Real-time estimation of lesion depth and control of radiofrequency ablation within ex vivo animal tissues using a neural network
Real-time estimation of lesion depth and control of radiofrequency ablation within ex vivo animal tissues using a neural network
复制标题
DOI：
10.1080/02656736.2017.1416495
复制
发表时间：
2018-01-01
影响因子：
3.1
通讯作者：
Sahakian, Alan Varteres
中科院分区：
文献类型：
--
作者：
Wang, Yearnchee Curtis;Chan, Terence Chee-Hung;Sahakian, Alan Varteres
背景：射频消融（RFA）是一种诱导热消融（细胞死亡）的方法，通常用于破坏肿瘤或潜在的癌组织。当前的 RFA 估计技术（电阻抗断层扫描、Nakagami 超声等）需要较长的计算时间 (2 秒) 和除 RFA 设备之外的测量设备。本研究旨在确定神经网络 (NN) 是否可以仅使用 RFA 治疗设备的电极实时估计消融病变深度，以使用复电阻抗控制双极 RFA（因为组织电导率随组织温度变化）。方法：由代表目标组织的牛肝、猪腰肉或五花肉组成的三维立方模型。使用猪腰肉和猪肚中 72 个数据生成消融的温度和复电阻抗来训练神经网络（Xeon 处理器上的 403）。 NN输入为查询深度、起始复阻抗和当前复阻抗。训练-验证-测试比例为 70%-0%-30% 和 80%-10%-10%（过度拟合测试）。一旦 NN 估计的边缘病变深度达到目标病变深度，就停止该组织边缘的 RFA。结果：NN 训练的准确度为 93%，NN 集成控制消融组织的平均距离目标病变深度在 1.0mm 以内。在单核 ARMv7 处理器上，可在 0.2 秒内计算出完整的 15 毫米深度图。结论：结果表明，与当前技术相比，神经网络可以使用更少的原位设备来实时估计病变深度。利用基于神经网络的技术，医生可以提供更快、更精确的消融治疗。
Background: Radiofrequency ablation (RFA), a method of inducing thermal ablation (cell death), is often used to destroy tumours or potentially cancerous tissue. Current techniques for RFA estimation (electrical impedance tomography, Nakagami ultrasound, etc.) require long compute times (2s) and measurement devices other than the RFA device. This study aims to determine if a neural network (NN) can estimate ablation lesion depth for control of bipolar RFA using complex electrical impedance - since tissue electrical conductivity varies as a function of tissue temperature - in real time using only the RFA therapy device's electrodes.Methods: Three-dimensional, cubic models comprised of beef liver, pork loin or pork belly represented target tissue. Temperature and complex electrical impedance from 72 data generation ablations in pork loin and belly were used for training the NN (403s on Xeon processor). NN inputs were inquiry depth, starting complex impedance and current complex impedance. Training-validation-test splits were 70%-0%-30% and 80%-10%-10% (overfit test). Once the NN-estimated lesion depth for a margin reached the target lesion depth, RFA was stopped for that margin of tissue.Results: The NN trained to 93% accuracy and an NN-integrated control ablated tissue to within 1.0mm of the target lesion depth on average. Full 15-mm depth maps were calculated in 0.2s on a single-core ARMv7 processor.Conclusions: The results show that a NN could make lesion depth estimations in real-time using less in situ devices than current techniques. With the NN-based technique, physicians could deliver quicker and more precise ablation therapy.