Deep Learning to Obtain Simultaneous Image and Segmentation Outputs From a Single Input of Raw Ultrasound Channel Data

Arun Asokan Nair; Kendra N. Washington; Trac D. TranAustin ReiterMuyinatu A. Lediju Bell

首页> 外文期刊>IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control >Deep Learning to Obtain Simultaneous Image and Segmentation Outputs From a Single Input of Raw Ultrasound Channel Data

【24h】

Deep Learning to Obtain Simultaneous Image and Segmentation Outputs From a Single Input of Raw Ultrasound Channel Data

机译：Deep Learning to Obtain Simultaneous Image and Segmentation Outputs From a Single Input of Raw Ultrasound Channel Data

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相关主题

摘要

Single plane wave transmissions are promising for automated imaging tasks requiring high ultrasound frame rates over an extended field of view. However, a single plane wave insonification typically produces suboptimal image quality. To address this limitation, we are exploring the use of deep neural networks (DNNs) as an alternative to delay-and-sum (DAS) beamforming. The objectives of this work are to obtain information directly from raw channel data and to simultaneously generate both a segmentation map for automated ultrasound tasks and a corresponding ultrasound B-mode image for interpretable supervision of the automation. We focus on visualizing and segmenting anechoic targets surrounded by tissue and ignoring or deemphasizing less important surrounding structures. DNNs trained with Field II simulations were tested with simulated, experimental phantom, and amp;italicamp;in vivoamp;/italicamp; data sets that were not included during training. With unfocused input channel data (i.e., prior to the application of receive time delays), simulated, experimental phantom, and amp;italicamp;in vivoamp;/italicamp; test data sets achieved mean ± standard deviation Dice similarity coefficients of 0.92 ± 0.13, 0.92 ± 0.03, and 0.77 ± 0.07, respectively, and generalized contrast-to-noise ratios (gCNRs) of 0.95 ± 0.08, 0.93 ± 0.08, and 0.75 ± 0.14, respectively. With subaperture beamformed channel data and a modification to the input layer of the DNN architecture to accept these data, the fidelity of image reconstruction increased (e.g., mean gCNR of multiple acquisitions of two amp;italicamp;in vivoamp;/italicamp; breast cysts ranged 0.89–0.96), but DNN display frame rates were reduced from 395 to 287 Hz. Overall, the DNNs successfully translated feature representations learned from simulated data to phantom and amp;italicamp;in vivoamp;/italicamp; data, which is promising for this novel approach to simultaneous ultrasound image formation and segmentation.

著录项

来源
《IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control》 |2020年第12期|2493-2509|共17页
作者
Arun Asokan Nair; Kendra N. Washington; Trac D. TranAustin ReiterMuyinatu A. Lediju Bell;
展开▼
作者单位

Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA;

Department of Biomedical Engineering, Georgia Institute of Technology, Atlanta, GA, USA;

Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA;

展开▼
收录信息
原文格式 PDF
正文语种英语
中图分类无线电设备、电信设备;
关键词
Ultrasonic imaging; Image segmentation; Training; Task analysis; Array signal processing; Machine learning; Decoding; Beamforming; deep learning; fully convolutional neural network (FCNN); image segmentation; neural network;

Deep Learning to Obtain Simultaneous Image and Segmentation Outputs From a Single Input of Raw Ultrasound Channel Data

摘要

著录项

相关主题

期刊订阅