Image Acquisition Speed Research Articles

Resolution-dependent MRI-to-CT translation for orthotopic breast cancer models using deep learning.


This study aims to investigate the feasibility of utilizing generative adversarial networks (GANs) to synthesize high-fidelity CT images from lower-resolution MR images. The goal is to reduce patient exposure to ionizing radiation while maintaining treatment accuracy and accelerating MR image acquisition. The primary focus is to determine the extent to which low-resolution MR images can be utilized to generate high-quality CT images through a systematic study of spatial resolution-dependent MRI-to-CT image conversion. 
Approach. 
Paired MRI-CT images were acquired from healthy control and tumor models, generated by injecting MDA-MB-231 and 4T1 tumor cells into the mammary fat pad of nude and BALB/c mice to ensure model diversification. To explore various MRI resolutions, we downscaled the highest-resolution MR image into three lower resolutions. Using a customized U-Net model, we automated region of interest masking for both MRI and CT modalities with precise alignment, achieved through three-dimensional affine paired MRI-CT registrations. Then our customized models, Nested U-Net Generative Adversarial Network (NUGAN) and Attention U-Net Generative Adversarial Network (AUGAN), were employed to translate low-resolution MR images into high-resolution CT images, followed by evaluation with separate testing datasets.
Main Results.
Our approach successfully generated high-quality CT images (0.142 mm²) from both lower-resolution (0.282 mm²) and higher-resolution (0.142 mm²) MR images, with no statistically significant differences between them, effectively doubling the speed of MR image acquisition. Our customized GANs successfully preserved anatomical details, addressing the typical loss issue seen in other MRI-CT translation techniques across all resolutions of MR image inputs.
 Significance. 
This study demonstrates the potential of using low-resolution MR images to generate high-quality CT images, thereby reducing radiation exposure and expediting MRI acquisition while maintaining accuracy for radiotherapy.&#xD.

Correlation Hyperspectral Imaging.

Hyperspectral imaging aims at providing information on both the spatial and the spectral distribution of light, with high resolution. However, state-of-the-art protocols are characterized by an intrinsic trade-off imposing to sacrifice either resolution or image acquisition speed. We address this limitation by exploiting light intensity correlations, which are shown to enable overcoming the typical downsides of traditional hyperspectral imaging techniques, both scanning and snapshot. The proposed approach also opens possibilities that are not otherwise achievable, such as sharper imaging and natural filtering of broadband spectral components that would otherwise hide the spectrum of interest. The enabled combination of high spatial and spectral resolution, high speed, and insensitivity to undesired spectral features shall lead to a paradigm change in hyperspectral imaging devices and open up new application scenarios.

Internal thread defect detection system based on multi-vision.

In the realm of industrial inspection, the precise assessment of internal thread quality is crucial for ensuring mechanical integrity and safety. However, challenges such as limited internal space, inadequate lighting, and complex geometry significantly hinder high-precision inspection. In this study, we propose an innovative automated internal thread detection scheme based on machine vision, aimed at addressing the time-consuming and inefficient issues of traditional manual inspection methods. Compared with other existing technologies, this research significantly improves the speed of internal thread image acquisition through the optimization of lighting and image capturing devices. To effectively tackle the challenge of image stitching for complex thread textures, an internal thread image stitching technique based on a cylindrical model is proposed, generating a full-view thread image. The use of the YOLOv8 model for precise defect localization in threads enhances the accuracy and efficiency of detection. This system provides an efficient and intuitive artificial intelligence solution for detecting surface defects on geometric bodies in confined spaces.

Alrecon: computed tomography reconstruction web application based on Solara

Synchrotron X-ray computed tomography is a non-destructive 3D imaging technique that offers the possibility to study the internal microstructure of samples with high spatial and temporal resolution. Given its unmatched image quality and acquisition speed, and the possibility to preserve the specimens, there is an increasing demand for this technique, from scientific users from innumerable disciplines. Computed tomography reconstruction is the computational process by which experimental radiographs are converted to a meaningful 3-dimensional image after the scan. The procedure involves pre-processing steps for image background and artifact correction on raw data, a reconstruction step approximating the inverse Radon-transform, and writing of the reconstructed volume image to disk. Several open-source Python packages exist to help scientists in the process of tomography reconstruction, by offering efficient implementations of reconstruction algorithms exploiting central or graphics processing unit (CPU and GPU, respectively), and by automating significant portions of the data processing pipeline. A further increase in productivity is attained by scheduling and parallelizing demanding reconstructions on high performance computing (HPC) clusters. Nevertheless, visual inspection and interactive selection of optimal reconstruction parameters remain crucial steps that are often performed in close interaction with the end-user of the data. As a result, the reconstruction task involves more than one software. Graphical user interfaces are provided to the user for fast inspection and optimization of reconstructions, while HPC resources are often accessed through scripts and command line interface. We propose Alrecon, a pure Python web application for tomographic reconstruction built using Solara. Alrecon offers users an intuitive and reactive environment for exploring data and customizing reconstruction pipelines. By leveraging upon popular 3D image visualization tools, and by providing a user-friendly interface for reconstruction scheduling on HPC resources, Alrecon guarantees productivity and efficient use of resources for any type of beamline user.

Diving head-first into brain intravital microscopy.

Tissue microenvironments during physiology and pathology are highly complex, meaning dynamic cellular activities and their interactions cannot be accurately modelled ex vivo or in vitro. In particular, tissue-specific resident cells which may function and behave differently after isolation and the heterogenous vascular beds in various organs highlight the importance of observing such processes in real-time in vivo. This challenge gave rise to intravital microscopy (IVM), which was discovered over two centuries ago. From the very early techniques of low-optical resolution brightfield microscopy, limited to transparent tissues, IVM techniques have significantly evolved in recent years. Combined with improved animal surgical preparations, modern IVM technologies have achieved significantly higher speed of image acquisition and enhanced image resolution which allow for the visualisation of biological activities within a wider variety of tissue beds. These advancements have dramatically expanded our understanding in cell migration and function, especially in organs which are not easily accessible, such as the brain. In this review, we will discuss the application of rodent IVM in neurobiology in health and disease. In particular, we will outline the capability and limitations of emerging technologies, including photoacoustic, two- and three-photon imaging for brain IVM. In addition, we will discuss the use of these technologies in the context of neuroinflammation.

Alrecon: computed tomography reconstruction web application based on Solara.

Synchrotron X-ray computed tomography is a non-destructive 3D imaging technique that offers the possibility to study the internal microstructure of samples with high spatial and temporal resolution. Given its unmatched image quality and acquisition speed, and the possibility to preserve the specimens, there is an increasing demand for this technique, from scientific users from innumerable disciplines. Computed tomography reconstruction is the computational process by which experimental radiographs are converted to a meaningful 3-dimensional image after the scan. The procedure involves pre-processing steps for image background and artifact correction on raw data, a reconstruction step approximating the inverse Radon-transform, and writing of the reconstructed volume image to disk. Several open-source Python packages exist to help scientists in the process of tomography reconstruction, by offering efficient implementations of reconstruction algorithms exploiting central or graphics processing unit (CPU and GPU, respectively), and by automating significant portions of the data processing pipeline. A further increase in productivity is attained by scheduling and parallelizing demanding reconstructions on high performance computing (HPC) clusters. Nevertheless, visual inspection and interactive selection of optimal reconstruction parameters remain crucial steps that are often performed in close interaction with the end-user of the data. As a result, the reconstruction task involves more than one software. Graphical user interfaces are provided to the user for fast inspection and optimization of reconstructions, while HPC resources are often accessed through scripts and command line interface. We propose Alrecon, a pure Python web application for tomographic reconstruction built using Solara. Alrecon offers users an intuitive and reactive environment for exploring data and customizing reconstruction pipelines. By leveraging upon popular 3D image visualization tools, and by providing a user-friendly interface for reconstruction scheduling on HPC resources, Alrecon guarantees productivity and efficient use of resources for any type of beamline user.

Compressed Sensitivity Encoding Artificial Intelligence Accelerates Brain Metastasis Imaging by Optimizing Image Quality and Reducing Scan Time.

Accelerating the image acquisition speed of MR imaging without compromising the image quality is challenging. This study aimed to evaluate the feasibility of contrast-enhanced (CE) 3D T1WI and CE 3D-FLAIR sequences reconstructed with compressed sensitivity encoding artificial intelligence (CS-AI) for detecting brain metastases (BM) and explore the optimal acceleration factor (AF) for clinical BM imaging. Fifty-one patients with cancer with suspected BM were included. Fifty participants underwent different customized CE 3D-T1WI or CE 3D-FLAIR sequence scans. Compressed SENSE encoding acceleration 6 (CS6), a commercially available standard sequence, was used as the reference standard. Quantitative and qualitative methods were used to evaluate image quality. The SNR and contrast-to-noise ratio (CNR) were calculated, and qualitative evaluations were independently conducted by 2 neuroradiologists. After exploring the optimal AF, sample images were obtained from 1 patient by using both optimized sequences. Quantitatively, the CNR of the CS-AI protocol for CE 3D-T1WI and CE 3D-FLAIR sequences was superior to that of the CS protocol under the same AF (P < .05). Compared with reference CS6, the CS-AI groups had higher CNR values (all P < .05), with the CS-AI10 scan having the highest value. The SNR of the CS-AI group was better than that of the reference for both CE 3D-T1WI and CE 3D-FLAIR sequences (all P < .05). Qualitatively, the CS-AI protocol produced higher image quality scores than did the CS protocol with the same AF (all P < .05). In contrast to the reference CS6, the CS-AI group showed good image quality scores until an AF of up to 10 (all P < .05). The CS-AI10 scan provided the optimal images, improving the delineation of normal gray-white matter boundaries and lesion areas (P < .05). Compared with the reference, CS-AI10 showed reductions in scan time of 39.25% and 39.93% for CE 3D-T1WI and CE 3D-FLAIR sequences, respectively. CE 3D-T1WI and CE 3D-FLAIR sequences reconstructed with CS-AI for the detection of BM may provide a more effective alternative reconstruction approach than CS. CS-AI10 is suitable for clinical applications, providing optimal image quality and a shortened scan time.

Fast Real-Time Brain Tumor Detection Based on Stimulated Raman Histology and Self-Supervised Deep Learning Model.

In intraoperative brain cancer procedures, real-time diagnosis is essential for ensuring safe and effective care. The prevailing workflow, which relies on histological staining with hematoxylin and eosin (H&E) for tissue processing, is resource-intensive, time-consuming, and requires considerable labor. Recently, an innovative approach combining stimulated Raman histology (SRH) and deep convolutional neural networks (CNN) has emerged, creating a new avenue for real-time cancer diagnosis during surgery. While this approach exhibits potential, there exists an opportunity for refinement in the domain of feature extraction. In this study, we employ coherent Raman scattering imaging method and a self-supervised deep learning model (VQVAE2) to enhance the speed of SRH image acquisition and feature representation, thereby enhancing the capability of automated real-time bedside diagnosis. Specifically, we propose the VQSRS network, which integrates vector quantization with a proxy task based on patch annotation for analysis of brain tumor subtypes. Training on images collected from the SRS microscopy system, our VQSRS demonstrates a significant speed enhancement over traditional techniques (e.g., 20-30min). Comparative studies in dimensionality reduction clustering confirm the diagnostic capacity of VQSRS rivals that of CNN. By learning a hierarchical structure of recognizable histological features, VQSRS classifies major tissue pathological categories in brain tumors. Additionally, an external semantic segmentation method is applied for identifying tumor-infiltrated regions in SRH images. Collectively, these findings indicate that this automated real-time prediction technique holds the potential to streamline intraoperative cancer diagnosis, providing assistance to pathologists in simplifying the process.

Interpolated Plane Wave Imaging: IPWI

This paper offers a solution to the problems caused by sub-Nyquist spatial sampling in ultrasound image generation, which can result in aliasing and grating lobes in Full Matrix Capture (FMC) and Plane Wave Imaging (PWI). Neglecting the spatial sampling requirements can lead to artifacts that compromise the accuracy of ultrasound image interpretation. Although limiting the transducer element pitch to half the wavelength can alleviate grating lobes, it can also cause reduced energy transmission and limit the method's applicability in thick-walled structures. Similarly, using sparse techniques to increase acquisition speed by subsampling the firing elements is also constrained by the sampling criterion. To address these challenges, we introduce an interpolation step to PWI, which overcomes ambiguities imposed by the sampling theorem and improves image quality and acquisition speed.

Explainable deep neural network for in-plain defect detection during additive manufacturing

PurposeThe purpose of this study is to develop a deep learning framework for additive manufacturing (AM), that can detect different defect types without being trained on specific defect data sets and can be applied for real-time process control.Design/methodology/approachThis study develops an explainable artificial intelligence (AI) framework, a zero-bias deep neural network (DNN) model for real-time defect detection during the AM process. In this method, the last dense layer of the DNN is replaced by two consecutive parts, a regular dense layer denoted (L1) for dimensional reduction, and a similarity matching layer (L2) for equal weight and non-biased cosine similarity matching. Grayscale images of 3D printed samples acquired during printing were used as the input to the zero-bias DNN.FindingsThis study demonstrates that the approach is capable of successfully detecting multiple types of defects such as cracks, stringing and warping with high accuracy without any prior training on defective data sets, with an accuracy of 99.5%.Practical implicationsOnce the model is set up, the computational time for anomaly detection is lower than the speed of image acquisition indicating the potential for real-time process control. It can also be used to minimize manual processing in AI-enabled AM.Originality/valueTo the best of the authors’ knowledge, this is the first study to use zero-bias DNN, an explainable AI approach for defect detection in AM.

A dynamic parallel image acquisition method for slide scanning process

Automated microscope systems have played an important role in the screening of numerous diseases. However, it is a very time-consuming process to continuously acquire images under the high magnification objective lens. This paper proposes a dynamic parallel image acquisition method, which can greatly improve image acquisition speed. Due to the relative motion between the x-y stage and the camera, some of the captured images have motion blur To this end, we also designed a motor variable speed motion curve to ensure the quality of the collected images. The experimental results show that the traditional image scanning mode needs 47.3 ms to obtain continuous microscopic images, while the dynamic parallel image acquisition method only needs 25.4 ms, which improves the acquisition speed without affecting the clarity of the acquired images.

Deep Neural Network for Visual Localization of Autonomous Car in ITS Campus Environment

Intelligent Car (I-Car) ITS is an autonomous car prototype where one of the main localization methods is obtained through reading GPS data. However the accuracy of GPS readings is influenced by the availability of the information from GPS satellites, in which it often depends on the conditions of the place at that time, such as weather or atmospheric conditions, signal blockage, and density of a land. In this paper we propose the solution to overcome the unavailability of GPS localization information based on the omnidirectional camera visual data through environmental recognition around the ITS campus using Deep Neural Network. The process of recognition is to take GPS coordinate data to be used as an output reference point when the omnidirectional camera takes images of the surrounding environment. Visual localization trials were carried out in the ITS environment with a total of 200 GPS coordinates, where each GPS coordinate represents one class so that there are 200 classes for classification. Each coordinate/class has 96 training images. This condition is achieved for a vehicle speed of 20 km/h, with an image acquisition speed of 30 fps from the omnidirectional camera. By using AlexNet architecture, the result of visual localization accuracy is 49-54%. The test results were obtained by using a learning rate parameter of 0.00001, data augmentation, and the Drop Out technique to prevent overfitting and improve accuracy stability.

Fast autofocus method for piezoelectric microscopy system for high interaction scenes.

Piezoelectric objective driver positioners are increasingly used in the field of microscopy. They have the advantages of high dynamic and fast response. This paper presents a fast autofocus algorithm for highly interactive microscope system. First, the Tenengrad gradient of the down-sampled image is used to calculate the image sharpness, and Brent search method is adopted to quickly converge to the correct focal length. At the same time, the input shaping method is used to eliminate the displacement vibration of the piezoelectric objective lens driver and further accelerate the image acquisition speed. Experimental results show that the proposed scheme can improve the speed of the automatic focusing task of the piezoelectric objective driver and improve the real-time focus of the automatic microscopic system. HIGHLIGHTS: A high real-time autofocus strategy. A vibration control method suitable for a piezoelectric objective driver.

Non-uniform image reconstruction for fast photoacoustic microscopy of histology imaging.

Photoacoustic microscopic imaging utilizes the characteristic optical absorption properties of pigmented materials in tissues to enable label-free observation of fine morphological and structural features. Since DNA/RNA can strongly absorb ultraviolet light, ultraviolet photoacoustic microscopy can highlight the cell nucleus without complicated sample preparations such as staining, which is comparable to the standard pathological images. Further improvements in the imaging acquisition speed are critical to advancing the clinical translation of photoacoustic histology imaging technology. However, improving the imaging speed with additional hardware is hampered by considerable costs and complex design. In this work, considering heavy redundancy in the biological photoacoustic images that overconsume the computing power, we propose an image reconstruction framework called non-uniform image reconstruction (NFSR), which exploits an object detection network to reconstruct low-sampled photoacoustic histology images into high-resolution images. The sampling speed of photoacoustic histology imaging is significantly improved, saving 90% of the time cost. Furthermore, NFSR focuses on the reconstruction of the region of interest while maintaining high PSNR and SSIM evaluation indicators of more than 99% but reducing the overall computation by 60%.

The General Population's Perspectives on Implementation of Artificial Intelligence in Radiology in the Western Region of Saudi Arabia.

Background Artificial intelligence (AI) is a broad spectrum of computer-executed operations that mimics the human intellect. It is expected to improve healthcare practice in general and radiology in particular by enhancing image acquisition, image analysis, and processing speed. Despite the rapid development of AI systems, successful application in radiology requires analysis of social factors such as the public's perspectives toward the technology. Objectives The current study aims to investigate the general population's perspectives on AI implementation in radiology in the Western region of Saudi Arabia. Methods A cross-sectional study was conducted from November 2022 and July 2023 utilizing a self-administrative online survey distributed via social media platforms. A convenience sampling technique was used to recruit the study participants. After obtaining Institutional Review Board approval, data were collected from citizens and residents of the western region of Saudi Arabia aged 18 years or older. Results A total of 1,024 participants were included in the present study, with the mean age of respondents being 29.6 ± 11.3. Of them, 49.9% (511) were men, and 50.1% (513) were women. The comprehensive mean score of the first four domains among our participants was 3.93 out of 5.00. Higher mean scores suggest being more negative regarding AI in radiology, except for the fifth domain. Respondents had less trust in AI utilization in radiology, as evidenced by their overall distrust and accountability domain mean score of 3.52 out of 5. The majority of respondents agreed that it is essential to understand every step of the diagnostic process, and the mean score for the procedural knowledge domain was 4.34 out of 5. The mean score for the personal interaction domain was 4.31 out of 5, indicating that the participants agreed on the value of direct communication between the patient and the radiologist for discussing test results and asking questions. Our data show that people think AI is more effective than human doctors in making accurate diagnoses and decreasing patient wait times, with an overall mean score of the efficiency domain of 3.56 out of 5. Finally, the fifth domain, "being informed," had a mean score of 3.91 out of 5. Conclusion The application of AI in radiologic assessment and interpretation is generally viewed negatively. Even though people think AI is more efficient and accurate at diagnosing than humans, they still think that computers will never be able to match a specialist doctor's years of training.

Confocal rescan structured illumination microscopy for real-time deep tissue imaging with superresolution

Structured illumination microscopy (SIM) is an established optical superresolution imaging technique. However, conventional SIM based on wide-field image acquisition is generally limited to visualizing thin cellular samples. We propose combining one-dimensional image rescan and structured illumination in the orthogonal direction to achieve superresolution without the need to rotate the illumination pattern. The image acquisition speed is consequently improved threefold, which is also beneficial for minimizing photobleaching and phototoxicity. Optical sectioning in thick biological tissue is enhanced by including a confocal slit in the system to significantly suppress the out-of-focus background and the associated noise. With all the technical improvements, our method captures three-dimensional superresolved image stacks of neuronal structures in mouse brain tissue samples for a depth range of more than 200 μm.

USE OF NEURAL NETWORKS FOR PLANNING THE CORRECT SELECTION OF PLANT AND SOIL SAMPLES IN PRECISION AGRICULTURE TECHNOLOGIES

The article is devoted to the study of the use of neural networks to optimize the selection of plant stands in precision agriculture technologies. The study takes into account the complex aspects of sample selection, such as the speed of image acquisition, the effectiveness of assessing the state of mineral nutrition and soil moisture, etc. This data is a necessary component for precision farming technologies and, in particular, crop management. Research was conducted on production fields in 2019-2020 in Boryspil district of Kyiv region. Spectral studies were performed using the Slantrange 3p complex installed on the UAV. Data processing was performed both with the specialized software for spectral data Slantview and with the mathematical package MathCad. The assessment of the nature of the distribution of both individual spectral channels and their combination in the form of vegetation indices turned out to be unprepared for the identification of uneven water supply of areas. The red channel and its derivatives turned out to be the most promising in the direction of identifying the water supply of wheat. The use of neural networks made it possible to identify probable areas with increased water supply on the maps of the distribution of vegetation indices in the field. The duration of identification using neural networks will not interfere with the sampling procedure, so that such a procedure can be effectively implemented in agronomic practices. Therefore, the use of neural networks allows you to automate and increase the accuracy of selection, improving the quality of the analysis of plant stands, subject to compliance with soil sample evaluation technologies. The obtained results indicate the prospects of implementing this approach in modern agriculture.

A modulation method that can improve the performance of LED multi-spectral imaging

In the LED multi-spectral imaging (LEDMSI) system, modulation by using the square wave frequency division with frequency ratio of 2 can improve the image quality and acquisition speed, but it will occupy a wide frequency band. Moreover, since there is a simultaneous change in the state of multiple signals when this method is used, it will lead to serious ringing phenomenon or insufficient slew rate and affect the quality of multi-spectral images. To solve the above problems, this paper proposes a modulation method for LEDMSI system, which uses n same frequency square wave signals with different phases as the carrier signals. Comparing the multi-spectral images modulated by the proposed method with the multi-spectral images modulated by the traditional method, experimental results show that the quality of the image modulated by the proposed method is higher, which indicates that the proposed method is of great significance to improve the performance of LEDMSI system.

Radiation Dose Reduction Opportunities in Vascular Imaging.

Computed tomography angiography (CTA) has been the gold standard imaging modality for vascular imaging due to a variety of factors, including the widespread availability of computed tomography (CT) scanners, the ease and speed of image acquisition, and the high sensitivity of CTA for vascular pathology. However, the radiation dose experienced by the patient during imaging has long been a concern of this image acquisition method. Advancements in CT image acquisition techniques in combination with advancements in non-ionizing radiation imaging techniques including magnetic resonance angiography (MRA) and contrast-enhanced ultrasound (CEUS) present growing opportunities to reduce total radiation dose to patients. This review provides an overview of advancements in imaging technology and acquisition techniques that are helping to minimize radiation dose associated with vascular imaging.

Adaptive Optics Imaging of Inherited Retinal Disease.

The human retina is amenable to direct, noninvasive visualization using a wide array of imaging modalities. In the ∼140 years since the publication of the first image of the living human retina, there has been a continued evolution of retinal imaging technology. Advances in image acquisition and processing speed now allow real-time visualization of retinal structure, which has revolutionized the diagnosis and management of eye disease. Enormous advances have come in image resolution, with adaptive optics (AO)-based systems capable of imaging the retina with single-cell resolution. In addition, newer functional imaging techniques provide the ability to assess function with exquisite spatial and temporal resolution. These imaging advances have had an especially profound impact on the field of inherited retinal disease research. Here we will review some of the advances and applications of AO retinal imaging in patients with inherited retinal disease.