Composition of training and validation sets. The original dataset used to train and validate our networks was obtained through the automated processing of 499 patient samples with ACCEPT and

In an inhomogeneously illuminated photoacoustic image, important information like vascular geometry is not readily available when only the initial pressure is reconstructed. To obtain the desired information, algorithms for image segmentation are often applied as a post-processing step. In this work, we propose to jointly acquire the photoacoustic reconstruction and segmentation, by modifying a recently developed partially learned algorithm based on a convolutional neural network. We investigate the stability of the algorithm against changes in initial pressures and photoacoustic system settings. These insights are used to develop an algorithm that is robust to input and system settings. Our approach can easily be applied to other imaging modalities and can be modified to perform other high-level tasks different from segmentation. The method is validated on challenging synthetic and experimental photoacoustic tomography data in limited angle and limited view scenarios. It is computationally less expensive than classical iterative methods and enables higher quality reconstructions and segmentations than state-of-the-art learned and non-learned methods.

Pulsed lasers in photoacoustic tomography systems are expensive, which limit their use to a few clinics and small animal labs. We present a method to realize tomographic ultrasound and photoacoustic imaging using a commercial LED-based photoacoustic and ultrasound system. We present two illumination configurations using LED array units and an optimal number of angular views for tomographic reconstruction. The proposed method can be a cost-effective solution for applications demanding tomographic imaging and can be easily integrated into conventional linear array-based ultrasound systems. We present a potential application for finger joint imaging in vivo, which can be used for point-of-care rheumatoid arthritis diagnosis and monitoring.

Photoacoustic tomography is a hybrid imaging technique that combines high optical tissue contrast with high ultrasound resolution. Direct reconstruction methods such as filtered back-projection, time reversal and least squares suffer from curved line artefacts and blurring, especially in the case of limited angles or strong noise. In recent years, there has been great interest in regularised iterative methods. These methods employ prior knowledge of the image to provide higher quality reconstructions. However, easy comparisons between regularisers and their properties are limited, since many tomography implementations heavily rely on the specific regulariser chosen. To overcome this bottleneck, we present a modular reconstruction framework for photoacoustic tomography, which enables easy comparisons between regularisers with different properties, e.g. nonlinear, higher-order or directional. We solve the underlying minimisation problem with an efficient first-order primal-dual algorithm. Convergence rates are optimised by choosing an operator-dependent preconditioning strategy. A variety of reconstruction methods are tested on challenging 2D synthetic and experimental data sets. They outperform direct reconstruction approaches for strong noise levels and limited angle measurements, offering immediate benefits in terms of acquisition time and quality. This work provides a basic platform for the investigation of future advanced regularisation methods in photoacoustic tomography.

Enabling handheld perfusion imaging would drastically improve the feasibility of perfusion imaging in clinical practice. Therefore, we examine the performance of handheld laser speckle contrast imaging (LSCI) measurements compared to mounted measurements, demonstrated in psoriatic skin. A pipeline is introduced to process, analyze and compare data of 11 measurement pairs (mounted-handheld LSCI modes) operated on 5 patients and various skin locations. The on-surface speeds (i.e. speed of light beam movements on the surface) are quantified employing mean separation (MS) segmentation and enhanced correlation coefficient maximization (ECC). The average on-surface speeds are found to be 8.5 times greater in handheld mode compared to mounted mode. Frame alignment sharpens temporally averaged perfusion maps, especially in the handheld case. The results show that after proper post-processing, the handheld measurements are in agreement with the corresponding mounted measurements on a visual basis. The absolute movement-induced difference between mounted-handheld pairs after the background correction is $$16.4\pm 9.3~\%$$ 16.4 ± 9.3 % (mean ± std, $$n=11$$ n = 11 ), with an absolute median difference of $$23.8\%$$ 23.8 % . Realization of handheld LSCI facilitates measurements on a wide range of skin areas bringing more convenience for both patients and medical staff.