Goto

Collaborating Authors

Deep learning for biomedical photoacoustic imaging: A review

#artificialintelligence

Photoacoustic imaging (PAI) is a promising emerging imaging modality that enables spatially resolved imaging of optical tissue properties up to several centimeters deep in tissue, creating the potential for numerous exciting clinical applications. However, extraction of relevant tissue parameters from the raw data requires the solving of inverse image reconstruction problems, which have proven extremely difficult to solve. The application of deep learning methods has recently exploded in popularity, leading to impressive successes in the context of medical imaging and also finding first use in the field of PAI. Deep learning methods possess unique advantages that can facilitate the clinical translation of PAI, such as extremely fast computation times and the fact that they can be adapted to any given problem.


Deep learning for biomedical photoacoustic imaging: A review

arXiv.org Artificial Intelligence

Photoacoustic imaging (PAI) is a promising emerging imaging modality that enables spatially resolved imaging of optical tissue properties up to several centimeters deep in tissue, creating the potential for numerous exciting clinical applications. However, extraction of relevant tissue parameters from the raw data requires the solving of inverse image reconstruction problems, which have proven extremely difficult to solve. The application of deep learning methods has recently exploded in popularity, leading to impressive successes in the context of medical imaging and also finding first use in the field of PAI. Deep learning methods possess unique advantages that can facilitate the clinical translation of PAI, such as extremely fast computation times and the fact that they can be adapted to any given problem. In this review, we examine the current state of the art regarding deep learning in PAI and identify potential directions of research that will help to reach the goal of clinical applicability


Utilizing variational autoencoders in the Bayesian inverse problem of photoacoustic tomography

#artificialintelligence

Photoacoustic tomography (PAT) is a hybrid biomedical imaging modality based on the photoacoustic effect [6, 44, 32]. In PAT, the imaged target is illuminated with a short pulse of light. Absorption of light creates localized areas of thermal expansion, resulting in localized pressure increases within the imaged target. This pressure distribution, called the initial pressure, relaxes as broadband ultrasound waves that are measured on the boundary of the imaged target. In the inverse problem of PAT, the initial pressure distribution is estimated from a set of measured ultrasound data.


A Novel Concept of Identification of Metal-oxide Powders by Energy-resolved Density of Electron Traps

VideoLectures.NET

Energy-resolved distribution of electron traps (ERDT) as well as conduction-band bottom (CBB) in metal oxide particles as a function of energy from valence-band (VB) top has been evaluated by newly developed reversed double-beam photoacoustic spectroscopy (RDB-PAS), in which photoabsorption of electrons in ETs directly excited from VB by irradiation of intense continuous light is measured by photoacoustic spectroscopy (PAS) using modulated LED light at 625 nm. In this study, how to use ERDT/CBB patterns as a finger print for identification of metal oxide (titania, niobia and the others) particles having band gap and ETs by weighted degree of coincidence multiplied by the degrees of coincidence of ERDT patterns, total density of ETs and CBB, and correlation between degree of coincidences of ERDT/CBB patterns and photocatalytic activities are discussed.


Less Energy, Better Quality Photoacoustic Microscopy Images With Machine Learning - Todayuknews

#artificialintelligence

Photoacoustic microscopy (PAM) allows researchers to see the smallest vessels inside a body, but it can generate some unwanted signals or noise. A team of researchers at the McKelvey School of Engineering at Washington University in St. Louis found a way to significantly reduce the noise and maintain image quality while reducing the laser energy needed to generate images by 80%. Song Hu, associate professor of biomedical engineering, and members of his lab devised this new method using a machine-learning-based image processing technique, called sparse coding, to remove the noise from PAM images of vessel structure, oxygen saturation and blood flow in a mouse brain. Results of the work were published online in IEEE Transactions on Medical Imaging. To acquire such images, the researchers need a dense sampling of data, which requires a high laser pulse repetition rate that may raise safety concerns.