Solving inverse problems using data-driven models

Acta Numerica, Год журнала: 2019, Номер 28, С. 1 - 174

Опубликована: Май 1, 2019

Recent research in inverse problems seeks to develop a mathematically coherent foundation for combining data-driven models, and particular those based on deep learning, with domain-specific knowledge contained physical–analytical models. The focus is solving ill-posed that are at the core of many challenging applications natural sciences, medicine life as well engineering industrial applications. This survey paper aims give an account some main contributions problems.

Язык: Английский

---

Single-breath-hold photoacoustic computed tomography of the breast

Nature Communications, Год журнала: 2018, Номер 9(1)

Опубликована: Июнь 11, 2018

We have developed a single-breath-hold photoacoustic computed tomography (SBH-PACT) system to reveal detailed angiographic structures in human breasts. SBH-PACT features deep penetration depth (4 cm vivo) with high spatial and temporal resolutions (255 µm in-plane resolution 10 Hz 2D frame rate). By scanning the entire breast within single breath hold (~15 s), volumetric image can be acquired subsequently reconstructed utilizing 3D back-projection negligible breathing-induced motion artifacts. clearly reveals tumors by observing higher blood vessel densities associated at resolution, showing early promise for sensitivity radiographically dense In addition imaging, imaging speed enables dynamic studies, such as elastography, which identifies less compliance. imaged cancer patients sizes ranging from B cup DD cup, skin pigmentations light dark. identified all without resorting ionizing radiation or exogenous contrast, posing no health risks.

Язык: Английский

---

Model-Based Learning for Accelerated, Limited-View 3-D Photoacoustic Tomography

IEEE Transactions on Medical Imaging, Год журнала: 2018, Номер 37(6), С. 1382 - 1393

Опубликована: Март 29, 2018

Recent advances in deep learning for tomographic reconstructions have shown great potential to create accurate and high quality images with a considerable speed up. In this paper, we present neural network that is specifically designed provide resolution 3-D from restricted photoacoustic measurements. The represent an iterative scheme incorporates gradient information of the data fit compensate limited view artifacts. Due complexity forward operator, separate training computation information. A suitable prior desired image structures learned as part training. resulting trained tested on set segmented vessels lung computed tomography scans then applied in-vivo measurement data.

Язык: Английский

---

Medical Imaging of Microrobots: Toward In Vivo Applications

ACS Nano, Год журнала: 2020, Номер 14(9), С. 10865 - 10893

Опубликована: Сен. 1, 2020

Medical microrobots (MRs) have been demonstrated for a variety of non-invasive biomedical applications, such as tissue engineering, drug delivery, and assisted fertilization, among others. However, most these demonstrations carried out in vitro settings under optical microscopy, being significantly different from the clinical practice. Thus, medical imaging techniques are required localizing tracking tiny therapeutic machines when used medical-relevant applications. This review aims at analyzing state art by critically discussing potentialities limitations employed this field. Moreover, physics working principle behind each analyzed strategy, spatiotemporal resolution, penetration depth thoroughly discussed. The paper deals with suitability technique single or swarms MRs discusses scenarios where contrast agent's inclusion is required, either to absorb, emit, reflect determined physical signal detected an external system. Finally, highlights existing challenges perspective solutions which could be promising future vivo

Язык: Английский

---

Recent advances toward preclinical and clinical translation of photoacoustic tomography: a review

Journal of Biomedical Optics, Год журнала: 2016, Номер 22(4), С. 041006 - 041006

Опубликована: Ноя. 22, 2016

Photoacoustic imaging is an emerging hybrid modality that can provide multicontrast, multiscale of biological features ranging from organelles to organs. The three major embodiments photoacoustic are microscopy, endoscopy, and computed tomography. tomography (PAT) or allows deep-tissue imaging, hence it more suitable for whole body preclinical/clinical applications. Due fast-growing laser technology ultrasound detector technology, PAT evolving rapidly, leading a quicker translation into clinical trials. We review the recent developments systems their applications in preclinical practices.

Язык: Английский

---

Double-Stage Delay Multiply and Sum Beamforming Algorithm: Application to Linear-Array Photoacoustic Imaging

IEEE Transactions on Biomedical Engineering, Год журнала: 2017, Номер 65(1), С. 31 - 42

Опубликована: Апрель 5, 2017

Photoacoustic imaging (PAI) is an emerging medical modality capable of providing high spatial resolution Ultrasound (US) and contrast optical imaging. Delay-and-Sum (DAS) the most common beamforming algorithm in PAI. However, using DAS beamformer leads to low images considerable contribution off-axis signals. A new paradigm namely delay-multiply-and-sum (DMAS), which was originally used as a reconstruction confocal microwave imaging, introduced overcome challenges DAS. DMAS PAI systems it shown that this results improvement sidelobe degrading. still sensitive levels noise, not satisfying. Here, we propose novel based on algebra inside formula expansion, double stage (DS-DMAS), improves image sidelobe, much less level noise compared DMAS. The performance DS-DMAS evaluated numerically experimentally. resulted are qualitatively quantitatively established quality metrics including signal-to-noise ratio (SNR), full-width-half-maximum (FWHM) (CR). It outperforms at expense higher computational load. reduces lateral valley for about 15 dB SNR FWHM better than 13% 30%, respectively. Moreover, reduced 10 comparison with those

Язык: Английский

---

Current and future trends in photoacoustic breast imaging

Photoacoustics, Год журнала: 2019, Номер 16, С. 100134 - 100134

Опубликована: Июнь 30, 2019

Non-invasive detection of breast cancer has been regarded as the holy grail applications for photoacoustic (optoacoustic) imaging right from early days re-discovery method. Two-and-a-half decades later we report on state-of-the-art in technology and clinical studies. Even within single application imaging, find imagers with various measurement geometries, ultrasound characteristics, illumination schemes, image reconstruction strategies. We first analyze implications performance a few these design choices generic system, before going into detailed descriptions imagers. Per system present highlights patient studies, which barring couple are mostly nature demonstrations proof-of-principle close this work discussion several aspects that may turn out to be crucial future translation

Язык: Английский

---

Photoacoustic imaging in the second near-infrared window: a review

Journal of Biomedical Optics, Год журнала: 2019, Номер 24(04), С. 1 - 1

Опубликована: Апрель 9, 2019

Photoacoustic (PA) imaging is an emerging medical modality that combines optical excitation and ultrasound detection. Because scatters much less than light in biological tissues, PA generates high-resolution images at centimeters depth. In recent years, wavelengths the second near-infrared (NIR-II) window (1000 to 1700 nm) have been increasingly explored due its potential for preclinical clinical applications. contrast conventional visible (400 700 first NIR-I (700 1000 window, NIR-II offers numerous advantages, including high spatial resolution, deeper penetration depth, reduced absorption, tissue scattering. Moreover, allows a fivefold higher energy density compared enhancing depth significantly. We highlight importance of discuss various systems agents with strong absorption spectral region. Numerous applications imaging, whole-body animal human are also discussed.

Язык: Английский

---

High-speed three-dimensional photoacoustic computed tomography for preclinical research and clinical translation

Nature Communications, Год журнала: 2021, Номер 12(1)

Опубликована: Фев. 9, 2021

Abstract Photoacoustic computed tomography (PACT) has generated increasing interest for uses in preclinical research and clinical translation. However, the imaging depth, speed, quality of existing PACT systems have previously limited potential applications this technology. To overcome these issues, we developed a three-dimensional photoacoustic (3D-PACT) system that features large scalable field view with isotropic spatial resolution, high superior image quality. 3D-PACT allows multipurpose to reveal detailed angiographic information biological tissues ranging from rodent brain human breast. In rat brain, visualize whole vasculatures hemodynamics. breast, an vivo depth 4 cm is achieved by scanning breast within single breath hold 10 s. Here, introduce provide unique tool appealing prototype

Язык: Английский

---

Recent Advances in Contrast-Enhanced Photoacoustic Imaging: Overcoming the Physical and Practical Challenges

Chemical Reviews, Год журнала: 2023, Номер 123(11), С. 7379 - 7419

Опубликована: Янв. 16, 2023

For decades now, photoacoustic imaging (PAI) has been investigated to realize its potential as a niche biomedical modality. Despite highly desirable optical contrast and ultrasonic spatiotemporal resolution, PAI is challenged by such physical limitations low signal-to-noise ratio (SNR), diminished image due strong attenuation, lower-bound on spatial resolution in deep tissue. In addition, contrast-enhanced faced practical insufficient cell-specific targeting delivery efficiency difficulties developing clinically translatable agents. Identifying these essential the continuing expansion of field, substantial advances contrast-enhancing agents, complemented high-performance acquisition systems, have synergistically dealt with challenges conventional PAI. This review covers past four years research pushing terms SNR/contrast, targeted delivery, clinical application. Promising strategies for dealing each challenge are reviewed detail, future directions next generation discussed.

Язык: Английский

---