies on the backscattered signal, which is difficult for high temperature (>50 °C) measurement. Given that artificial intelligence (AI) shows significant potential for biomedical applications, we propose an AI-powered ultrasonic thermometry using an end-to-end deep neural network termed Breath-guided Multimodal Teacher-Student (BMTS), which possesses the capability to elucidate the interaction between HIFU and complex heterogeneous biological media. It has been demonstrated experimentally that two-dimension temperature distribution within HIFU focal area in deep organ can be accurately reconstructed with an average error and a frame speed of 0.8 °C and 0.37 s, respectively. Most importantly, the maximum measurable temperature for ultrasonic technology has been successfully expanded to a record value of 67 °C. This breakthrough indicates that the development of AI-powered ultrasonic thermometry is beneficial for precise HIFU therapy planning in the future.</div></div>","PeriodicalId":442,"journal":{"name":"Ultrasonics Sonochemistry","volume":"111 ","pages":"Article 107154"},"PeriodicalIF":8.7000,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ultrasonics Sonochemistry","FirstCategoryId":"92","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1350417724004036","RegionNum":1,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ACOUSTICS","Score":null,"Total":0}

引用次数: 0

Abstract

High-intensity focused ultrasound (HIFU) is considered as an important non-invasive way for tumor ablation in deep organs. However, accurate real-time monitoring of the temperature field within HIFU focal area remains a challenge. Although ultrasound technology, compared with other approaches, is a good choice for noninvasive and real-time monitoring on the temperature distribution, traditional ultrasonic thermometry mainly relies on the backscattered signal, which is difficult for high temperature (>50 °C) measurement. Given that artificial intelligence (AI) shows significant potential for biomedical applications, we propose an AI-powered ultrasonic thermometry using an end-to-end deep neural network termed Breath-guided Multimodal Teacher-Student (BMTS), which possesses the capability to elucidate the interaction between HIFU and complex heterogeneous biological media. It has been demonstrated experimentally that two-dimension temperature distribution within HIFU focal area in deep organ can be accurately reconstructed with an average error and a frame speed of 0.8 °C and 0.37 s, respectively. Most importantly, the maximum measurable temperature for ultrasonic technology has been successfully expanded to a record value of 67 °C. This breakthrough indicates that the development of AI-powered ultrasonic thermometry is beneficial for precise HIFU therapy planning in the future.

查看原文本刊更多论文

用于深部器官 HIFU 治疗的人工智能超声波测温仪。

高强度聚焦超声（HIFU）被认为是深部器官肿瘤消融的重要非侵入性方法。然而，对 HIFU 聚焦区内的温度场进行准确的实时监测仍是一项挑战。虽然与其他方法相比，超声技术是无创实时监测温度分布的良好选择，但传统的超声测温主要依赖于背向散射信号，难以进行高温（>50 °C）测量。鉴于人工智能（AI）在生物医学应用中的巨大潜力，我们提出了一种使用端到端深度神经网络（称为 "呼吸引导多模态师生"（BMTS））的人工智能驱动的超声波测温仪，它具有阐明 HIFU 与复杂的异质生物介质之间相互作用的能力。实验证明，深部器官中 HIFU 焦点区域内的二维温度分布可以准确重建，平均误差和帧速分别为 0.8 °C 和 0.37 秒。最重要的是，超声波技术的最高可测量温度已成功扩展到创纪录的 67 ℃。这一突破表明，人工智能驱动的超声波测温技术的发展有利于未来精确的 HIFU 治疗规划。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Ultrasonics Sonochemistry 化学-化学综合

CiteScore

15.80

自引率

11.90%

发文量

361

审稿时长

59 days

期刊介绍： Ultrasonics Sonochemistry stands as a premier international journal dedicated to the publication of high-quality research articles primarily focusing on chemical reactions and reactors induced by ultrasonic waves, known as sonochemistry. Beyond chemical reactions, the journal also welcomes contributions related to cavitation-induced events and processing, including sonoluminescence, and the transformation of materials on chemical, physical, and biological levels. Since its inception in 1994, Ultrasonics Sonochemistry has consistently maintained a top ranking in the "Acoustics" category, reflecting its esteemed reputation in the field. The journal publishes exceptional papers covering various areas of ultrasonics and sonochemistry. Its contributions are highly regarded by both academia and industry stakeholders, demonstrating its relevance and impact in advancing research and innovation.