Imaging Algorithm Research Articles

Self-supervised neural network for Patlak-based parametric imaging in dynamic [18F]FDG total-body PET.

The objective of this study is to generate reliable Ki parametric images from a shortened [18F]FDG total-body PET for clinical applications using a self-supervised neural network algorithm. We proposed a self-supervised neural network algorithm with Patlak graphical analysis (SN-Patlak) to generate Ki images from shortened dynamic [18F]FDG PET without 60-min full-dynamic PET-based training. The algorithm deeply integrates neural network architecture with a Patlak method, employing the fitting error of the Patlak plot as the neural network's loss function. As the 0-60min blood time activity curve (TAC) required by the standard Patlak plot is unobtainable from shortened dynamic PET scans, a population-based "normalized time" (integral-to-instantaneous blood concentration ratio) was used for the linear fitting of Patlak plot of t* to 60min, and the modified Patlak plot equation was then incorporated into the neural network. Ki images were generated by minimizing the difference between the input layer (measured tissue-to-blood concentration ratios) and the output layer (predicted tissue-to-blood concentration ratios). The effects of t* (20 to 50min post injection) on the Ki images generated from the SN-Patlak and standard Patlak was evaluated using the normalized mean square error (NMSE), and Pearson's correlation coefficient (Pearson's r). The Ki images generated by the SN-Patlak are robust to the dynamic PET scan duration, and the Ki images generated by the SN-Patlak from just a 10-minute (50-60min post-injection) dynamic [18F]FDG total-body PET scan are comparable to those generated by the standard Patlak method from 40-min (20-60min post injection) with NMSE = 0.15 ± 0.03 and Pearson's r = 0.93 ± 0.01. The SN-Patlak parametric imaging algorithm is robust and reliable for quantification of 10-min dynamic [18F]FDG total-body PET.

Correlation reconstruction mechanism based on dual wavelength imaging and neural network

In a natural light-field imaging scene, lighting is usually performed using a mixed light field of multiple wavelengths. To better meet the requirements of human vision, this study proposes a correlation reconstruction method based on dual-wavelength imaging and a neural network (compression sensing correlation fusion-reconstruction by dual-wavelength imaging and auto-encoder neural network, CSCFR-DWI-AENN). Two different wavelengths of light are mixed through an optical multiplexer unit (OMU) to form a dual-wavelength illumination light field, and the light intensity value reflected by the object is received by the detector. The object information was reconstructed using the compressed sensing ghost imaging algorithm, and the distribution of the illumination field was taken as prior information. Two single-wavelength illumination information and the detection value are used for compressed sensing reconstruction, and the high-quality reconstructed image of the target to be measured is obtained by combining the noise reduction advantage of the autoencoder neural network. Then the target information is fused by the New Sum of Modified Laplacian (NSML) algorithm. Two single-wavelength reconstruction, dual-wavelength direct reconstruction and the proposed reconstruction were compared respectively, and non-reference image quality evaluation functions such as EN, MI, EAV and SF were used to process and analyze the reconstruction effect. It is proved that this algorithm can reconstruct the object image comprehensively, reproduce the complete detail information, and achieve a more accurate, more comprehensive and more reliable description of the same object. It provides a theoretical basis for multi-wavelength imaging technology and has a good application prospect.

A submillimeter notch visualization detection method based on local wavenumber imaging algorithm of broadband laser-generated surface-wave

Abstract Laser ultrasound is widely used in metal notch detection because of its non-contact, non-destructive and high accuracy, but there is still the problem of insufficient detection sensitivity. Therefore, this paper proposes a laser ultrasound-based broadband surface wave local wavenumber imaging algorithm to provide an effective method for the detection of surface notches by taking the aluminum alloy metal structure as the research object. Broadband surface waves on a metal plate are excited by a laser, and vibration information is obtained through vibrometer scanning with a Laser Doppler Vibrometer(LDV). It characterizes the surface notches in the wavenumber domain by filtering out the direct waves and retaining only the reflected surface waves of the new modes generated by the notches, successfully detecting and visually characterizing the tiny surface notches at the sub-millimeter level. The surface notch defect detection experiment was carried out using a laser ultrasound detection platform, and the surface notch with a width and depth of 0.1mm detection. The effectiveness of the method was verified by repeated experiments. The results of the study provide an effective surface notch detection method for metallic structures which has a broad application prospect.

A study of blind denoising algorithms for two-scale real images based on partial differential equations

In order to better preserve the details and texture information in the image, a dual scale real image blind denoising algorithm based on partial differential equations is studied. Input real image information, perform small-scale denoising based on differential curvature partial differential equations, and combine with a new diffusion coefficient function to distinguish the edges, flat areas, and noise of the image, allowing the algorithm to retain more subtle information such as weak edges and textures while removing noise. For the large-scale information in the input real image, a multi-stage partial differential equation is used for denoising processing. Based on the mixed denoising method of 8-neighborhood and implicit curvature, a weight function is constructed to control the proportion of the two types of equations in image denoising, effectively achieving the goal of large-scale image denoising. The experimental results show that in the MATLAB coding platform, this algorithm can eliminate different types of noise, preserve more edge and detail information of the image, and improve the registration and recognition accuracy in the image application process.

DeepCervix: enhancing cervical cancer detection through transfer learning with VGG-16 architecture

Cervical cancer remains a significant global health concern, emphasizing the urgent need for improved detection methods to ensure timely treatment. This research introduces a sophisticated methodology leveraging recent advances in medical imaging and deep learning algorithms to enhance the accuracy and efficiency of cervical cancer detection. The proposed approach comprises meticulous data preprocessing to ensure the integrity of input images, followed by the training of deep learning models including ResNet-50, AlexNet, and VGG-16, renowned for their performance in computer vision tasks. Evaluation metrics such as accuracy, precision, recall, and F1-score demonstrate the efficacy of the methodology, with an outstanding accuracy rate of 98% achieved. The model’s proficiency in accurately distinguishing healthy cervical tissue from cancerous tissue is underscored by precision, recall, and F1-score values. The primary strength of this deep learning-based approach lies in its potential for early detection, promising significant impact on cervical cancer diagnosis and treatment outcomes. This methodology contributes to advancements in medical imaging techniques, facilitating improved outcomes in cervical cancer detection and treatment.

ISAR High Resolution Imaging Algorithm Based on Weighted Adaptive Mixed Norm

ISAR High Resolution Imaging Algorithm Based on Weighted Adaptive Mixed Norm

A scanning manometry method to image the atomization pressure field for pre-debugging the nanocomposite spraying system

Spray coating process stands out among film manufacturing techniques to fabricate nanocomposite films because of its high production efficiency, and broad material applicability. However, the issues such as blockages, overspray, and rebound in the spray coating process restrict the fabrication of high-quality nanocomposite films. The atomization pressure field describes the spraying characteristics, and measuring and analyzing this parameter is vital to ensure the spray coating process functions properly. In this paper, a scanning manometry method is proposed to measure the atomization pressure field. The method involves setting a tube array to scan the atomization field, and reconstructing the pressure distribution by applying an imaging algorithm. This paper elaborates on the technical principle, implementation steps, and calibration of the scanning manometry method. Besides, the proposed method was validated by designing an actual testing system, and the 2D and 3D distribution images of the atomization pressure field were successfully obtained. The scanning manometry method features great potential for applications in nanocomposite spraying systems, assisting in fine-tuning the systems and stabilizing the production of nanocomposite films.

Evaluation and comparison of synthetic computed tomography algorithms with 3T MRI for prostate radiotherapy: AI-based versus bulk density method.

Synthetic computed tomography (sCT)-algorithms, which generate computed tomography images from magnetic resonance imaging data, are becoming part of the clinical radiotherapy workflow. The aim of this retrospective study was to evaluate and compare commercial bulk-density-method (BM)-based and AI (artificial intelligence)-based-algorithms using 3T magnetic resonance imaging (MRI) with patient data as part of the local clinical commissioning process. 44 prostate radiotherapy patients were subjected to MRI and treatment planning CT (TPCT) scans. From the MRI images, sCT images with two different sCT algorithms were generated. The sCT images were evaluated by visual inspection of artifacts. Both sCT methods were compared to TPCT, with Dice similarity score(DSC) of bone and body contours, DVH parameters for CTV, bladder and rectum, and gamma-analysis. Accuracy for treatment alignment using sCT images was also tested. Various limits were used to define whether the differences between sCT methods to TPCT were clinically relevant (DVH parameters<2%, gamma-analysis passing rates 90%, 95%, and 98%, and the DSC 0.98 for body and 0.7 for bone). Our results show that, differences in CTV-dose coverage values were<2% in most of the patients with both sCT algorithms when compared to reference dose coverage. While AI-sCT had mean dose coverage difference<0,5% and BM-sCT<1%. Gamma-analysis showed that the AI-sCT mean passing rates were 95.4%, 98.6%, and 99.4% with 1mm1%, 2mm2%, and 3mm3% criteria, respectively. Similarly for BM-sCT the mean passing rates were 93.4%, 98.2%, and 99.2%. For the treatment alignment accuracy, the mean difference in magnitude of the translational shifts was 1.43mm for BM-sCT and 1.57mm for AI-sCT. Even though AI-sCT showed statistically better correspondence to TPCT, the differences were not clinically relevant with any of the limits. Visual evaluation showed artifacts in the AI-sCT especially in the bowel area and fiducial markers were not generated with either of the sCT algorithms. In conclusion, sCT-algorithms were clinically usable on prostate treatments using 3T MR-only workflow. While AI-sCT showed better correspondence to TPCT than BM-sCT, it generated characteristic artifacts. As sCT algorithms perform well, we still recommend testing the sCT-algorithms with retrospective analyses from patient data prior to implementing sCT into the routine workflow to better understand the specific limitations and capabilities of these algorithms.

Lamb wave S0/A0 mode conversion for imaging the internal structure of composite panel

Stiffened structures are utilised in various industries and their structural assessment is of paramount importance. In this paper, a novel, automated algorithm for internal structure imaging based on S0/A0 mode conversion effect is proposed. Moreover, a contrast indicator for the quantitative characterisation of structure imaging results was introduced. The research is exclusively experimental and focuses on fibre-reinforced, stiffened aerospace composite panel. Both non-contact (air-coupled transducer-ACT) and contact (piezoelectric transducer-PZT) methods of elastic wave generation were investigated. Low-frequency (40 kHz) wave generation was applied to ACT and PZT, while high-frequency excitations (100 kHz and 180 kHz) were analysed for the PZT. The results obtained for both excitation methods were compared. Full wavefield signals of elastic wave propagation were registered with a scanning laser Doppler vibrometer. The S0/A0 mode conversion observed on the specimens stiffeners led to the development of a new algorithm based on time–space guided wave signal filtering, which enables the imaging of the internal structure of the stiffened panel. The efficacy of the developed algorithm was proved to be higher than conventional weighted RMS (WRMS) and wave irregularity mapping (WIM) algorithms. The proposed method allows for the generation of easily interpretable maps illustrating discontinuities in the examined structure. The contrast indicator is two times higher for the proposed MCWA than for WRMS and WIM for wave frequency 100 kHz and three times higher for frequency 180 kHz.

A Resource Scheduling Algorithm for Multi-Target 3D Imaging in Radar Network Based on Deep Reinforcement Learning

A Resource Scheduling Algorithm for Multi-Target 3D Imaging in Radar Network Based on Deep Reinforcement Learning

Application and Optimization of a Fast Non-Local Means Noise Reduction Algorithm in Pediatric Abdominal Virtual Monoenergetic Images

In this study, we applied and optimized a fast non-local means (FNLM) algorithm to reduce noise in pediatric abdominal virtual monoenergetic images (VMIs). To analyze various contrast agent concentrations, we produced contrast agent concentration samples (20, 40, 60, 80, and 100%) and inserted them into a phantom model of a one-year-old pediatric patient. Single-energy computed tomography (SECT) and dual-energy computed tomography (DECT) images were acquired from the phantom, and 40 kilo-electron-volt (keV) VMI was acquired based on the DECT images. For the 40 keV VMI, the smoothing factor of the FNLM algorithm was applied from 0.01 to 1.00 in increments of 0.01. We derived the optimized value of the FNLM algorithm based on quantitative evaluation and performed a comparative assessment with SECT, DECT, and a total variation (TV) algorithm. As a result of the analysis, we found that the average contrast to noise ratio (CNR) and coefficient of variation (COV) of each concentration were most improved at a smoothing factor of 0.02. Based on these results, we derived the optimized smoothing factor value of 0.02. Comparative evaluation shows that the optimized FNLM algorithm improves the CNR and COV results by approximately 3.14 and 2.45 times, respectively, compared with the DECT image, and the normalized noise power spectrum result shows a 10−1 mm2 improvement. The main contribution of this study is to demonstrate the effectiveness of an optimized FNLM algorithm in reducing noise in pediatric abdominal VMI, allowing high-quality images to be acquired while reducing contrast dose. This advancement has significant implications for minimizing the risk of contrast-induced toxicity, especially in pediatric patients. Our approach addresses the problem of limited datasets in pediatric imaging by providing a computationally efficient noise reduction technique and highlights the clinical applicability of the FNLM algorithm. In addition, effective noise reduction enables high-contrast imaging with minimal radiation and contrast exposure, which is expected to be suitable for repeat CT examinations of pediatric liver cancer patients and other abdominal diseases.

A big data analysis algorithm for massive sensor medical images

Big data analytics for clinical decision-making has been proposed for various clinical sectors because clinical decisions are more evidence-based and promising. Healthcare data is so vast and readily available that big data analytics has completely transformed this sector and opened up many new prospects. The smart sensor-based big data analysis recommendation system has significant privacy and security concerns when using sensor medical images for suggestions and monitoring. The danger of security breaches and unauthorized access, which might lead to identity theft and privacy violations, increases when sending and storing sensitive medical data on the cloud. Our effort will improve patient care and well-being by creating an anomaly detection system based on machine learning specifically for medical images and providing timely treatments and notifications. Current anomaly detection methods in healthcare systems, such as artificial intelligence and big data analytics-intracerebral hemorrhage (AIBDA-ICH) and parallel conformer neural network (PCNN), face several challenges, including high resource consumption, inefficient feature selection, and an inability to handle temporal data effectively for real-time monitoring. Techniques like support vector machines (SVM) and the hidden Markov model (HMM) struggle with computational overhead and scalability in large datasets, limiting their performance in critical healthcare applications. Additionally, existing methods often fail to provide accurate anomaly detection with low latency, making them unsuitable for time-sensitive environments. We infer the extraction, feature selection, attack detection, and data collection and processing procedures to anticipate anomaly inpatient data. We transfer the data, take care of missing values, and sanitize it using the pre-processing mechanism. We employed the recursive feature elimination (RFE) and dynamic principal component analysis (DPCA) algorithms for feature selection and extraction. In addition, we applied the Auto-encoded genetic recurrent neural network (AGRNN) approach to identify abnormalities. Data arrival rate, resource consumption, propagation delay, transaction epoch, true positive rate, false alarm rate, and root mean square error (RMSE) are some metrics used to evaluate the proposed task.

Unlocking AutoML: Enhancing Data with Deep Learning Algorithms for Medical Imaging

Deep learning algorithms have become increasingly popular over the years, having proved their efficiency in input-output functions for distinct types of data. This technology is particularly useful in medical imaging, where complex image structures often generate disagreements between medical staff. These technologies can streamline the diagnostic process by performing automatic image analysis, which results in more accurate and reproducible diagnoses. Additionally, these technologies can enhance content retrieval systems by automatically labeling the images based on the structures they possess. Despite the benefits, the mathematical complexity of deep learning algorithms and their training optimizations can be challenging. Automated machine learning provides a solution to this challenge by offering tools that automate the development and training of these algorithms. This makes it possible for users with limited programming experience to take advantage of these powerful technologies to quickly develop and prototype analysis algorithms for their specific needs. This paper presents a management platform for deep learning services on the cloud that provides a code-free experience through automated machine learning. The evaluation was done in one of the most demanding scenarios, where the service was integrated into a research pathology PACS to annotate mitotic cells in breast cancer tissue automatically. The annotations are processed by an open-source PACS archive and stored directly on the files, enhancing the image metadata and consequently content retrieval systems. The results of the developed algorithms were compared to the state-of-the-art to evaluate the competitiveness of the solution.

Comparative Study on Encryption Algorithms for Autism MRI Scan Images

Healthcare centre is the most susceptible sctor. Cyber-attack on medical institutions, such as hospitals and health care centre have increased year after year. Autism health care centre is one of the victims. Autism MRI scan images include sensitive and confidential information about a patient's health and other personal information. Therefore, image encryption is a fundamental aspect of information security, especially in today's digital era where the proliferation of images and the need to protect sensitive visual content are of paramount importance. In order to protect the confidentiality and integrity of images, image encryption techniques work to make sure that only authorised users can view and understand the visual data while prohibiting unauthorised access and modification. The pixel values and spatial properties of the image are hidden using a variety of cryptographic methods and key-based actions. Symmetric encryption algorithm, like Advanced Encryption Standard (AES), which use the same key for encryption and decryption operations, are among the famous image encryption techniques. After that, asymmetric encryption algorithm like Rivest-Shamir-Adleman (RSA), which employ two distinct keys for both encryption and decryption. Next, the research includes a hybridization method of Elliptic Curve Cryptography (ECC) with the Hill Cypher (HC) for image encryption and decryption. There are five different Autism MRI Scan images selected to be used as the input image for encryption process. Then, each image will have two different file format which is PNG and BMP and two different file size which is 256*256px and 512*512px. This research's goal is to compare how well symmetric encryption, asymmetric encryption and hybrid encryption work as three separate image encryption techniques. This can help users rapidly and efficiently speed up the encryption and decryption of images and enhance the security of MRI scan images. By applying differential analysis parameters like Number of Pixel Change Rate (NPCR), Unified Average Changing Intensity (UACI) and statistical analysis parameters like Histogram Analysis (HA), the characteristics of the image encryption approach are examined. At the end of the experiment, AES encryption proves to be the best among the three types of encryption with better performance in terms of security with NPCR percentage of 99.72%, UACI percentage of 32.68% and has a higher speed of encryption which only takes 0.0238s but has the second-best distribution in HA of pixel value to frequency compares to ECC with HC.

Fractional flow reserve measurement using dynamic CT perfusion imaging in patients with coronary artery disease

Fractional flow reserve measurement using dynamic CT perfusion imaging in patients with coronary artery disease

An Automated Fingerprint Image Detection and Localization Approach-based Unsupervised Learning Algorithms using Low-quality Biometrics Plam Data

In this study, fingerprint identification and classification of low-quality fingerprints have been analyzed accordingly. As technology advances and methodologies evolve, staying at the forefront of research and innovation is imperative. The challenges addressed in this paper provide a foundation for future investigations and underscore the importance of developing resilient and adaptable biometric systems for real-world applications. The quest for accurate, efficient, and robust fingerprint identification in adverse conditions is a testament to the continuous evolution and refinement of machine learning and deep learning approaches in biometrics. While deep learning models exhibited improved performance, it is essential to acknowledge the need for further research and development in this domain. Additionally, integrating multimodal biometric systems and combining fingerprint data with other biometric modalities might present a viable avenue for mitigating the limitations associated with degraded fingerprints. In this paper, we develop a fingerprint identification approach for low-quality fingerprint images. The success rate accuracy of the propped algorithm for the low-quality fingerprint images should be significantly better than that of the standard local minutia approach. The main design of our deep learning approach is based on detecting and extracting the primary correlation during the training and using the correlation feature map to calculate the distance between the low-quality fingerprint images during the predicting phase. The experimental results show a very promising repulsing and high prediction accuracy.

Precision compensation method for large-scale measurements based on full-space refractive index field reconstruction with vibratory mirror background oriented schlieren (VMBOS)

With the development of the large-scale equipment manufacturing industry, such as aircraft component assembly, wind turbine rotor blade measurement and large ship assembly the demand for optical measurement accuracy in large-dimensional spaces within industrial environments has become increasingly stringent. However, due to the presence of internal interference sources, light will no longer propagate in a straight line, thereby introducing measurement errors that cannot be ignored. To compensate for the measurement error, the refractive index field distribution within the large-dimensional measurement space must be reconstructed. Therefore, this paper proposed a vibratory mirror background oriented schlieren (VMBOS) based on vibratory scanning. This method scans the measurement space through the rotation of vibratory mirror to obtain light deflection angles at different directions. Subsequently, the refractive index field of the large-dimensional space is reconstructed by using the tomographic reconstruction algorithm. Then the optical path of the light in the optical measurement can be corrected through the Hamiltonian ray tracing algorithm, thereby achieving compensation for the measurement error. Finally, the VMBOS method has been verified through both simulation and experimental methods. The experimental results demonstrated that the method proposed in this paper can be applied to optical path correction and error compensation in large scale spaces.

Non-linear super-resolution computed tomography imaging algorithm based on a discrete X-ray source focal spot model

Spatial resolution is one of the critical metrics for evaluating the performance of a computed tomography (CT) system. Traditional methods often neglected the influence of the focal spot size of the X-ray source, leading to data inconsistency and degrading the spatial resolution of the reconstructed images. Thus, this study introduces what we believe to be a novel non-linear super-resolution CT reconstruction method based on the characteristics of the X-ray source’s focal spot. The proposed method employed a discrete focal spot model and utilized measured focal spot information to formulate a non-linear mathematical model for CT imaging. Building on this model, a high-precision iterative solution method was developed. The proposed approach achieved improved data consistency during the forward projection process and employed a highly accurate solution method in the inversion process. As a result, this approach reconstructed images of higher quality compared to other methods, revealing more detailed structural information.

Evaluation of SR-DLR in low-dose abdominal CT: superior image quality and noise reduction.

To evaluate the effectiveness of super-resolution deep learning reconstruction (SR-DLR) in low-dose abdominal computed tomography (CT) imaging compared with hybrid iterative reconstruction (HIR) and conventional deep learning reconstruction (cDLR) algorithms. We retrospectively analyzed abdominal CT scans performed using a low-dose protocol. Three different image reconstruction algorithms-HIR, cDLR, and SR-DLR-were applied to the same raw image data. Objective evaluations included noise magnitude and contrast-to-noise ratio (CNR), as well as noise power spectrum (NPS) and edge rise slope (ERS). Subjective evaluations were performed by radiologists, who assessed image quality in terms of noise, artifacts, sharpness, and overall diagnostic utility. Raw CT image data were obtained from 35 patients (mean CTDIvol 11.0 mGy; mean DLP 344.8 mGy/cm). cDLR yielded the lowest noise levels and highest CNR (p < 0.001). However, SR-DLR outperformed cDLR in terms of noise texture and resolution, achieving the lowest NPS peak and highest ERS (p < 0.001 and p = 0.005, respectively). Subjectively, SR-DLR was rated highest across all categories, including noise, artifacts, sharpness, and overall image quality, with statistically significant differences compared to cDLR and HIR (p < 0.001). SR-DLR was the most effective reconstruction algorithm for low-dose abdominal CT imaging, offering superior image quality and noise reduction compared to cDLR and HIR. This suggests that SR-DLR can enhance the reliability and diagnostic accuracy of abdominal imaging, particularly in low-dose settings, making it a valuable tool in clinical practice.

Accelerating radio astronomy imaging with RICK

This paper presents an implementation of radio astronomy imaging algorithms on modern High Performance Computing (HPC) infrastructures, exploiting distributed memory parallelism and acceleration throughout multiple GPUs. Our code, called RICK (Radio Imaging Code Kernels), is capable of performing the major steps of the w-stacking algorithm presented in Offringa et al. (2014) both inter- and intra-node, and in particular has the possibility to run entirely on the GPU memory, minimising the number of data transfers between CPU and GPU. This feature, especially among multiple GPUs, is critical given the huge sizes of radio datasets involved.After a detailed description of the new implementations of the code with respect to the first version presented in Gheller et al. (2023), we analyse the performances of the code for each step involved in its execution. We also discuss the pros and cons related to an accelerated approach to this problem and its impact on the overall behaviour of the code. Such approach to the problem results in a significant improvement in terms of runtime with respect to the CPU version of the code, as long as the amount of computational resources does not exceed the one requested by the size of the problem: the code, in fact, is now limited by the communication costs, with the computation that gets heavily reduced by the capabilities of the accelerators.