Motion Correction in Optical Resolution Photoacoustic Microscopy

Zhao, Hongxin; Ning-bo, Chen; Li, Tan; Zhang, Jianhui; Lin, Riqiang; Gong, Xiaojing; Liu, Song; Liu, Zhicheng; Liu, Chengbo

doi:10.1109/tmi.2019.2893021

Cited by 41 publications

(24 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We experimentally demonstrated the feasibility of the proposed method using a CNN to correct motion artifacts in OR-PAM. In comparison with the existing algorithms [5][6][7][8], the proposed method demonstrates a better performance in eliminating motion artifacts in all directions without any reference objects. Additionally, we verified that the performance of the method improves as the kernel size increases.…”

Section: Discussionmentioning

confidence: 92%

“…Recently, several motion-correction methods have been proposed for PAI to obtain high-quality images [5][6][7][8]. The majority of existing algorithms are primarily based on deblurring methods that are extensively employed in photoacoustic-computed tomography (PACT) and only suitable for cross-sectional B-scan images [5,6].…”

Section: Introductionmentioning

confidence: 99%

“…Unfortunately, the algorithm needs a dynamic reference, which is not feasible in high-resolution OR-PAM images. A method presented by Zhao et al [8] has the capability of addressing these shortcomings but can only correct the dislocations along the direction of a slow-scanning axis. Recent methods that are based on deep learning have demonstrated a state-ofthe-art performance in many fields, such as natural language processing, audio recognition and visual recognition [9][10][11][12][13][14].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep-learning-based motion-correction algorithm in optical resolution photoacoustic microscopy

Chen

2019

Vis. Comput. Ind. Biomed. Art

View full text Add to dashboard Cite

In this study, we propose a deep-learning-based method to correct motion artifacts in optical resolution photoacoustic microscopy (OR-PAM). The method is a convolutional neural network that establishes an end-to-end map from input raw data with motion artifacts to output corrected images. First, we performed simulation studies to evaluate the feasibility and effectiveness of the proposed method. Second, we employed this method to process images of rat brain vessels with multiple motion artifacts to evaluate its performance for in vivo applications. The results demonstrate that this method works well for both large blood vessels and capillary networks. In comparison with traditional methods, the proposed method in this study can be easily modified to satisfy different scenarios of motion corrections in OR-PAM by revising the training sets.

show abstract

Section: Discussionmentioning

confidence: 92%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep-learning-based motion-correction algorithm in optical resolution photoacoustic microscopy

Chen

2019

Vis. Comput. Ind. Biomed. Art

View full text Add to dashboard Cite

show abstract

“…Third, global 3D volumetric imaging cannot be performed seamlessly due to motion artifacts between consecutive B-mode images (e.g., respiration and heartbeat). These problems can be overcome by image processing methods, such as compressive sensing, and electrocardiogram (ECG) gating technology [35][36][37][38] . In addition, the continuously steered mirror also could lead the motion artifact because of the directivity of acoustic.…”

Section: Discussionmentioning

confidence: 99%

Versatile Single-Element Ultrasound Imaging Platform using a Water-Proofed MEMS Scanner for Animals and Humans

Choi

Kim

Lim

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Single-element transducer based ultrasound (US) imaging offers a compact and affordable solution for high-frequency preclinical and clinical imaging because of its low cost, low complexity, and high spatial resolution compared to array-based US imaging. To achieve B-mode imaging, conventional approaches adapt mechanical linear or sector scanning methods. However, due to its low scanning speed, mechanical linear scanning cannot achieve acceptable temporal resolution for real-time imaging, and the sector scanning method requires specialized low-load transducers that are small and lightweight. Here, we present a novel single-element US imaging system based on an acoustic mirror scanning method. Instead of physically moving the US transducer, the acoustic path is quickly steered by a waterproofed microelectromechanical (MEMS) scanner, achieving real-time imaging. Taking advantage of the low-cost and compact MEMS scanner, we implemented both a tabletop system for in vivo small animal imaging and a handheld system for in vivo human imaging. Notably, in combination with mechanical raster scanning, we could acquire the volumetric US images in live animals. This versatile US imaging system can be potentially used for various preclinical and clinical applications, including echocardiography, ophthalmic imaging, and ultrasound-guided catheterization.

show abstract

“…Currently, OR-PAM is widely used in preclinical research, e.g., studies of tumor [14], brain [15], [16] and skin tissues [17], [18]. A nanosecond pulsed laser is generally applied to shed laser into the biological tissues.…”

Section: Introductionmentioning

confidence: 99%

Multiscale Vascular Enhancement Filter Applied toIn VivoMorphologic and Functional Photoacoustic Imaging of Rat Ocular Vasculature

Zhao

Liu

et al. 2019

IEEE Photonics J.

Self Cite

View full text Add to dashboard Cite

Optical-resolution photoacoustic microscopy (OR-PAM) is used for in vivo imaging of a variety of albino and pigmented eyes taking advantages of requiring no exogenous dye, performing high-resolution imaging, and achieving morphologic and functional imaging at the same time. However, to accurately diagnose the ophthalmic disease in the OR-PAM images, vascular enhancement algorithms are necessary for extracting vessels and quantifying them correctly. Vascular enhancement algorithms developed for other imaging technologies, are not suitable to be used for OR-PAM, because of the underlying differences in the physics of the formation of images. In this study, a new vascular enhancement algorithm called photoacoustic imaging vasculature enhancement filter (PAIVEF) is proposed, which not only enhances vasculature including micro-vessels signals, suppresses noise signals effectively, but also achieves highly sensitive and accurate enhancement of the vasculature within a large depth range in and out of the system's depth of focus (DOF). Using the PAIVEF, the morphologic and functional 3D images of the whole rat's ocular anterior vasculature segment was displayed simultaneously for a depth range of ∼0.6 mm, which was ∼7 times of the system's DOF. This study paves the way for the application of OR-PAM technology in ophthalmic disease research.

show abstract

Motion Correction in Optical Resolution Photoacoustic Microscopy

Cited by 41 publications

References 36 publications

Deep-learning-based motion-correction algorithm in optical resolution photoacoustic microscopy

Deep-learning-based motion-correction algorithm in optical resolution photoacoustic microscopy

Versatile Single-Element Ultrasound Imaging Platform using a Water-Proofed MEMS Scanner for Animals and Humans

Multiscale Vascular Enhancement Filter Applied toIn VivoMorphologic and Functional Photoacoustic Imaging of Rat Ocular Vasculature

Contact Info

Product

Resources

About