De-noising Algorithm Research Articles

Generalized framework for the design of adaptive fractional-order masks for image denoising

This paper proposes a generalized fractional differential (GFD) mask which incorporates various fractional-order kernels such as power-law kernel, exponentional kernel, and Mittag-Leffler kernel, corresponding to Riemann-Liouville (RL)/Caputo, Caputo-Fabrizio (CF), and Atangana-Baleanu (AB) fractional-order differentials, respectively. Furthermore, a generalized fractional integral (GFI) mask incorporating RL and AB fractional integrals is put forward. The proposed generalized fractional masks provide a more flexible and appropriate tool for image enhancement and image denoising applications, and hence, avoids the construction of different masks for each kernel separately. Additionally, a generalized fractional integral and fractional differential based adaptive algorithm for image denoising (GFIFD-AA) is proposed. The proposedGFIFD-AA incorporates a novel noise detection method (NDM) for the detection of salt and pepper (SP) noise in images, which exhibits a profound advantage in avoiding misclassification of original pixels as noisy pixels when original image itself has some pixels with intensity values 0 or 255. The detected noisy pixels are processed by utilizing the proposed GFI-based adaptive mask (GFI-AM). The noise-free pixels are further updated by utilizing the proposed GFD-based adaptive mask (GFD-AM) so as to enhance the details of the image. Several standard and medical images of different characteristics are examined to evaluate the performance of the proposed approach on images affected by SP noise at various noise densities (i.e., 10%-95%). Furthermore, the performance of the proposed GFI mask is also tested for images affected by Gaussian noise and is compared against conventional fractional-order masks. The simulation results based upon several quantitative parameters validate the effectiveness of the proposed method against conventional methods.

Traffic flow prediction based on BILSTM model and data denoising scheme

Accurate prediction of road traffic flow is a significant part in the intelligent transportation systems. Accurate prediction can alleviate traffic congestion, and reduce environmental pollution. For the management department, it can make effective use of road resources. For individuals, it can help people plan their own travel paths, avoid congestion, and save time. Owing to complex factors on the road, such as damage to the detector and disturbances from environment, the measured traffic volume can contain noise. Reducing the influence of noise on traffic flow prediction is a piece of very important work. Therefore, in this paper we propose a combination algorithm of denoising and BILSTM to effectively improve the performance of traffic flow prediction. At the same time, three denoising algorithms are compared to find the best combination mode. In this paper, the wavelet (WL) denoising scheme, the empirical mode decomposition (EMD) denoising scheme, and the ensemble empirical mode decomposition (EEMD) denoising scheme are all introduced to suppress outliers in traffic flow data. In addition, we combine the denoising schemes with bidirectional long short-term memory (BILSTM) network to predict the traffic flow. The data in this paper are cited from performance measurement system (PeMS). We choose three kinds of road data (mainline, off ramp, on ramp) to predict traffic flow. The results for mainline show that data denoising can improve prediction accuracy. Moreover, prediction accuracy of BILSTM+EEMD scheme is the highest in the three methods (BILSTM+WL, BILSTM+EMD, BILSTM+EEMD). The results for off ramp and on ramp show the same performance as the results for mainline. It is indicated that this model is suitable for different road sections and long-term prediction.

An Improved Image Filtering Algorithm for Mixed Noise

In recent years, image filtering has been a hot research direction in the field of image processing. Experts and scholars have proposed many methods for noise removal in images, and these methods have achieved quite good denoising results. However, most methods are performed on single noise, such as Gaussian noise, salt and pepper noise, multiplicative noise, and so on. For mixed noise removal, such as salt and pepper noise + Gaussian noise, although some methods are currently available, the denoising effect is not ideal, and there are still many places worthy of improvement and promotion. To solve this problem, this paper proposes a filtering algorithm for mixed noise with salt and pepper + Gaussian noise that combines an improved median filtering algorithm, an improved wavelet threshold denoising algorithm and an improved Non-local Means (NLM) algorithm. The algorithm makes full use of the advantages of the median filter in removing salt and pepper noise and demonstrates the good performance of the wavelet threshold denoising algorithm and NLM algorithm in filtering Gaussian noise. At first, we made improvements to the three algorithms individually, and then combined them according to a certain process to obtain a new method for removing mixed noise. Specifically, we adjusted the size of window of the median filtering algorithm and improved the method of detecting noise points. We improved the threshold function of the wavelet threshold algorithm, analyzed its relevant mathematical characteristics, and finally gave an adaptive threshold. For the NLM algorithm, we improved its Euclidean distance function and the corresponding distance weight function. In order to test the denoising effect of this method, salt and pepper + Gaussian noise with different noise levels were added to the test images, and several state-of-the-art denoising algorithms were selected to compare with our algorithm, including K-Singular Value Decomposition (KSVD), Non-locally Centralized Sparse Representation (NCSR), Structured Overcomplete Sparsifying Transform Model with Block Cosparsity (OCTOBOS), Trilateral Weighted Sparse Coding (TWSC), Block Matching and 3D Filtering (BM3D), and Weighted Nuclear Norm Minimization (WNNM). Experimental results show that our proposed algorithm is about 2–7 dB higher than the above algorithms in Peak Signal-Noise Ratio (PSNR), and also has better performance in Root Mean Square Error (RMSE), Structural Similarity (SSIM), and Feature Similarity (FSIM). In general, our algorithm has better denoising performance, better restoration of image details and edge information, and stronger robustness than the above-mentioned algorithms.

GPR Image Noise Removal Using Grey Wolf Optimisation in the NSST Domain

Hyper-wavelet transforms, such as a non-subsampled shearlet transform (NSST), are one of the mainstream algorithms for removing random noise from ground-penetrating radar (GPR) images. Because GPR image noise is non-uniform, the use of a single fixed threshold for noisy coefficients in each sub-band of hyper-wavelet denoising algorithms is not appropriate. To overcome this problem, a novel NSST-based GPR image denoising grey wolf optimisation (GWO) algorithm is proposed. First, a time-varying threshold function based on the trend of noise changes in GPR images is proposed. Second, an edge area recognition and protection method based on the Canny algorithm is proposed. Finally, GWO is employed to select appropriate parameters for the time-varying threshold function and edge area protection method. The Natural Image Quality Evaluator is utilised as the optimisation index. The experiment results demonstrate that the proposed method provides excellent noise removal performance while protecting edge signals.

Design of Robust Heart Abnormality Detection System based on Wavelet Denoising Algorithm

The technology that continues to be developed by many researchers today is an automatic heart attack detection system based on an Electrocardiogram (ECG) signal. Several other studies have been carried out to build an Internet of Things (IoT) based heart abnormality detection system. Based on the analysis of related studies that have been carried out previously, several researchers have developed an ECG signal-based heart abnormality detection system using clean ECG signal data. While the reality of the concept of an IoT-based detection system, the process of recording ECG signal data on the sensor, the process of sending data to the server, and the process of retrieving data from the server are vulnerable to noise exposure. ECG signal containing noise will greatly affect the accuracy of system detection. This paper proposes the development of a noise-resistant heart condition detection system using a wavelet denoising algorithm. The process of denoising ECG signals using the Wavelet algorithm is generally able to improve the accuracy of detecting noisy ECG signals. The most significant increase in accuracy is seen in the low SNR value. The Daubechies 4 (db4) denoising algorithm is the best-performing algorithm. The ECG signal classification method uses the Artificial Neural Network (ANN) algorithm. Detection system hardware is also designed in this research using the concept based on the Internet of Things.

Investigation and Analysis of Voltage By Wavelet Denoising Algorithm for HTS NI Coil Excited by Rotating Flux Pump

High temperature superconducting (HTS) no-insulation (NI) magnet excited by rotating flux pump has the characteristics of high current density, high field stability and small volume, which is in accordance with the development trend of MRI/NMR equipment for main magnet. In poor electromagnetic environment, however, quench detection of direct electrometric method based on threshold judgment is easily interfered by noise and severely disrupted quench signal may cause wrong quench determination and malfunction of quench protection, thereby resulting in unnecessary loss. To suppress the influence of the noises caused by current fluctuation and the rotation of motor on the correction of quench determination or accurate reading of data. Therefore, this paper compares and analyzes the experimental and filtering data detected by equipment based on wavelet de-noising algorithm, and verifies the necessity of using wavelet filtering data.

An optimized pulse coupled neural network image de-noising method for a field-programmable gate array based polarization camera.

The quality of polarization images is easy to be affected by the noise in the image acquired by a polarization camera. Consequently, a de-noising method optimized with a Pulse Coupled Neural Network (PCNN) for polarization images is proposed for a Field-Programmable Gate Array (FPGA)-based polarization camera in this paper, in which the polarization image de-noising is implemented using an adaptive PCNN improved by Gray Wolf Optimization (GWO) and Bi-Dimensional Empirical Mode Decomposition (BEMD). Unlike other artificial neural networks, PCNN does not need to be trained, but the parameters of PCNN such as the exponential decay time constant, the synaptic junction strength factor, and the inherent voltage constant play a critical influence on its de-noising performance. GWO is able to start optimization by generating a set of random solutions as the first population and saves the optimized solutions of PCNN. In addition, BEMD can decompose a complicated image into different Bi-Dimensional Intrinsic Mode Functions with local stabilized characteristics according to the input source image, and the decomposition result is able to lower the complexity of heavy noise image analysis. Moreover, the circuit in the polarization camera is accomplished by FPGA so as to obtain the polarization image with higher quality synchronously. These two schemes are combined to attenuate different types of noises and improve the quality of the polarization image significantly. Compared with the state-of-the-art image de-noising algorithms, the noise in the polarization image is suppressed effectively by the proposed optimized image de-noising method according to the indices of peak signal-to-noise ratio, standard deviation, mutual information, structural similarity, and root mean square error.

De-noising drift chambers in CLAS12 using convolutional auto encoders

Modern Nuclear Physics experimental setups run experiments with higher beam intensity resulting in increased noise in detector components used for particle track reconstruction. Increased uncorrelated signals (noise) result in decreased particle reconstruction efficiency. In this paper, we investigate the usage of Machine Learning, specifically Convolutional Neural Network Auto-Encoders (CAE), for de-noising raw hits from drift chambers in the CLAS12 detector. To the best of our knowledge, this is the first time CAE is employed to perform such an operation in this field.During the de-noising phase, it is important to remove as much noise as possible while retaining the valid hits to avoid losing crucial information about the experiment. We show that using CAE, it is possible to remove noise hits while retaining up to 94% of valid tracks for a beam current of 110nA while for lower beam currents (45−55nA), we get up to 98% efficiency. Studies on experimental conditions with increasing noise show that CAE performs better than conventional tracking algorithms in isolating hits belonging to tracks. Specifically, the de-noising algorithm results in tracking efficiency improvements greater than 15%, in real data production procedures with nominal conditions, and up to two times better efficiency in synthetically generated data with high luminosity conditions (90−110nA), indicating that machine learning can lead to significantly shorter times for conducting physics experiments.

Doppler Ultrasound under Image Denoising Algorithm in the Diagnosis and Treatment of Fetal Growth Restriction Using Aspirin Combined with Low-Molecular-Weight Heparin.

Objective This study explored the clinical application value of image denoising algorithm combined with Doppler ultrasound imaging in evaluation of aspirin combined with low-molecular-weight heparin (LMWH) on fetal growth restriction (FGR). Method A two-stage image denoising by principal component analysis (PCA) with local pixel grouping (LPG-PCA) denoising algorithm was constructed in this study. Eighty FGR pregnant women were included in the study, and they were rolled into an experimental group (aspirin enteric-coated tablets + LMWH calcium injection) and a control group (LMWH calcium injection) according to the different treatment plans, with 40 cases in each group. All patients were performed with Doppler ultrasound imaging. The blood flow parameters (BFPs) were recorded and compared before and after the treatment in two groups, including power index (PI), resistance index (RI), high systolic blood flow velocity (S), high diastolic blood flow velocity (D), S/D value, and peak systolic velocity (PSV). In addition, the middle cerebral artery (MCA) BFPs, cerebral placental rate (CPR), amniotic fluid index (AFI) and perinatal outcome (PO) of the two groups were compared. Results The total effective rate of treatment in group A (87.5%) was greatly higher than that in group B (62.5%), showing statistical difference (P < 0.05). The PI (0.72 ± 0.19), RI (0.57 ± 0.17), and S/D values (2.26 ± 0.43) in group A were dramatically lower than those in group B, which were 0.92 ± 0.21, 0.75 ± 0.14, and 2.64 ± 0.45, respectively (P < 0.05), and the AFI was higher (13.71 ± 2.2 cm vs 11.38 ± 2.16 cm) (P < 0.05). The Apgar score (9.17 ± 0.26), weight (3.57 ± 1.08), and gestational age (38.85 ± 2.50) of group A were all higher in contrast to those of group B, which were 7.33 ± 0.25, 2.61 ± 1.13, and 36.18 ± 2.25, respectively (P < 0.05). In addition, the fetal double parietal diameter (2.4 ± 0.9 mm), femur diameter (2.2 ± 0.6 mm), head circumference (1.2 ± 0.4 mm), abdominal circumference (1.3 ± 0.7 mm), and uterine height (0.8 ± 0.3 mm) in group A were obviously superior to those in group B, which were 1.8 ± 0.4 mm, 1.7 ± 0.5 mm, 0.8 ± 0.2 mm, 0.9 ± 0.4 mm, and 0.4 ± 0.6 mm, respectively, showing statistically observable differences (P < 0.05). Conclusion Doppler ultrasound based on image denoising algorithm can accurately evaluate the effect of aspirin combined with LMWH on the improvement of FGR and showed good application value.

Development of learning-based noise reduction and image reconstruction algorithm in two dimensional Rayleigh thermometry

Consistent research efforts have been invested to deal with particles’ Mie scattering interference in Rayleigh measurements. This work reports an alternative learning-based image denoising and reconstruction algorithm to remove high value Mie scattering noise in Rayleigh thermometry. The algorithm, named denoising generative adversarial network (DNGAN), consists of a generator and a discriminator to learn the texture features and infer denoised image with a given noisy counterpart. Training data of the neural network come from artificially generated noise-free Rayleigh image superimposed with experimentally acquired Mie scattering image. Extensive evaluations are then conducted to prove the superiority of the proposed DNGAN network, compared with several other neural networks reported in literature. Quantitative results show that a convincing denoising with an overall reconstruction error of ~ 0.6% a peak signal-to-noise ratio of ~ 43 dB can be reached. Moreover, the pre-trained network is able to denoise image of the jet flame with a different Reynolds number without retraining the network parameters.

A novel wavelet threshold denoising and deep belief network fault detection algorithm

For oil pipeline leakage fault detection problems, a novel negative pressure wave (NPW) leak detection method based on wavelet threshold denoising and deep belief network (Wavelet-DBN) is proposed. Firstly, the wavelet threshold denoising method is used to deal with the sample pressure signal, and the results of wavelet denoising with different wavelet basis functions and different decomposition levels are compared. The optimal parameters are selected for wavelet denoising and the characteristic information of a pipeline pressure signal is extracted. Secondly, in order to improve the accuracy of the pipeline leakage monitoring method based on NPW, the deep belief network algorithms are proposed to classify and identify the NPW sample signals. Finally, the sample data are collected from the industrial oil pipeline leakage experiment. The simulation experimental results show that the proposed method has a higher accuracy rate than other traditional machine learning methods, such as support vector machines, and reduces the false alarm rate of oil pipeline leakage monitoring.

Research on de-noising method of fiber grating multiplexing network based on LCEEMD-LWT

A de-noising algorithm combining local complementary ensemble empirical mode decomposition (LCEEMD) and lifting wavelet transform technology (LWT) is proposed to deal with the crosstalk noise buildup in high-capacity fiber grating multiplexing networks. Complementary ensemble empirical mode decomposition (CEEMD) serves for decompose this original spectral signal, and the normalization permutation en-tropy (NPE) is applied for identifying high-frequency nonlinear sequences in low-order intrinsic mode function to suppress the random noise. The filtering accuracy is improved by further decomposing the high-frequency intrinsic mode function with LWT. Finally, reconstruction of de-noised signal. The simulation results show that the LCEEMD-LWT method achieves better quality evaluation indexes than LCEEMD and EEMD-LWT when processing 1dBlow SNR spectral signal. To study the noise elimination capability of this devised method for nonlinear non-stationary semaphores, this de-trended fluctuation analysis (DFA) algorithm served for evaluating the results. It is indicted that this devised way has this highest fractal scaling index (2.114), which is better than other de-noising methods.

Geometric Characteristics of the Wasserstein Metric on SPD(n) and Its Applications on Data Processing.

The Wasserstein distance, especially among symmetric positive-definite matrices, has broad and deep influences on the development of artificial intelligence (AI) and other branches of computer science. In this paper, by involving the Wasserstein metric on , we obtain computationally feasible expressions for some geometric quantities, including geodesics, exponential maps, the Riemannian connection, Jacobi fields and curvatures, particularly the scalar curvature. Furthermore, we discuss the behavior of geodesics and prove that the manifold is globally geodesic convex. Finally, we design algorithms for point cloud denoising and edge detecting of a polluted image based on the Wasserstein curvature on . The experimental results show the efficiency and robustness of our curvature-based methods.

InNetGAN: Inception Network-Based Generative Adversarial Network for Denoising Low-Dose Computed Tomography.

Low-dose Computed Tomography (LDCT) has gained a great deal of attention in clinical procedures due to its ability to reduce the patient's risk of exposure to the X-ray radiation. However, reducing the X-ray dose increases the quantum noise and artifacts in the acquired LDCT images. As a result, it produces visually low-quality LDCT images that adversely affect the disease diagnosing and treatment planning in clinical procedures. Deep Learning (DL) has recently become the cutting-edge technology of LDCT denoising due to its high performance and data-driven execution compared to conventional denoising approaches. Although the DL-based models perform fairly well in LDCT noise reduction, some noise components are still retained in denoised LDCT images. One reason for this noise retention is the direct transmission of feature maps through the skip connections of contraction and extraction path-based DL modes. Therefore, in this study, we propose a Generative Adversarial Network with Inception network modules (InNetGAN) as a solution for filtering the noise transmission through skip connections and preserving the texture and fine structure of LDCT images. The proposed Generator is modeled based on the U-net architecture. The skip connections in the U-net architecture are modified with three different inception network modules to filter out the noise in the feature maps passing over them. The quantitative and qualitative experimental results have shown the performance of the InNetGAN model in reducing noise and preserving the subtle structures and texture details in LDCT images compared to the other state-of-the-art denoising algorithms.

Finger Vein De-noising Algorithm Based on Custom Sample-Texture Conditional Generative Adversarial Nets

Finger Vein De-noising Algorithm Based on Custom Sample-Texture Conditional Generative Adversarial Nets

Fast dictionary learning for 3D simultaneous seismic data reconstruction and denoising

Simultaneous seismic data reconstruction and denoising is a hot research topic. The sparse representation method based on dictionary learning is one of the most effective methods to reconstruct seismic data and suppress noise. Sparse dictionary traditionally uses the K-means singular value decompositions (K-SVD) method for learning. However, the main disadvantage of K-SVD is that it requires many singular value decompositions (SVDs), which is low in computational efficiency and not suitable for practical applications, especially in high-dimensional problems. To address the computational efficiency problem of K-SVD, we propose a fast dictionary learning method based on sequence generalized K-means (SGK) algorithm for efficient reconstruction and denoising of 3D seismic data. In SGK algorithm, dictionary atoms are updated by arithmetic average of several training signals instead of singular value decomposition in the K-SVD algorithm. The performance of the two methods is verified by 3D numerical examples. The results demonstrate that the proposed reconstruction and denoising method using SGK can achieve comparable performance as the K-SVD method but significantly improve the computational efficiency.

Evaluation of Severity of Infectious Pneumonia for Newborn Using Ultrasound Image under Adaptive Image Denoising Algorithm

This study was to analyze the ultrasound imaging characteristics of infectious pneumonia of newborn in different conditions and the differences in neurobehavioral development. An adaptive image denoising (AID) algorithm was constructed based on multiscale wavelet features. It was compared with the transform domain denoising (TDD) algorithm and spatial domain denoising (SDD) algorithm and applied to ultrasound images of newborns with infectious pneumonia. It was found that the peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and feature similarity index (FSIM) of the constructed algorithm were higher than those of the TDD and SDD algorithms ( P &lt; 0.05 ). The ultrasound scores of newborns in noncritical group (group A, 1.54 ± 0.62 scores) were all lower than those of the critical group (group B, 3.96 ± 0.41 scores) and extremely critical group (group C, 4.25 ± 0.35 scores) ( P &lt; 0.05 ). The behavioral ability, passive muscle tension, active muscle tension, and original reflection of the newborns in group A were better than other groups ( P &lt; 0.05 ). It indicated that the constructed algorithm showed better denoising effect on ultrasound images, which could effectively evaluate the severity of newborns’ infectious pneumonia.

Image Definition Evaluations on Denoised and Sharpened Wood Grain Images

Decorative paper and wood veneer have been widely used in the surface decoration of wood-based panels. These surface decoration methods require two-dimensional image acquisition of natural wood grain to obtain the digital grain. However, optically scanned images sometimes produce noise during the process of image acquisition and transmission. In this situation, scanned images cannot be used directly in wood grain reproductions. To reduce noise and retain or strengthen the image sharpness, studies are mostly aimed at the improvement of classic denoising algorithms and edge width-based sharpness evaluation algorithms. To enhance accessibility for common users, four kinds of wood grain images with distinct colors were chosen, and the noise filter (Dust &amp; Scratches) and sharpen filter (Unsharp Mask, USM) were used to denoise and sharpen the images. According to the properties of the two filters, image definition in this study was considered from two aspects: detail retention and sharpness retention. To have an objective evaluation on the definition of denoised and sharpened images, two types of evaluation functions Roberts gradient function (RGF) and modulation transfer function (MTF) were introduced. The purpose of this study was to estimate the image definition by exploring the relationships between the evaluation functions and the commonly used filters in order to allow the required wood grain images to be quickly and accurately processed by common users. The results showed that RGF was only applicable to the case where the two parameters in Dust &amp; Scratches were changed individually, while MTF was not suitable in any case. When both parameters were changed, the required denoising scheme could be obtained through PSNR and SSIM. For the images with distinct colors, even if they were acquired in the same way, denoising them with the same parameter setting was not recommended. For sharpness retention, the values of Radius and Amount in USM were given, and when the Threshold value was set to 20 (levels), the sharpness of the wood grain images barely changed. In this case, both RGF and MTF were suitable to evaluate the sharpness of the wood grain images sharpened by USM.

Research on denoising algorithm of thoracic impedance signal for respiratory monitoring during running exercise

Pulmonary Function Exercise Test (PFET) or Cardio Pulmonary Exercise Test (CPET) using spirometer, as a method for early detection of pulmonary dysfunction or an effective supplement method to conventional pulmonary function test, has considerable clinical significance. However, the spirometer that uses air flowmeter to measure exhale/inhale air flowrate and flow velocity, increases respiratory resistance and is not comfortable for using during physical exercise. Thoracic impedance is sensitive to pulmonary ventilation and has no disturbance to human airway, hence is more suitable for respiratory monitoring, nevertheless it is influenced by many other factors, such as body movement during running exercises. In this paper, we first analyze the characteristics of thoracic impedance collected during running exercise, then put forward a wpsTID (wavelet and polynomial smoothing methods based Thoracic Impedance Denoising) algorithm to remove high-frequency alternating noises and motion artifacts to obtain clean thoracic impedance information that varies only with the pulmonary ventilation. The wpsTID algorithm is compared with a few other denoising algorithms using synthetic thoracic impedance data that containing known noises, and demonstrated to have the best performance in retaining respiratory information from the original signal and suppressing noises, which lays a foundation for the undisturbed monitoring of pulmonary ventilation during running with impedance method. Finally, the wpsTID algorithm is further verified with thoracic impedance signals of healthy volunteers measured during different kinds of motions.

Comparative Analysis of Low-Rank Matrix Denoising Algorithm-Based MRI and CT Images in Diagnosis of Cerebral Aneurysms

This study aimed to compare the role of magnetic resonance imaging (MRI) and computed tomography (CT) images based on the low-rank matrix (LRM) denoising (LRMD) algorithm in the diagnosis of cerebral aneurysms (CAs). By comparing the role of MRI and CT in the diagnosis of CA, it would be helpful to formulate more reasonable diagnosis strategies and provide a solid foundation for clinical treatment of patients. 80 patients with cerebral aneurysm admitted to hospital were selected as the research objects. First, the LRMD algorithm was established and applied to the image denoising process of MRI and CT. Then, the diagnosis rate of CA by MRI and CT before and after denoising was compared, and the diagnostic rates of the two methods for aneurysms of different sizes were compared. Finally, the location, foci, and patient satisfaction of the aneurysm were compared. The results showed that the MRI and CT images after denoising with LRM were clearer, and the secondary structures in the brain were more obvious. It meant that LRMD had good image denoising effect. The diagnostic rate of denoised MRI and CT was improved. Although the difference was not statistically notable, the diagnostic rate of CT was obviously higher in contrast to MRI ( P &lt; 0.05 ). The diagnostic rate of CT for smaller aneurysms (&lt;3 mm and 3–5 mm) was also notably higher in contrast to MRI ( P &lt; 0.05 ). However, there was no difference in the diagnosis of tumor location between the two. The clarity of CT diagnostic images was better than MRI ( P &lt; 0.05 ). Accordingly, patients were more satisfied with CT in contrast to MRI ( P &lt; 0.05 ). In summary, CT images based on the LRMD algorithm were superior to MRI in the diagnosis of CA, and it could provide more accurate diagnosis results.