Nondestructive Detection of Targeted Microbubbles Using Dual-Mode Data and Deep Learning for Real-Time Ultrasound Molecular Imaging.
Nondestructive Detection of Targeted Microbubbles Using Dual-Mode Data and Deep Learning for Real-Time Ultrasound Molecular Imaging.
复制标题
DOI：
10.1109/tmi.2020.2986762
复制
发表时间：
2020-10
影响因子：
10.6
通讯作者：
Dahl JJ
中科院分区：
文献类型：
--
作者：
Hyun D;Abou-Elkacem L;Bam R;Brickson LL;Herickhoff CD;Dahl JJ
超声分子成像(UMI)是通过靶向微泡(MBS)实现的，MBS是结合特定生物标志物的高反射超声造影剂。在体内区分附着的MBS和背景信号可能是一项挑战。首选的临床前技术是差分靶向增强(DTE)，其中使用强大的声脉冲来破坏MBS以验证其位置。然而，DTE本质上不能用于实时成像，并且可能会引起不良的生物效应。在这项工作中，我们提出了一种简单的四层卷积神经网络来无损检测附着的MB签名。我们研究了几种类型的网络输入数据：使用IQ通道信号、通道和或通道和幅度的“解剖模式”(基频)、“对比模式”(脉冲反转谐波频率)或两者，即“双模式”。在小鼠体内肿瘤数据和微血管模型上进行训练和评估。双模通道信号产生了最佳的性能，在两个测试图像中获得了0.45的软芯片系数和0.91的AUC。在体积采集中，该网络最好地发现了乳腺癌肿瘤，导致广义对比噪声比(GCNR)为0.93，Kolmogorov-Smirnov统计量(KSS)为0.86，优于常规对比模式成像(GCNR=0.76，KSS=0.53)和DTE成像(GCNR=0.81，KSS=0.62)。有必要进一步发展方法学，以区分自由和附着性住房抵押贷款支持证券。这些结果表明，神经网络可以被训练成使用非破坏性双模数据来检测具有类似DTE质量的目标MBS，并且可以用于促进UMI安全和实时地转换到临床应用。
Ultrasound molecular imaging (UMI) is enabled by targeted microbubbles (MBs), which are highly reflective ultrasound contrast agents that bind to specific biomarkers. Distinguishing between adherent MBs and background signals can be challenging in vivo. The preferred preclinical technique is differential targeted enhancement (DTE), wherein a strong acoustic pulse is used to destroy MBs to verify their locations. However, DTE intrinsically cannot be used for real-time imaging and may cause undesirable bioeffects. In this work, we propose a simple 4-layer convolutional neural network to nondestructively detect adherent MB signatures. We investigated several types of input data to the network: “anatomy-mode” (fundamental frequency), “contrast-mode” (pulse-inversion harmonic frequency), or both, i.e., “dual-mode”, using IQ channel signals, the channel sum, or the channel sum magnitude. Training and evaluation were performed on in vivo mouse tumor data and microvessel phantoms. The dual-mode channel signals yielded optimal performance, achieving a soft Dice coefficient of 0.45 and AUC of 0.91 in two test images. In a volumetric acquisition, the network best detected a breast cancer tumor, resulting in a generalized contrast-to-noise ratio (GCNR) of 0.93 and Kolmogorov-Smirnov statistic (KSS) of 0.86, outperforming both regular contrast mode imaging (GCNR=0.76, KSS=0.53) and DTE imaging (GCNR=0.81, KSS=0.62). Further development of the methodology is necessary to distinguish free from adherent MBs. These results demonstrate that neural networks can be trained to detect targeted MBs with DTE-like quality using nondestructive dual-mode data, and can be used to facilitate the safe and real-time translation of UMI to clinical applications.