Deep learning of image- and time-domain data enhances the visibility of structures in optoacoustic tomography

Abstract

Images rendered with common optoacoustic system implementations are often afflicted with distortions and poor visibility of structures, hindering reliable image interpretation and quantification of bio-chrome distribution. Among the practical limitations contributing to artifactual reconstructions are insufficient tomographic detection coverage and suboptimal illumination geometry, as well as inability to accurately account for acoustic reflections and speed of sound heterogeneities in the imaged tissues. Here we developed a convolutional neural network (CNN) approach for enhancement of optoacoustic image quality which combines training on both time-resolved signals and tomographic reconstructions. Reference human finger data for training the CNN were recorded using a full-ring array system that provides optimal tomographic coverage around the imaged object. The reconstructions were further refined with a dedicated algorithm that minimizes acoustic reflection artifacts induced by acoustically mismatch structures, such as bones. The combined methodology is shown to outperform other learning-based methods solely operating on image-domain data.

A practical guide for model-based reconstruction in optoacoustic imaging

“…However, the ways deep neural networks process data are mathematically not fully understood with serious concerns raised regarding validity of the results. Nevertheless, in the OA field deep learning has been used for image quality improvement as well as for directly reconstructing images from the acquired signals [166][167][168][169][170][171][172][173][174][175][176][177][178][179]. Also, it was possible to train neural networks to learn the regularization term in an iterative MB inversion framework [101,180,181].…”

Recent advances in deep-learning-enhanced photoacoustic imaging

“…proposed a U-Net network to improve the image quality from sparsely sampled data from a full-ring transducer array. They later updated their U-Net architecture 102 to operate on both images and PA signals. Awasthi et al 103 .…”

“…Davoudi et al 101 proposed a U-Net network to improve the image quality from sparsely sampled data from a full-ring transducer array. They later updated their U-Net architecture 102 to operate on both images and PA signals. Awasthi et al 103 proposed a U-Net architecture to achieve superresolution, denoising, and bandwidth enhancements.…”

Rapid rotary-scanning photoacoustic computed tomography for pharmacokinetic monitoring in small animals

“…Building upon previous studies [22][23][24][25], we propose an alternative approach utilizing a continuous rotatingscanning method with a hemispherical transducer array for rapid imaging. Our goal is to develop a fast-scanning strategy to increase the whole-trunk imaging speed while maintaining high image quality.…”