Corpus ID: 237571409

Photoacoustic digital brain: numerical modelling and image reconstruction via deep learning

  title={Photoacoustic digital brain: numerical modelling and image reconstruction via deep learning},
  author={Tengbo Lyu and Jiadong Zhang and Zijian Gao and Changchun Yang and Feng Gao and Fei Gao},
Photoacoustic tomography (PAT) is a newly developed medical imaging modality, which combines the advantages of pure optical imaging and ultrasound imaging, owning both high optical contrast and deep penetration depth. Very recently, PAT is studied in human brain imaging. Nevertheless, while ultrasound waves are passing through the human skull tissues, the strong acoustic attenuation and aberration will happen, which causes photoacoustic signals’ distortion. In this work, we use 10 magnetic… Expand

Figures and Tables from this paper


3D Opto-Acoustic Simulation of Human Skin Vascular for Quantitative Image Analysis.
Photoacoustic computed tomography (PACT) is a hybrid imaging modality, which combines the high optical contrast of pure optical imaging and the high penetration depth of ultrasound imaging. However,Expand
A numerical model for the study of photoacoustic imaging of brain tumours
Photoacoustic imaging has shown great promise for medical imaging, where optical energy absorption by blood haemoglobin is used as the contrast mechanism. A numerical method was developed for theExpand
Human Breast Numerical Model Generation Based on Deep Learning for Photoacoustic Imaging
A method to automatically generate breast numerical model with proper optical and acoustic properties is proposed, which is specifically suitable for PA imaging studies, and the experiment results indicate that the method is feasible with high efficiency. Expand
Transcranial photoacoustic computed tomography based on a layered back-projection method
A modified universal back-projection (UBP) method that can de-aberrate the transcranial PA signals by accommodating the skull heterogeneity into conventional UBP is presented, termed layered UBP (L-UBP). Expand
Generation of anatomically realistic numerical phantoms for photoacoustic and ultrasonic breast imaging
A methodology for generating anatomically realistic numerical breast phantoms from clinical contrast-enhanced magnetic resonance imaging data is developed and implemented and will depict vascular structures and the volumetric distribution of different tissue types in the breast. Expand
Deep Neural Network-Based Sinogram Super-Resolution and Bandwidth Enhancement for Limited-Data Photoacoustic Tomography
A deep neural network-based model with loss function being scaled root-mean-squared error was proposed for super-resolution, denoising, as well as BW enhancement of the PA signals collected at the boundary of the domain and is shown to improve the collected boundary data, in turn, providing superior quality reconstructed PA image. Expand
Photoacoustic tomography through a whole adult human skull with a photon recycler
For the first time, the feasibility of PAT through a whole adult human skull is demonstrated and the results indicate that PAT can potentially be applied to in vivo human brain imaging. Expand
Semi-anthropomorphic photoacoustic breast phantom.
The first three dimensional multi-layered semi-anthropomorphic photoacoustic breast phantom is presented, which aims to simulate skin, fat, fibroglandular tissue and blood vessels and a good correspondence is observed, which confirms the phantom's usefulness. Expand
Photoacoustic Source Detection and Reflection Artifact Removal Enabled by Deep Learning
It is shown that the CNN-based information can be displayed in a novel artifact-free image format, enabling us to effectively remove reflection artifacts from photoacoustic images, which is not possible with traditional geometry-based beamforming. Expand
Adaptive Ultrasound Beamforming Using Deep Learning
It is shown that deep neural networks, that adopt the algorithmic structure and constraints of adaptive signal processing techniques, can efficiently learn to perform fast high-quality ultrasound beamforming using very little training data, and that high image quality can be maintained when measuring at low data-rates, using undersampled array designs. Expand