Efficient Photoacoustic Image Synthesis with Deep Learning.

Photoacoustic imaging potentially allows for the real-time visualization of functional human tissue parameters such as oxygenation but is subject to a challenging underlying quantification problem. While in silico studies have revealed the great potential of deep learning (DL) methodology in solving this problem, the inherent lack of an efficient gold standard method for model training and validation remains a grand challenge. This work investigates whether DL can be leveraged to accurately and efficiently simulate photon propagation in biological tissue, enabling photoacoustic image synthesis. Our approach is based on estimating the initial pressure distribution of the photoacoustic waves from the underlying optical properties using a back-propagatable neural network trained on synthetic data. In proof-of-concept studies, we validated the performance of two complementary neural network architectures, namely a conventional U-Net-like model and a Fourier Neural Operator (FNO) network. Our in silico validation on multispectral human forearm images shows that DL methods can speed up image generation by a factor of 100 when compared to Monte Carlo simulations with 5×108 photons. While the FNO is slightly more accurate than the U-Net, when compared to Monte Carlo simulations performed with a reduced number of photons (5×106), both neural network architectures achieve equivalent accuracy. In contrast to Monte Carlo simulations, the proposed DL models can be used as inherently differentiable surrogate models in the photoacoustic image synthesis pipeline, allowing for back-propagation of the synthesis error and gradient-based optimization over the entire pipeline. Due to their efficiency, they have the potential to enable large-scale training data generation that can expedite the clinical application of photoacoustic imaging.

A Potential Prognostic Gene Signature Associated with p53-Dependent NTRK1 Activation and Increased Survival of Neuroblastoma Patients.

Neuroblastoma is the most common extracranial solid tumour in children, comprising close to 10% of childhood cancer-related deaths. We have demonstrated that activation of NTRK1 by TP53 repression of PTPN6 expression is significantly associated with favourable survival in neuroblastoma. The molecular mechanisms by which this activation elicits cell molecular changes need to be determined. This is critical to identify dependable biomarkers for the early detection and prognosis of tumours, and for the development of personalised treatment. In this investigation we have identified and validated a gene signature for the prognosis of neuroblastoma using genes differentially expressed upon activation of the NTRK1-PTPN6-TP53 module. A random survival forest model was used to construct a gene signature, which was then assessed across validation datasets using Kaplan-Meier analysis and ROC curves. The analysis demonstrated that high BASP1, CD9, DLG2, FNBP1, FRMD3, IL11RA, ISGF10, IQCE, KCNQ3, and TOX2, and low BSG/CD147, CCDC125, GABRB3, GNB2L1/RACK1 HAPLN4, HEBP2, and HSD17B12 expression was significantly associated with favourable patient event-free survival (EFS). The gene signature was associated with favourable tumour histology and NTRK1-PTPN6-TP53 module activation. Importantly, all genes were significantly associated with favourable EFS in an independent manner. Six of the signature genes, BSG/CD147, GNB2L1/RACK1, TXNDC5, FNPB1, B3GAT1, and IGSF10, play a role in cell differentiation. Our findings strongly suggest that the identified gene signature is a potential prognostic biomarker and therapeutic target for neuroblastoma patients and that it is associated with neuroblastoma cell differentiation through the activation of the NTRK1-PTPN6-TP53 module.

SIMPA: an open-source toolkit for simulation and image processing for photonics and acoustics.

SIGNIFICANCE: Optical and acoustic imaging techniques enable noninvasive visualisation of structural and functional properties of tissue. The quantification of measurements, however, remains challenging due to the inverse problems that must be solved. Emerging data-driven approaches are promising, but they rely heavily on the presence of high-quality simulations across a range of wavelengths due to the lack of ground truth knowledge of tissue acoustical and optical properties in realistic settings. AIM: To facilitate this process, we present the open-source simulation and image processing for photonics and acoustics (SIMPA) Python toolkit. SIMPA is being developed according to modern software design standards. APPROACH: SIMPA enables the use of computational forward models, data processing algorithms, and digital device twins to simulate realistic images within a single pipeline. SIMPA's module implementations can be seamlessly exchanged as SIMPA abstracts from the concrete implementation of each forward model and builds the simulation pipeline in a modular fashion. Furthermore, SIMPA provides comprehensive libraries of biological structures, such as vessels, as well as optical and acoustic properties and other functionalities for the generation of realistic tissue models. RESULTS: To showcase the capabilities of SIMPA, we show examples in the context of photoacoustic imaging: the diversity of creatable tissue models, the customisability of a simulation pipeline, and the degree of realism of the simulations. CONCLUSIONS: SIMPA is an open-source toolkit that can be used to simulate optical and acoustic imaging modalities. The code is available at: https://github.com/IMSY-DKFZ/simpa, and all of the examples and experiments in this paper can be reproduced using the code available at: https://github.com/IMSY-DKFZ/simpa_paper_experiments.

Comparison among transposed brachiobasilic, brachiobrachial arteriovenous fistulas and Flixene™ vascular graft.

OBJECTIVE: To compare the outcomes of 3 upper arm access types: transposed brachiobasilic arteriovenous fistula (BBAVF), autogenous brachial vein-brachial artery access (ABBA), and a new type of ePTFE graft (Flixene™ graft) (AVG), in a consecutive series of patients treated in a tertiary centre. METHODS: A prospective, computerized access database was analysed retrospectively to identify all patients undergoing BBAVF, ABBA, or AVG between January 1, 2008, and December 31, 2009. RESULTS: A total of 108 patients were identified; of whom 45 had BBAVF, 15 ABBA, and 48 ePTFE brachioaxillary AVG. Early failure was similar in all 3 groups. The 18-month functional patency rates for the ABBAs, BBAVFs, and grafts were 27%, 51%, and 55%, respectively. The median time to first use for AVGs was significantly shorter (p<0.0001). Complications were not more frequent in AVGs than ABBAs and BBAVFs (p=0.127). The total number of access interventions was similar between the AVG and ABBA groups (p=0.58), but it was significantly higher in the AVG group compared with the BBAVF group (p<0.0001). CONCLUSIONS: This study supports the current recommendations of the NKF Kidney Disease Outcomes Quality Initiative for using BBAVFs as third choice after radiocephalic and brachiocephalic arteriovenous fistulas. We also showed good results with a new type of prosthetic graft (Flixene™ graft) that allows cannulation within days of implantation. We now favour the use of this graft instead of basilic vein transposition in elderly patients with short life expectancy and urgent need of renal access.