Accelerate Data Acquisition Research Articles

Accelerating data acquisition with FPGA-based edge machine learning: a case study with LCLS-II

Abstract New scientific experiments and instruments generate vast amounts of data that need to be transferred for storage or further processing, often overwhelming traditional systems. Edge Machine Learning (EdgeML) addresses this challenge by integrating
Machine Learning (ML) algorithms with edge computing, enabling real-time data processing directly at the point of data generation. EdgeML is particularly beneficial for environments where immediate decisions are required, or where bandwidth and
storage are limited. In this paper, we demonstrate a high-speed configurable ML model in a fully customizable EdgeML system using a Field Programmable Gate Array (FPGA). Our demonstration focuses on an angular array of electron spectrometers,
referred to as the ’CookieBox,’ developed for the Linac Coherent Light Source II (LCLS-II) project. The EdgeML system captures 51.2 Gbps from a 6.4 GS/s analog to digital converter and is designed to integrate data pre-processing and ML inside an
FPGA. Our implementation achieves an inference latency of 0.2 μs for the ML model, and a total latency of 0.4 μs for the complete EdgeML system, which includes preprocessing, data transmission, digitization, and ML inference. The modular design of
the system allows it to be adapted for other instrumentation applications requiring low-latency data processing.

Frame rate improvement in coherent plane-wave compounding using null subtraction imaging

Coherent plane-wave compounding (CPWC) has attracted significant attention in preclinical research and clinical diagnosis. However, a trade-off exists in CPWC between the image quality and frame rate. Null subtraction imaging (NSI), as a novel beamforming method, can realize high-quality imaging with enhanced lateral resolution and suppressed grating lobes. This study explores NSI to reduce the number of emissions while preserving the imaging quality. The performance of the proposed method is assessed using the Plane-Wave Imaging Challenge in Medical Ultrasound datasets, including phantom and in vivo datasets. The results verify the potential of NSI in terms of frame rate improvement compared to the conventional delay and sum beamforming method. NSI with 5 and 15 plane-wave emissions is evaluated. For example, for the experimental phantom datasets, NSI with 15 plane-wave emissions improves the lateral full-width at half maximum by 0.10 in comparison to DAS with 75 plane-wave emissions. Moreover, the corresponding contrast ratio and generalized contrast-to-noise ratio increase from 25.11 to 31.19 dB and 0.63 to 0.68, respectively, indicating contrast improvement. Thus, compared to DAS with 75 plane-wave emissions, the proposed method accelerates data acquisition by a factor of 5, resulting in remarkable frame rate improvement.

Compact Single-Shot Dual-Wavelength Interferometry for Large Object Measurement with Rough Surfaces

Single-shot dual-wavelength interferometry offers a promising avenue for surface profile measurement of dynamic objects. However, current techniques employing pixel multiplexing or color cameras encounter challenges such as complex optical alignment, limited measurement range, and difficulty in measuring rough surfaces. To address these issues, this study presents a novel approach to single-shot dual-wavelength interferometry. By utilizing separated polarization illumination and detection, along with a monochromatic polarization camera and two slightly different wavelengths, this method enables the simultaneous recording of two frames of separated interferometric patterns. This approach facilitates straightforward optical alignment, expands measurement ranges, accelerates data acquisition, and simplifies data processing for dual-wavelength interferometry. Consequently, it enables online shape measurement of large dynamic samples with rough surfaces.

Low-Cost Portable Road Smoothness Testing Method Based on Pseudo-Vibration Velocity Range

Road smoothness not only directly affects the safety and comfort of vehicle travel but also relates to the efficiency and cost-effectiveness of road maintenance. Traditional road smoothness detection methods usually require professional equipment and personnel, leading to high costs and cumbersome operations. Therefore, finding a low-cost, simple, and accurate method for detecting road smoothness is of great significance. This study uses vehicle-mounted acceleration sensors to detect road smoothness, establishing a correlation between driving vibration acceleration data and the international roughness index (IRI). For this research, a driving vibration acceleration data acquisition device was developed, and the driving acceleration data from the test sections were denoised and their feature values extracted. The pseudo-vibration velocity range was used as the characteristic index representing the road surface smoothness IRI value. Testing with different vehicle types showed that the method is applicable to both sedans and SUV models, yielding a relative error of 8.9% for the sedan smoothness test model and 6.7% for the SUV smoothness test model. This study contributes to conducting large-scale road smoothness detection at a low cost, improving the efficiency of road maintenance and operations.

SPICER: Self-supervised learning for MRI with automatic coil sensitivity estimation and reconstruction.

To introduce a novel deep model-based architecture (DMBA), SPICER, that uses pairs of noisy and undersampled k-space measurements of the same object to jointly train a model for MRI reconstruction and automatic coil sensitivity estimation. SPICER consists of two modules to simultaneously reconstructs accurate MR images and estimates high-quality coil sensitivity maps (CSMs). The first module, CSM estimation module, uses a convolutional neural network (CNN) to estimate CSMs from the raw measurements. The second module, DMBA-based MRI reconstruction module, forms reconstructed images from the input measurements and the estimated CSMs using both the physical measurement model and learned CNN prior. With the benefit of our self-supervised learning strategy, SPICER can be efficiently trained without any fully sampled reference data. We validate SPICER on both open-access datasets and experimentally collected data, showing that it can achieve state-of-the-art performance in highly accelerated data acquisition settings (up to ). Our results also highlight the importance of different modules of SPICER-including the DMBA, the CSM estimation, and the SPICER training loss-on the final performance of the method. Moreover, SPICER can estimate better CSMs than pre-estimation methods especially when the ACS data is limited. Despite being trained on noisy undersampled data, SPICER can reconstruct high-quality images and CSMs in highly undersampled settings, which outperforms other self-supervised learning methods and matches the performance of the well-known E2E-VarNet trained on fully sampled ground-truth data.

Swin Transformer and the Unet Architecture to Correct Motion Artifacts in Magnetic Resonance Image Reconstruction.

We present a deep learning-based method that corrects motion artifacts and thus accelerates data acquisition and reconstruction of magnetic resonance images. The novel model, the Motion Artifact Correction by Swin Network (MACS-Net), uses a Swin transformer layer as the fundamental block and the Unet architecture as the neural network backbone. We employ a hierarchical transformer with shifted windows to extract multiscale contextual features during encoding. A new dual upsampling technique is employed to enhance the spatial resolutions of feature maps in the Swin transformer-based decoder layer. A raw magnetic resonance imaging dataset is used for network training and testing; the data contain various motion artifacts with ground truth images of the same subjects. The results were compared to six state-of-the-art MRI image motion correction methods using two types of motions. When motions were brief (within 5 s), the method reduced the average normalized root mean square error (NRMSE) from 45.25% to 17.51%, increased the mean structural similarity index measure (SSIM) from 79.43% to 91.72%, and increased the peak signal-to-noise ratio (PSNR) from 18.24 to 26.57 dB. Similarly, when motions were extended from 5 to 10 s, our approach decreased the average NRMSE from 60.30% to 21.04%, improved the mean SSIM from 33.86% to 90.33%, and increased the PSNR from 15.64 to 24.99 dB. The anatomical structures of the corrected images and the motion-free brain data were similar.

MR signature matching (MRSIGMA) implementation for true real-time free-breathing volumetric imaging with sub-200 ms latency on an MR-Linac.

Develop a true real-time implementation of MR signature matching (MRSIGMA) for free-breathing 3D MRI with sub-200 ms latency on the Elekta Unity 1.5T MR-Linac. MRSIGMA was implemented on an external computer with a network connection to the MR-Linac. Stack-of-stars with partial kz sampling was used to accelerate data acquisition and ReconSocket was employed for simultaneous data transmission. Movienet network computed the 4D MRI motion dictionary and correlation analysis was used for signature matching. A programmable 4D MRI phantom was utilized to evaluate MRSIGMA with respect to a ground-truth translational motion reference. In vivo validation was performed on patients with pancreatic cancer, where 15 patients were employed to train Movienet and 7 patients to test the real-time implementation of MRSIGMA. Dice coefficients between real-time MRSIGMA and a retrospectively computed 4D reference were used to evaluate motion tracking performance. Motion dictionary was computed in under 5 s. Signature acquisition and matching presented 173 ms latency on the phantom and 193 ms on patients. MRSIGMA presented a mean error of 1.3-1.6 mm for all phantom experiments, which was below the 2 mm acquisition resolution along the motion direction. The Dice coefficient over time between MRSIGMA and reference contours was 0.88 ± 0.02 (GTV), 0.87 ± 0.02(duodenum-stomach), and 0.78 ± 0.02(small bowel), demonstrating high motion tracking performance for both tumor and organs at risk. The real-time implementation of MRSIGMA enabled true real-time free-breathing 3D MRI with sub-200 ms imaging latency on a clinical MR-Linac system, which can be used for treatment monitoring, adaptive radiotherapy and dose accumulation mapping in tumors affected by respiratory motion.

ISP-IRLNet: Joint optimization of interpretable sampler and implicit regularization learning network for accerlerated MRI

Compressed Sensing Magnetic Resonance Imaging (CS-MRI) was proposed to accelerate data acquisition and reconstruct MR images from under-sampled data in k-space. However, the traditional approaches design the sampling patterns separately from the reconstruction process, which often leads to suboptimal reconstruction performance. To address this issue, we propose a joint optimization model dubbed as ISP-IRLNet to yield optimal recovery including an interpretable sampler and a reconstructor using the implicit regularization learning network. In particular, we introduce a probabilistic distribution model of the sampling incorporated into the prior of k-space locations, which provides a robust CS-MRI sample pattern with an explicit expression. To estimate the approximating gradient in backward propagation for more stable training, we employ a differentiable binarization strategy. In addition, we unroll the ADMM optimization for solving the regularized reconstruction model to be a deep network (i.e., IRLNet) with a learnable implicit regularization sub-network to learn a regularizer or prior term implicitly. The experiments on our collected brain and public knee datasets demonstrate that our method provides an optimal sample pattern and achieves superior image reconstruction performance compared with existing methods, especially at high acceleration rates.

Guidelines for Application of High-Content Screening in Traditional Chinese Medicine: Concept, Equipment, and Troubleshooting

High-content screening (HCS) technology combines automated high-speed imaging hardware and single-cell quantitative analysis. It can greatly accelerate data acquisition in cellular fluorescence imaging and is a powerful research technique in traditional Chinese medicine (TCM). An increasing number of laboratories and platforms, including TCM laboratories, have begun utilizing HCS systems. However, this technology is still in its infancy in TCM research and there is a lack of sufficient experience with the associated concepts, instrument configurations, and analysis methods. To improve the understanding of HCS among researchers in the field of TCM, this paper summarizes the concept of HCS, software and hardware configuration, the overall research process, as well as common problems and related solutions of HCS in TCM research based on our team’s previous research experience, providing several research examples and an outlook on future perspectives, aiming to provide a technical guide for HCS in TCM research.

Mud-Net: multi-domain deep unrolling network for simultaneous sparse-view and metal artifact reduction in computed tomography

Sparse-view computed tomography (SVCT) is regarded as a promising technique to accelerate data acquisition and reduce radiation dose. However, in the presence of metallic implants, SVCT inevitably makes the reconstructed CT images suffer from severe metal artifacts and streaking artifacts due to the lack of sufficient projection data. Previous stand-alone SVCT and metal artifact reduction (MAR) methods to solve the problem of simultaneously sparse-view and metal artifact reduction (SVMAR) are plagued by insufficient correction accuracy. To overcome this limitation, we propose a multi-domain deep unrolling network, called Mud-Net, for SVMAR. Specifically, we establish a joint sinogram, image, artifact, and coding domains deep unrolling reconstruction model to recover high-quality CT images from the under-sampled sinograms corrupted by metallic implants. To train this multi-domain network effectively, we embed multi-domain knowledge into the network training process. Comprehensive experiments demonstrate that our method is superior to both existing MAR methods in the full-view MAR task and previous SVCT methods in the SVMAR task.

Incorporation of view sharing and KWIC filtering into GRASP-Pro improves spatial resolution of single-shot, multi-TI, late gadolinium enhancement MRI.

While single-shot late gadolinium enhancement (LGE) is useful for imaging patients with arrhythmia and/or dyspnea, it produces low spatial resolution. One approach to improve spatial resolution is to accelerate data acquisition using compressed sensing (CS). Our previous work described a single-shot, multi-inversion time (TI) LGE pulse sequence using radial k-space sampling and CS, but over-regularization resulted in significant image blurring that muted the benefits of data acceleration. The purpose of the present study was to improve the spatial resolution of the single-shot, multi-TI LGE pulse sequence by incorporating view sharing (VS) and k-space weighted contrast (KWIC) filtering into a GRASP-Pro reconstruction. In 24 patients (mean age = 61 ± 16 years; 9/15 females/males), we compared the performance of our improved multi-TI LGE and standard multi-TI LGE, where clinical standard LGE was used as a reference. Two clinical raters independently graded multi-TI images and clinical LGE images visually on a five-point Likert scale (1, nondiagnostic; 3, clinically acceptable; 5, best) for three categories: the conspicuity of myocardium or scar, artifact, and noise. The summed visual score (SVS) was defined as the sum of the three scores. Myocardial scar volume was quantified using the full-width at half-maximum method. The SVS was not significantly different between clinical breath-holding LGE (median 13.5, IQR 1.3) and multi-TI LGE (median 12.5, IQR 1.6) (P = 0.068). The myocardial scar volumes measured from clinical standard LGE and multi-TI LGE were strongly correlated (coefficient of determination, R2 = 0.99) and in good agreement (mean difference = 0.11%, lower limit of the agreement = -2.13%, upper limit of the agreement = 2.34%). The inter-rater agreement in myocardial scar volume quantification was strong (intraclass correlation coefficient = 0.79). The incorporation of VS and KWIC into GRASP-Pro improved spatial resolution. Our improved 25-fold accelerated, single-shot LGE sequence produces clinically acceptable image quality, multi-TI reconstruction, and accurate myocardial scar volume quantification.

Movienet: Deep space-time-coil reconstruction network without k-space data consistency for fast motion-resolved 4D MRI.

To develop a novel deep learning approach for 4D-MRI reconstruction, named Movienet, which exploits space-time-coil correlations and motion preservation instead of k-space data consistency, to accelerate the acquisition of golden-angle radial data and enable subsecond reconstruction times in dynamic MRI. Movienet uses a U-net architecture with modified residual learning blocks that operate entirely in the image domain to remove aliasing artifacts and reconstruct an unaliased motion-resolved 4D image. Motion preservation is enforced by sorting the input image and reference for training in a linear motion order from expiration to inspiration. The input image was collected with a lower scan time than the reference XD-GRASP image used for training. Movienet is demonstrated for motion-resolved 4D MRI and motion-resistant 3D MRI of abdominal tumors on a therapeutic 1.5T MR-Linac (1.5-fold acquisition acceleration) and diagnostic 3T MRI scanners (2-fold and 2.25-fold acquisition acceleration for 4D and 3D, respectively). Image quality was evaluated quantitatively and qualitatively by expert clinical readers. The reconstruction time of Movienet was 0.69 s (4 motion states) and 0.75 s (10 motion states), which is substantially lower than iterative XD-GRASP and unrolled reconstruction networks. Movienet enables faster acquisition than XD-GRASP with similar overall image quality and improved suppression of streaking artifacts. Movienet accelerates data acquisition with respect to compressed sensing and reconstructs 4D images in less than 1 s, which would enable an efficient implementation of 4D MRI in a clinical setting for fast motion-resistant 3D anatomical imaging or motion-resolved 4D imaging.

Development and testing of a ground recognition system for tractor field operations

To overcome the problems of poor recognition accuracy, slow response speed, and unsuitable for farmland ground environment based on the traditional ground recognition method of vehicle mathematical model, this paper proposes a ground recognition system for tractor field operation based on wheel acceleration. A wheel acceleration sensor and data acquisition device are designed, and a ground recognition algorithm based on Principal Component Analysis - Genetic Algorithm optimization of an Extreme Learning Machine (PCA-GA-ELM) is investigated. The system can collect acceleration samples and extract statistical features in different frequency bands in real time according to the cycle of wheel rotation and then use the trained recognition model to recognize the ground type. In the actual operation process, this system only needs to collect the acceleration test data of one rotation of the tractor wheels to achieve the recognition of the ground. The test set data show that this system achieves 96 % discrimination accuracy, higher than the 87 % of the ELM model without genetic algorithm optimization and 92 % of the GA-BP neural network model. In addition, the real-time ground recognition test shows that the increase in operation speed will slightly reduce the accuracy of the recognition model, but the overall can still maintain 94–98 % accuracy, indicating that the system has good stability. This system can provide a reference for real-time speed adjustment, implement position, and other control parameters during tractor operation.

A Heterogeneous Microprocessor Based on All-Digital Compute-in-Memory for End-to-End AIoT Inference

Deploying neural network (NN) models on Internet-of-Things (IoT) devices is important to enable artificial intelligence (AI) on the edge realizing AI-of-Things (AIoT). However, high energy consumption and bandwidth requirement of NN models restricts AI applications on battery-limited equipments. Compute-In-Memory (CIM), featured with high energy efficiency, provides new opportunities for the IoT deployment of NN. However, the design of CIM-based full system is still at the early stage, lacking system-level demonstration and vertical optimization for running end-to-end AI applications. In this paper, we demonstrate a low-power heterogeneous microprocessor System-on-Chip (SoC) with an all-digital SRAM CIM accelerator and rich data acquisition interfaces for end-to-end AIoT NN inference. A dedicated reconfigurable dataflow controller for CIM computation greatly lowers bandwidth requirement on the system bus and improves execution efficiency. The all-digital SRAM CIM array embeds NAND-based bit-serial multiplication within the readout sense amplifier balancing the storage density and system-level throughput. Our chip achieves a throughput of 12.8 GOPS, with 10 TOPS/W energy efficiency. Benchmarked by the four tasks in MLPerf Tiny, experimental results show 1.8x to 2.9x inference speedup over a baseline CIM processor.

Demystifying image-based machine learning: a practical guide to automated analysis of field imagery using modern machine learning tools

Image-based machine learning methods are becoming among the most widely-used forms of data analysis across science, technology, engineering, and industry. These methods are powerful because they can rapidly and automatically extract rich contextual and spatial information from images, a process that has historically required a large amount of human labor. A wide range of recent scientific applications have demonstrated the potential of these methods to change how researchers study the ocean. However, despite their promise, machine learning tools are still under-exploited in many domains including species and environmental monitoring, biodiversity surveys, fisheries abundance and size estimation, rare event and species detection, the study of animal behavior, and citizen science. Our objective in this article is to provide an approachable, end-to-end guide to help researchers apply image-based machine learning methods effectively to their own research problems. Using a case study, we describe how to prepare data, train and deploy models, and overcome common issues that can cause models to underperform. Importantly, we discuss how to diagnose problems that can cause poor model performance on new imagery to build robust tools that can vastly accelerate data acquisition in the marine realm. Code to perform analyses is provided at https://github.com/heinsense2/AIO_CaseStudy.

Research on the measurement method of artillery recoil displacement based on acceleration integration

The measurement of artillery recoil displacement is investigated in this paper. Unlike most existing works in which optical measurements are susceptible to fire, smoke, and obstructions in the light propagation path, a measurement method based on acceleration integration is proposed in this paper. First, the recoil acceleration data is obtained by the acceleration sensor and data acquisition module, and then transmitted to the host computer for subsequent data processing. Then, the pre-processing methods including low-pass filter, effective data segment extraction, and cubic spline interpolation are utilized to handle the original recoil acceleration data. Afterward, the adaptive integration algorithm based on the Simpson method is proposed to integrate the pre-processed acceleration to obtain the recoil displacement, which improves the integration accuracy and reduces the amount of computation compared with other common integration methods. Finally, the performance of the proposed method used to measure the recoil displacement is verified through a simulation example and practical experiments.

A Methodology for a Scalable, Collaborative, and Resource-Efficient Platform, MERLIN, to Facilitate Healthcare AI Research.

Healthcare artificial intelligence (AI) holds the potential to increase patient safety, augment efficiency and improve patient outcomes, yet research is often limited by data access, cohort curation, and tools for analysis. Collection and translation of electronic health record data, live data, and real-time high-resolution device data can be challenging and time-consuming. The development of clinically relevant AI tools requires overcoming challenges in data acquisition, scarce hospital resources, and requirements for data governance. These bottlenecks may result in resource-heavy needs and long delays in research and development of AI systems. We present a system and methodology to accelerate data acquisition, dataset development and analysis, and AI model development. We created an interactive platform that relies on a scalable microservice architecture. This system can ingest 15,000 patient records per hour, where each record represents thousands of multimodal measurements, text notes, and high-resolution data. Collectively, these records can approach a terabyte of data. The platform can further perform cohort generation and preliminary dataset analysis in 2-5 minutes. As a result, multiple users can collaborate simultaneously to iterate on datasets and models in real time. We anticipate that this approach will accelerate clinical AI model development, and, in the long run, meaningfully improve healthcare delivery.

Streak artifact suppressed back projection for sparse-view photoacoustic computed tomography.

The development of fast and accurate image reconstruction algorithms under constrained data acquisition conditions is important for photoacoustic computed tomography (PACT). Sparse-view measurements have been used to accelerate data acquisition and reduce system complexity; however, reconstructed images suffer from sparsity-induced streak artifacts. In this paper, a modified back-projection (BP) method termed anti-streak BP is proposed to suppress streak artifacts in sparse-view PACT reconstruction. During the reconstruction process, the anti-streak BP finds the back-projection terms contaminated by high-intensity sources with an outlier detection method. Then, the weights of the contaminated back-projection terms are adaptively adjusted to eliminate the effects of high-intensity sources. The proposed anti-streak BP method is compared with the conventional BP method on both simulation and in vivo data. The anti-streak BP method shows substantially fewer artifacts in the reconstructed images, and the streak index is 54% and 20% lower than that of the conventional BP method on simulation and in vivo data, when the transducer number N=128. The anti-streak BP method is a powerful improvement of the BP method with the ability of artifact suppression.

MP17-15 INFRARED-(IR)-IMAGING CLASSIFIES PROSTATE CANCER LABEL-FREE: A PROSPECTIVE IR-PROSPECT-STUDY SHOWS POTENTIAL FOR CLINICAL APPLICATION AND RESEARCH

You have accessJournal of UrologyCME1 Apr 2023MP17-15 INFRARED-(IR)-IMAGING CLASSIFIES PROSTATE CANCER LABEL-FREE: A PROSPECTIVE IR-PROSPECT-STUDY SHOWS POTENTIAL FOR CLINICAL APPLICATION AND RESEARCH Henning Bahlburg, Claus Kuepper, Frederik Grosserueschkamp, Nina Goertzen, Carlo Sternemann, Sebastian Berg, Karl Tully, Axel Mosig, Rein-Jueri Palisaar, Andrea Tannapfel, Klaus Gerwert, Joachim Noldus, and Florian Roghmann Henning BahlburgHenning Bahlburg More articles by this author , Claus KuepperClaus Kuepper More articles by this author , Frederik GrosserueschkampFrederik Grosserueschkamp More articles by this author , Nina GoertzenNina Goertzen More articles by this author , Carlo SternemannCarlo Sternemann More articles by this author , Sebastian BergSebastian Berg More articles by this author , Karl TullyKarl Tully More articles by this author , Axel MosigAxel Mosig More articles by this author , Rein-Jueri PalisaarRein-Jueri Palisaar More articles by this author , Andrea TannapfelAndrea Tannapfel More articles by this author , Klaus GerwertKlaus Gerwert More articles by this author , Joachim NoldusJoachim Noldus More articles by this author , and Florian RoghmannFlorian Roghmann More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003237.15AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: The Goal of this study was to evaluate whether artificial intelligence (AI) is suited to classify prostate cancer (PCa) label-free. In the last decade, IR-microscopy was able to showcase its potential to classify different tissues and pathologies in several studies. Recorded IR-Spectra reflect the biochemical status of the examined cell. The application of quantum-cascade lasers as source of light has accelerated data acquisition and thus enabled integration into clinical research pathways METHODS: In this study, tissue from 258 patients was investigated. Initially, AI with Random Forrest (RF) algorithm was applied. Prostatic tissue showed to be morphologically more demanding than expected. As the study population increased, a robust deep-learning AI was implemented. RESULTS: Deep-learning AI reached an AUC of 0.96 with a sensitivity of ∼98% and a specificity of ∼83% when classifying PCa label-free. This marks an improvement compared to RF, which showed a sensitivity of 82% and a specificity of 69%. CONCLUSIONS: AI-based IR-Imaging detects PCa with a sensitivity of 98%. Further improvement may be achieved by additional training and increase in sample size. Subsequently, laser-assisted micro-dissection may allow precise and homogenous sampling for detailed molecular analysis of tumor tissues. Results may be used to train AI in the detection of molecular tumor characteristics such as oncological targets. Source of Funding: This project was funded by the Ministry of Culture and Research of the Federal State of Northrine Westphalia © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e218 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information Henning Bahlburg More articles by this author Claus Kuepper More articles by this author Frederik Grosserueschkamp More articles by this author Nina Goertzen More articles by this author Carlo Sternemann More articles by this author Sebastian Berg More articles by this author Karl Tully More articles by this author Axel Mosig More articles by this author Rein-Jueri Palisaar More articles by this author Andrea Tannapfel More articles by this author Klaus Gerwert More articles by this author Joachim Noldus More articles by this author Florian Roghmann More articles by this author Expand All Advertisement PDF downloadLoading ...

Low-Rank Tensor Subspace Decomposition With Weighted Group Sparsity for the Acceleration of Non-Cartesian Dynamic MRI.

Dynamic MR imaging often requires long scan time, and acceleration of data acquisition is highly desirable in clinical applications. We proposed a Low-rank Tensor subspace decomposition with Weighted Group Sparsity (LTWGS) algorithm for non-Cartesian dynamic MRI. The proposed algorithm introduces the weighted group sparse constraints together with the subspace decomposition technique into the framework of low-rank tensor and sparse decomposition to better utilize the sparsity in the data. LTWGS increases the PSNR values by 1.97 dB, 2.03 dB, and 2.83 dB compared with PROST (patch-based reconstruction), SRTPCA (smooth robust tensor principal component analysis), and LRTES (low-rank tensor with "explicit subspace") in the dynamic abdominal imaging at an acceleration rate R = 25. LTWGS increases the PSNR values by 2.42 dB and 3.57 dB compared with PROST and LRTES in DCE liver imaging at R = 25. LTWGS increases the PSNR values by 1.40 dB and 1.96 dB compared with PROST and SRTPCA in cardiac cine imaging at R = 25. Jointly using group sparsity and sparsity can obtain better results than that using group sparsity alone, and weighted regularization can achieve better results than that without weighted regularization. The proposed algorithm results in reduced reconstruction error and improved image structural similarity in comparison with several state-of-the-art methods at relatively high acceleration factors. The proposed algorithm has the potential in various dynamic MRI application scenarios.