Recent advances in deep-learning-enhanced photoacoustic imaging

Advanced Photonics Nexus, Journal Year: 2023, Volume and Issue: 2(05)

Published: July 24, 2023

Photoacoustic imaging (PAI), recognized as a promising biomedical modality for preclinical and clinical studies, uniquely combines the advantages of optical ultrasound imaging. Despite PAI's great potential to provide valuable biological information, its wide application has been hindered by technical limitations, such hardware restrictions or lack biometric information required image reconstruction. We first analyze limitations PAI categorize them seven key challenges: limited detection, low-dosage light delivery, inaccurate quantification, numerical reconstruction, tissue heterogeneity, imperfect segmentation/classification, others. Then, because deep learning (DL) increasingly demonstrated ability overcome physical modalities, we review DL studies from past five years that address each challenges in PAI. Finally, discuss promise future research directions DL-enhanced

Language: Английский

---

Accelerating photoacoustic microscopy by reconstructing undersampled images using diffusion models

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: July 23, 2024

Photoacoustic Microscopy (PAM) integrates optical and acoustic imaging, offering enhanced penetration depth for detecting optical-absorbing components in tissues. Nonetheless, challenges arise scanning large areas with high spatial resolution. With speed limitations imposed by laser pulse repetition rates, the potential role of computational methods is highlighted accelerating PAM imaging. We propose a novel highly adaptable algorithm named DiffPam that utilizes diffusion models to up photoacoustic imaging process. leveraged model trained exclusively on natural images, comparing its performance an in-domain U-Net using dataset focused images mice brain microvasculature. Our findings indicate performs similarly dedicated without needing dataset. demonstrate can be accelerated fivefold limited information loss. achieved $$24.70\%$$ increase peak signal-to-noise ratio $$27.54\%$$ structural similarity index compared baseline bilinear interpolation method. The study also introduces efficacy shortened processes reducing computing time compromising accuracy. stands out from existing as it does not require supervised training or detailed parameter optimization typically needed other unsupervised methods. This underscores significance practical reconstructing undersampled particularly researchers artificial intelligence expertise resources.

Language: Английский

---

State of the Art in Carbon Nanomaterials for Photoacoustic Imaging

Biomedicines, Journal Year: 2022, Volume and Issue: 10(6), P. 1374 - 1374

Published: June 10, 2022

Photoacoustic imaging using energy conversion from light to ultrasound waves has been developed as a powerful tool investigate in vivo phenomena due their complex characteristics. In photoacoustic imaging, endogenous chromophores such oxygenated hemoglobin, deoxygenated melanin, and lipid provide useful biomedical information at the molecular level. However, these intrinsic absorbers show strong absorbance only visible or infrared optical windows have limited transmission, making them difficult apply for clinical translation. Therefore, development of novel exogenous contrast agents capable increasing depth while ensuring absorption is required. We report here application carbon nanomaterials that exhibit unique physical, mechanical, electrochemical properties probes imaging. Classified into specific structures, are synthesized with different substances according purposes modulate spectra highly enhance signals. addition, functional drugs can be loaded composite, effective monitoring photothermal therapy performed cell-specific targeting. Diverse applied cases suggest high potential nanomaterial-based research.

Language: Английский

---

Three-dimensional reconstructing undersampled photoacoustic microscopy images using deep learning

Photoacoustics, Journal Year: 2022, Volume and Issue: 29, P. 100429 - 100429

Published: Dec. 1, 2022

Spatial sampling density and data size are important determinants of the imaging speed photoacoustic microscopy (PAM). Therefore, undersampling methods that reduce number scanning points typically adopted to enhance PAM by increasing step size. Since sacrifice spatial density, considering points, size, characteristics provides three-dimensional (3D) volume data, in this study, we newly reported deep learning-based fully reconstructing undersampled 3D data. The results quantitative analyses demonstrate proposed method exhibits robustness outperforms interpolation-based reconstruction at various ratios, enhancing system performance with 80-times faster-imaging 800-times lower is demonstrated be closest model can used under experimental conditions, effectively shortening time significantly reduced for processing.

Language: Английский

---

A practical guide for model-based reconstruction in optoacoustic imaging

Frontiers in Physics, Journal Year: 2022, Volume and Issue: 10

Published: Nov. 1, 2022

Optoacoustic (OA, photoacoustic) imaging capitalizes on the low scattering of ultrasound within biological tissues to provide optical absorption-based contrast with high resolution at depths not reachable microscopy. For deep tissue applications, OA image formation commonly relies acoustic inversion time-resolved tomographic data. The excitation responses and subsequent propagation waves can be mathematically described as a forward model enabling reconstruction via algebraic inversion. These model-based methods have been shown outperform alternative approaches further render images from incomplete datasets, strongly distorted signals or other suboptimally recorded Herein, we general perspective methods, review recent progress, discuss performance different algorithms under practical scenarios.

Language: Английский

---

Transportable Multispectral Optical-Resolution Photoacoustic Microscopy Using Stimulated Raman Scattering Spectrum

IEEE Transactions on Instrumentation and Measurement, Journal Year: 2024, Volume and Issue: 73, P. 1 - 9

Published: Jan. 1, 2024

Photoacoustic imaging (PAI) has become a powerful biomedical technique in the last decades, combining optical and ultrasound (USI) principles. Among various configurations, optical-resolution photoacoustic microscopy (OR-PAM) served as vital tool for high-resolution high-sensitivity of small animals vivo. However, current systems have limited mobility, which hinders preclinical clinical research cramped spaces. Here, we propose compact ( $510\times 660\times1660$ mm3) transportable PAI system with stimulated Raman scattering (SRS) spectroscopy to address this challenge. The proposed is designed complete overcoming space restrictions. We demonstrate feasibility by vitro phantoms vivo mice. Additionally, verify its functional capabilities visualizing oxygen saturation levels mice ears. Our results indicate that maintains fast data acquisition time, superior image quality, multispectral capabilities. This shows great potential expanding applications OR-PAM wider range scenarios.

Language: Английский

---

Nanosecond SRS fiber amplifier for label-free near-infrared photoacoustic microscopy of lipids

Photoacoustics, Journal Year: 2022, Volume and Issue: 25, P. 100331 - 100331

Published: Jan. 15, 2022

Near-infrared photoacoustics receives increasing interest as an intravital modality to sense key biomolecules. One of the most central types biomolecules are lipids they constitute essential bio-hallmarks cardiovascular and metabolic diseases their in-vivo detection holds insightful information about disease progression treatment monitoring. However, full potential near-infrared photoacoustic for high-resolution high-sensitivity biomedical studies has so far not been exploited due a lack appropriate excitation sources delivering short-pulses at high-repetition-rate, high-pulse-energy, wavelength around 1200 nm. Here, we demonstrate custom-built SRS fiber amplifier that provides optical excitations 1192.8 nm, repetition rates 200 kHz, pulse durations below 2 ns, energies beyond 5 μJ. We capitalize on performance our source show resolving intrinsic lipid contrast in biomedically relevant specimens ranging from single cells lipid-rich tissue with subcellular resolution.

Language: Английский

---

Near-infrared-II deep tissue fluorescence microscopy and application

Nano Research, Journal Year: 2022, Volume and Issue: 16(1), P. 692 - 714

Published: Sept. 27, 2022

Language: Английский

---

Whole-Body Photoacoustic Imaging Techniques for Preclinical Small Animal Studies

Sensors, Journal Year: 2022, Volume and Issue: 22(14), P. 5130 - 5130

Published: July 8, 2022

Photoacoustic imaging is a hybrid technique that has received considerable attention in biomedical studies. In contrast to pure optical techniques, photoacoustic enables the visualization of absorption properties at deeper depths. preclinical small animal studies, widely used visualize biodistribution molecular level. Monitoring whole-body distribution chromophores animals key method research, including drug-delivery monitoring, treatment assessment, contrast-enhanced tumor imaging, and gastrointestinal tracking. this review, systems for are explored summarized. The configurations vary with scanning methods geometries ultrasound transducers. future direction research also discussed regard achieving depth faster speed, which main factors an system should realize broaden its application

Language: Английский

---

Efficient label-free in vivo photoacoustic imaging of melanoma cells using a condensed NIR-I spectral window

Photoacoustics, Journal Year: 2023, Volume and Issue: 29, P. 100456 - 100456

Published: Jan. 27, 2023

In this paper, we propose an efficient label-free in vivo photoacoustic (PA) imaging of melanoma using a condensed near infrared-I (NIR-I) supercontinuum light source. Although NIR-II spectral window is advantageous such as longer penetration depth compared to the NIR-I region, sources emitting both and region could lower efficiency target because low optical power density melanoma's absorption spectra. To exploit PA melanoma, demonstrated source from visible (532-600 nm) (600-1000 by optimizing stimulated Raman scattering induced generation. The structure successfully differentiated blood vessels at high pulse energy 2.5 µJ flexible repetition rate (PRR) 5-50 kHz. proposed with microjoules energies tens kHz PRR can potentially accelerate clinical trials early diagnosis melanoma.

Language: Английский

---