当前位置: X-MOL 学术Ultrasonics › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
DSWE-Net: A Deep Learning Approach for Shear Wave Elastography and Lesion Segmentation Using Single Push Acoustic Radiation Force
Ultrasonics ( IF 3.8 ) Pub Date : 2021-02-01 , DOI: 10.1016/j.ultras.2020.106283
Shahed Ahmed , Uday Kamal , Md. Kamrul Hasan

Ultrasound-based non-invasive elasticity imaging modalities have received significant consideration for tissue characterization over the last few years. Though substantial advances have been made, the conventional Shear Wave Elastography (SWE) methods still suffer from poor image quality in regions far from the push location, particularly those which rely on single focused ultrasound push beam to generate shear waves. In this study, we propose DSWE-Net, a novel deep learning-based approach that is able to construct Young's modulus maps from ultrasonically tracked tissue velocity data resulting from a single acoustic radiation force (ARF) push. The proposed network employs a 3D convolutional encoder, followed by a recurrent block consisting of several Convolutional Long Short-Term Memory (ConvLSTM) layers to extract high-level spatio-temporal features from different time-frames of the input velocity data. Finally, a pair of coupled 2D convolutional decoder blocks reconstructs the modulus image and additionally performs inclusion segmentation by generating a binary mask. We also propose a multi-task learning loss function for end-to-end training of the network with 1260 data samples obtained from a simulation environment which include both bi-level and multi-level phantom structures. The performance of the proposed network is evaluated on 140 synthetic test data and the results are compared both qualitatively and quantitatively with that of the current state of the art method, Local Phase Velocity Based Imaging (LPVI). With an average SSIM of 0.90, RMSE of 0.10 and 20.69 dB PSNR, DSWE-Net performs much better on the imaging task compared to LPVI. Our method also achieves an average IoU score of 0.81 for the segmentation task which makes it suitable for localizing inclusions as well. In this initial study, we also show that our method gains an overall improvement of 0.09 in SSIM, 4.81 dB in PSNR, 2.02 dB in CNR, and 0.09 in RMSE over LPVI on a completely unseen set of CIRS tissue mimicking phantom data. This proves its better generalization capability and shows its potential for use in real-world clinical practice.

中文翻译:

DSWE-Net:使用单推声辐射力进行剪切波弹性成像和病变分割的深度学习方法

在过去几年中,基于超声的非侵入性弹性成像方式在组织表征方面得到了重要考虑。尽管已经取得了实质性的进步,但传统的剪切波弹性成像 (SWE) 方法在远离推动位置的区域仍然存在图像质量差的问题,尤其是那些依靠单聚焦超声推动束产生剪切波的方法。在这项研究中,我们提出了 DSWE-Net,这是一种基于深度学习的新型方法,能够根据由单个声辐射力 (ARF) 推动产生的超声波跟踪组织速度数据构建杨氏模量图。提议的网络采用 3D 卷积编码器,然后是一个由几个卷积长短期记忆 (ConvLSTM) 层组成的循环块,用于从输入速度数据的不同时间帧中提取高级时空特征。最后,一对耦合的 2D 卷积解码器块重建模数图像,并通过生成二进制掩码额外执行包含分割。我们还提出了一种多任务学习损失函数,用于网络的端到端训练,其中包含从模拟环境中获得的 1260 个数据样本,其中包括双层和多层幻影结构。所提出的网络的性能在 140 个综合测试数据上进行了评估,并将结果与​​当前最先进的方法——基于局部相速度的成像 (LPVI) 的结果进行了定性和定量的比较。与 LPVI 相比,DSWE-Net 的平均 SSIM 为 0.90、RMSE 为 0.10 和 20.69 dB PSNR,在成像任务上的表现要好得多。我们的方法还为分割任务实现了 0.81 的平均 IoU 分数,这使其也适用于定位包含物。在这项初步研究中,我们还表明,在一组完全看不见的 CIRS 组织模拟幻影数据上,我们的方法在 SSIM 中获得了 0.09、PSNR 中 4.81 dB、CNR 中 2.02 dB 和 LPVI 中 0.09 的 RMSE 整体改进。这证明了其更好的泛化能力,并显示了其在实际临床实践中的应用潜力。在这项初步研究中,我们还表明,在一组完全看不见的 CIRS 组织模拟幻影数据上,我们的方法在 SSIM 中获得了 0.09、PSNR 中 4.81 dB、CNR 中 2.02 dB 和 LPVI 中 0.09 的 RMSE 整体改进。这证明了其更好的泛化能力,并显示了其在实际临床实践中的应用潜力。在这项初步研究中,我们还表明,在一组完全看不见的 CIRS 组织模拟幻影数据上,我们的方法在 SSIM 中获得了 0.09、PSNR 中 4.81 dB、CNR 中 2.02 dB 和 LPVI 中 0.09 的 RMSE 整体改进。这证明了其更好的泛化能力,并显示了其在实际临床实践中的应用潜力。
更新日期:2021-02-01
down
wechat
bug