Deep Learning-Based Photoacoustic Imaging of Vascular Network Through Thick Porous Media

Abstract

Photoacoustic imaging is a promising approach used to realize in vivo transcranial cerebral vascular imaging. However, the strong attenuation and distortion of the photoacoustic wave caused by the thick porous skull greatly affect the imaging quality. In this study, we developed a convolutional neural network based on U-Net to extract the effective photoacoustic information hidden in the speckle patterns obtained from vascular network images datasets under porous media. Our simulation and experimental results show that the proposed neural network can learn the mapping relationship between the speckle pattern and the target, and extract the photoacoustic signals of the vessels submerged in noise to reconstruct high-quality images of the vessels with a sharp outline and a clean background. Compared with the traditional photoacoustic reconstruction methods, the proposed deep learning-based reconstruction algorithm has a better performance with a lower mean absolute error, higher structural similarity, and higher peak signal-to-noise ratio of reconstructed images. In conclusion, the proposed neural network can effectively extract valid information from highly blurred speckle patterns for the rapid reconstruction of target images, which offers promising applications in transcranial photoacoustic imaging.

Deep Learning-Based Super-Resolution Reconstruction and Segmentation of Photoacoustic Images

“…Therefore, despite the great progress in PAI, there are still great challenges in image quality improvement and accurate segmentation of tissue structures [18,19]. Traditional photoacoustic image reconstruction and segmentation methods often rely on hand-designed feature extractors and mathematical models, which have many limitations in dealing with complex backgrounds, noise interference, and blurred organizational boundaries [20,21].…”

Photoacoustic digital brain and deep-learning-assisted image reconstruction

“…In this scattering mode, some side-lobe signals are generated. The superimposition of main lobe and side lobes makes the reconstruction process more complicated [7] . In this regard, more works appear to correct aberration and make a big step towards the clinical PA human brain imaging.…”

Unsupervised segmentation of 3D microvascular photoacoustic images using deep generative learning

“…To date, the application of deep learning methods in PAI has primarily focused on image reconstruction [27][28][29] or bridging the domain gap between simulations and experiments 30,31 . Supervised methods have not only explored the task of blood vessel segmentation from 2D photoacoustic images [32][33][34][35][36] but have also shown promise in addressing the complexities involved in segmenting 3D images, as recent work has demonstrated the potential of combining synthetic data and manual annotations for effective supervised segmentation of 3D photoacoustic images 37 . However, the transition to unsupervised methods in 3D PAI has been challenging due to artefacts arising from low signal-to-noise ratio (SNR) 38 or excitation and detection geometries 39 , which severely limit their effectiveness.…”