Fast ultrasonic imaging using end-to-end deep learning

被引:0
|
作者
Pilikos, Georgios [1 ]
Horchens, Lars [2 ]
Batenburg, Kees Joost [1 ,3 ]
van Leeuwen, Tristan [1 ,4 ]
Lucka, Felix [1 ,5 ]
机构
[1] Ctr Wiskunde & Informat, Computat Imaging, Amsterdam, Netherlands
[2] Applus E&I Technol Ctr, Rotterdam, Netherlands
[3] Leiden Univ, Leiden Inst Adv Comp Sci, Leiden, Netherlands
[4] Univ Utrecht, Math Inst, Utrecht, Netherlands
[5] UCL, Ctr Med Image Comp, London, England
基金
荷兰研究理事会;
关键词
deep learning; end-to-end training; Delay-And-Sum; fast ultrasonic imaging; approximate inversion;
D O I
暂无
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Ultrasonic imaging algorithms used in many clinical and industrial applications consist of three steps: A data pre-processing, an image formation and an image post-processing step. For efficiency, image formation often relies on an approximation of the underlying wave physics. A prominent example is the Delay-And-Sum (DAS) algorithm used in reflectivity-based ultrasonic imaging. Recently, deep neural networks (DNNs) are being used for the data pre-processing and the image post-processing steps separately. In this work, we propose a novel deep learning architecture that integrates all three steps to enable end-to-end training. We examine turning the DAS image formation method into a network layer that connects data pre-processing layers with image post-processing layers that perform segmentation. We demonstrate that this integrated approach clearly outperforms sequential approaches that are trained separately. While network training and evaluation is performed only on simulated data, we also showcase the potential of our approach on real data from a non-destructive testing scenario.
引用
收藏
页数:4
相关论文
共 50 条
  • [1] Automated Classification Using End-to-End Deep Learning
    Jaipurkar, Shobhit Sandeep
    Jie, Wang
    Zeng, Zeng
    Gee, Teo Sin
    Veeravalli, Bharadwaj
    Chua, Matthew
    [J]. 2018 40TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2018, : 706 - 709
  • [2] Traffic Signal Recognition Using End-to-End Deep Learning
    Sarker, Tonmoy
    Meng, Xiangyu
    [J]. TRAN-SET 2022, 2022, : 182 - 191
  • [3] Arabic speech recognition using end-to-end deep learning
    Alsayadi, Hamzah A.
    Abdelhamid, Abdelaziz A.
    Hegazy, Islam
    Fayed, Zaki T.
    [J]. IET SIGNAL PROCESSING, 2021, 15 (08) : 521 - 534
  • [4] End-to-end online quality prediction for ultrasonic metal welding using sensor fusion and deep learning
    Wu, Yulun
    Meng, Yuquan
    Shao, Chenhui
    [J]. JOURNAL OF MANUFACTURING PROCESSES, 2022, 83 : 685 - 694
  • [5] DeepDive: An End-to-End Dehazing Method Using Deep Learning
    Goncalves, Lucas T.
    Gaya, Joel O.
    Drews, Paulo, Jr.
    Botelho, Silvia S. C.
    [J]. 2017 30TH SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 2017, : 436 - 441
  • [6] Autonomous Driving Control Using End-to-End Deep Learning
    Lee, Myoung-jae
    Ha, Young-guk
    [J]. 2020 IEEE INTERNATIONAL CONFERENCE ON BIG DATA AND SMART COMPUTING (BIGCOMP 2020), 2020, : 470 - 473
  • [7] AmyloidPETNet: Classification of Amyloid Positivity in Brain PET Imaging Using End-to-End Deep Learning
    Fan, Shuyang
    Ponisio, Maria Rosana
    Xiao, Pan
    Ha, Sung Min
    Chakrabarty, Satrajit
    Lee, John J.
    Flores, Shaney
    LaMontagne, Pamela
    Gordon, Brian
    Raji, Cyrus A.
    Marcus, Daniel S.
    Nazeri, Arash
    Ances, Beau M.
    Bateman, Randall J.
    Morris, John C.
    Benzinger, Tammie L. S.
    Sotiras, Aristeidis
    [J]. RADIOLOGY, 2024, 311 (03)
  • [8] Fast End-to-End Deep Learning Identity Document Detection, Classification and Cropping
    Chiron, Guillaume
    Arrestier, Florian
    Awal, Ahmad Montaser
    [J]. DOCUMENT ANALYSIS AND RECOGNITION, ICDAR 2021, PT IV, 2021, 12824 : 333 - 347
  • [9] Fast end-to-end learning on protein surfaces
    Sverrisson, Freyr
    Feydy, Jean
    Correia, Bruno E.
    Bronstein, Michael M.
    [J]. 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 15267 - 15276
  • [10] End-to-End Deep Learning for Robotic Following
    Pierre, John M.
    [J]. ICMSCE 2018: PROCEEDINGS OF THE 2018 2ND INTERNATIONAL CONFERENCE ON MECHATRONICS SYSTEMS AND CONTROL ENGINEERING, 2015, : 77 - 85