Deep Learning Enables Superior Photoacoustic Imaging at Ultralow Laser Dosages

Zhao, Hongxin; Ke, Ziwen; Yang, Fan; Li, Ké; Chen, Ningbo; Liu, Song; Zheng, Chuansheng; Liang, Dong; Liu, Chengbo

doi:10.1002/advs.202003097

Cited by 47 publications

(28 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our GANs, generators are designed based on U-net (Fig. 1c ), which has recently proven effective for multiscale image learning, especially PA image reconstruction 29 , 31 , 38 , 41 . The generator for 3D OR-PAM images contains 17 3D convolutional layers and roughly 43 million trainable parameters (Table S1 ).…”

Section: Resultsmentioning

confidence: 99%

“…Computational strategies based on a deep neural network (DNN) have proved effective in improving such biomedical imaging modalities as optical microscopy, US imaging, magnetic resonance angiography (MRI), and computed tomography (CT) 29 – 37 . An especially interesting emerging application minimizes data acquisition times by reconstructing dense data from spatially or temporally undersampled sparse data 30 , 31 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning acceleration of multiscale superresolution localization photoacoustic imaging

Kim

et al. 2022

Light Sci Appl

View full text Add to dashboard Cite

A superresolution imaging approach that localizes very small targets, such as red blood cells or droplets of injected photoacoustic dye, has significantly improved spatial resolution in various biological and medical imaging modalities. However, this superior spatial resolution is achieved by sacrificing temporal resolution because many raw image frames, each containing the localization target, must be superimposed to form a sufficiently sampled high-density superresolution image. Here, we demonstrate a computational strategy based on deep neural networks (DNNs) to reconstruct high-density superresolution images from far fewer raw image frames. The localization strategy can be applied for both 3D label-free localization optical-resolution photoacoustic microscopy (OR-PAM) and 2D labeled localization photoacoustic computed tomography (PACT). For the former, the required number of raw volumetric frames is reduced from tens to fewer than ten. For the latter, the required number of raw 2D frames is reduced by 12 fold. Therefore, our proposed method has simultaneously improved temporal (via the DNN) and spatial (via the localization method) resolutions in both label-free microscopy and labeled tomography. Deep-learning powered localization PA imaging can potentially provide a practical tool in preclinical and clinical studies requiring fast temporal and fine spatial resolutions.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep learning acceleration of multiscale superresolution localization photoacoustic imaging

Kim

et al. 2022

Light Sci Appl

View full text Add to dashboard Cite

show abstract

“…For more reliable results, it is necessary to develop better laser sources with faster repetition rates, less fluctuation, and more wavelengths. Motion correction can be applied to mitigate the inevitable motions [ 68 , 69 ], and vascular enhancement can be adopted to achieve high-quality blood vessel images [ 70 , 71 ]. From the improvement, if real-time 3D imaging is available, the heartbeat and vascular density could be more accurate.…”

Section: Discussionmentioning

confidence: 99%

High-resolution functional photoacoustic monitoring of vascular dynamics in human fingers

et al. 2021

View full text Add to dashboard Cite

Functional imaging of microvascular dynamics in extremities delivers intuitive information for early detection, diagnosis, and prognosis of vascular diseases. High-resolution and high-speed photoacoustic microscopy (PAM) visualizes and measures multiparametric information of microvessel networks in vivo such as morphology, flow, oxygen saturation, and metabolic rate. Here, we demonstrate high-resolution photoacoustic monitoring of vascular dynamics in human fingers. We photoacoustically monitored the position displacement of blood vessels associated with arterial pulsation in human fingers. Then, during and after arterial occlusion, we photoacoustically quantified oxygen consumption and blood perfusion in the fingertips. The results demonstrate that high-resolution functional PAM could be a vital tool in peripheral vascular examination for measuring heart rate, oxygen consumption, and/or blood perfusion.

show abstract

“…In that work, a CNN architecture was developed mainly to improve out-of-focus lateral resolution of AR-PAM images, while background noise reduction was also observed. Zhao et al demonstrated good de-noising performance for OR-PAM images [28], yet the use of two wavelengths for PA excitation was required, which results in higher cost and more complexity of the imaging system (e.g., an optical parametric oscillator laser was used. ).…”

Section: Introductionmentioning

confidence: 99%

De-Noising of Photoacoustic Microscopy Images by Deep Learning

He¹,

Zhou²,

Shang³

et al. 2022

Preprint

View full text Add to dashboard Cite

As a hybrid imaging technology, photoacoustic microscopy (PAM) imaging suffers from noise due to the maximum permissible exposure of laser intensity, attenuation of ultrasound in the tissue, and the inherent noise of the transducer. De-noising is a post-processing method to reduce noise, and PAM image quality can be recovered. However, previous de-noising techniques usually heavily rely on mathematical priors as well as manually selected parameters, resulting in unsatisfactory and slow de-noising performance for different noisy images, which greatly hinders practical and clinical applications. In this work, we propose a deep learning-based method to remove complex noise from PAM images without mathematical priors and manual selection of settings for different input images. An attention enhanced generative adversarial network is used to extract image features and remove various noises. The proposed method is demonstrated on both synthetic and real datasets, including phantom (leaf veins) and in vivo (mouse ear blood vessels and zebrafish pigment) experiments. The results show that compared with previous PAM de-noising methods, our method exhibits good performance in recovering images qualitatively and quantitatively. In addition, the de-noising speed of 0.016 s is achieved for an image with 256 × 256 pixels. Our approach is effective and practical for the de-noising of PAM images.

show abstract

Deep Learning Enables Superior Photoacoustic Imaging at Ultralow Laser Dosages

Cited by 47 publications

References 42 publications

Deep learning acceleration of multiscale superresolution localization photoacoustic imaging

Deep learning acceleration of multiscale superresolution localization photoacoustic imaging

High-resolution functional photoacoustic monitoring of vascular dynamics in human fingers

De-Noising of Photoacoustic Microscopy Images by Deep Learning

Contact Info

Product

Resources

About