Learning sub-sampling and signal recovery with applications in ultrasound imaging

Iris A.M. Huijben (Corresponding author), Bastiaan S. Veeling, Kees Janse, Massimo Mischi, Ruud J. G. van Sloun

Research output: Contribution to journalArticleAcademicpeer-review

39 Citations (Scopus)
17 Downloads (Pure)

Abstract

Limitations on bandwidth and power consumption impose strict bounds on data rates of diagnostic imaging systems. Consequently, the design of suitable (i.e. task- and data-aware) compression and reconstruction techniques has attracted considerable attention in recent years. Compressed sensing emerged as a popular framework for sparse signal reconstruction from a small set of compressed measurements. However, typical compressed sensing designs measure a (non)linearly weighted combination of all input signal elements, which poses practical challenges. These designs are also not necessarily task-optimal. In addition, realtime recovery is hampered by the iterative and time-consuming nature of sparse recovery algorithms. Recently, deep learning methods have shown promise for fast recovery from compressed measurements, but the design of adequate and practical sensing strategies remains a challenge. Here, we propose a deep learning solution termed Deep Probabilistic Sub-sampling (DPS), that enables joint optimization of a task-adaptive sub-sampling pattern and a subsequent neural task model in an end-to-end fashion. Once learned, the task-based sub-sampling patterns are fixed and straightforwardly implementable, e.g. by non-uniform analog-to-digital conversion, sparse array design, or slow-time ultrasound pulsing schemes. The effectiveness of our framework is demonstrated in-silico for sparse signal recovery from partial Fourier measurements, and in-vivo for both anatomical image and tissue-motion (Doppler) reconstruction from sub-sampled medical ultrasound imaging data.
Original languageEnglish
Article number9138467
Pages (from-to)3955-3966
Number of pages12
JournalIEEE Transactions on Medical Imaging
Volume39
Issue number12
Early online date20 Jul 2020
DOIs
Publication statusPublished - 1 Dec 2020

Keywords

  • Deep learning
  • compressed sensing
  • probabilistic sampling
  • ultrasound imaging

Fingerprint

Dive into the research topics of 'Learning sub-sampling and signal recovery with applications in ultrasound imaging'. Together they form a unique fingerprint.

Cite this