Deep Learning-based Denoising Research Articles

Enhancing diffusion-weighted prostate MRI through self-supervised denoising and evaluation

Diffusion-weighted imaging (DWI) is a magnetic resonance imaging (MRI) technique that provides information about the Brownian motion of water molecules within biological tissues. DWI plays a crucial role in stroke imaging and oncology, but its diagnostic value can be compromised by the inherently low signal-to-noise ratio (SNR). Conventional supervised deep learning-based denoising techniques encounter challenges in this domain as they necessitate noise-free target images for training. This work presents a novel approach for denoising and evaluating DWI scans in a self-supervised manner, eliminating the need for ground-truth data. By leveraging an adapted version of Stein’s unbiased risk estimator (SURE) and exploiting a phase-corrected combination of repeated acquisitions, we outperform both state-of-the-art self-supervised denoising methods and conventional non-learning-based approaches. Additionally, we demonstrate the applicability of our proposed approach in accelerating DWI scans by acquiring fewer image repetitions. To evaluate denoising performance, we introduce a self-supervised methodology that relies on analyzing the characteristics of the residual signal removed by the denoising approaches.

437 - Fast and low dose myocardial perfusion imaging SPECT using deep learning-based denoising

437 - Fast and low dose myocardial perfusion imaging SPECT using deep learning-based denoising

Self-inspired learning for denoising live-cell super-resolution microscopy.

Every collected photon is precious in live-cell super-resolution (SR) microscopy. Here, we describe a data-efficient, deep learning-based denoising solution to improve diverse SR imaging modalities. The method, SN2N, is a Self-inspired Noise2Noise module with self-supervised data generation and self-constrained learning process. SN2N is fully competitive with supervised learning methods and circumvents the need for large training set and clean ground truth, requiring only a single noisy frame for training. We show that SN2N improves photon efficiency by one-to-two orders of magnitude and is compatible with multiple imaging modalities for volumetric, multicolor, time-lapse SR microscopy. We further integrated SN2N into different SR reconstruction algorithms to effectively mitigate image artifacts. We anticipate SN2N will enable improved live-SR imaging and inspire further advances.

Study of Acoustic Emission Signal Noise Attenuation Based on Unsupervised Skip Neural Network.

Acoustic emission (AE) technology, as a non-destructive testing methodology, is extensively utilized to monitor various materials' structural integrity. However, AE signals captured during experimental processes are often tainted with assorted noise factors that degrade the signal clarity and integrity, complicating precise analytical evaluations of the experimental outcomes. In response to these challenges, this paper introduces an unsupervised deep learning-based denoising model tailored for AE signals. It juxtaposes its efficacy against established methods, such as wavelet packet denoising, Hilbert transform denoising, and complete ensemble empirical mode decomposition with adaptive noise denoising. The results demonstrate that the unsupervised skip autoencoder model exhibits substantial potential in noise reduction, marking a significant advancement in AE signal processing. Subsequently, the paper focuses on applying this advanced denoising technique to AE signals collected during the tensile testing of steel fiber-reinforced concrete (SFRC), the tensile testing of steel, and flexural experiments of reinforced concrete beam, and it meticulously discusses the variations in the waveform and the spectrogram of the original signal and the signal after noise reduction. The results show that the model can also remove the noise of AE signals.

A Novel Network for Low-Dose CT Denoising Based on Dual-Branch Structure and Multi-Scale Residual Attention.

Deep learning-based denoising of low-dose medical CT images has received great attention both from academic researchers and physicians in recent years, and has shown important application value in clinical practice. In this work, a novel two-branch and multi-scale residual attention-based network for low-dose CT image denoising is proposed. It adopts a two-branch framework structure, to extract and fuse image features at shallow and deep levels respectively, to recover image texture and structure information as much as possible. We propose the adaptive dynamic convolution block (ADCB) in the local information extraction layer. It can effectively extract the detailed information of low-dose CT denoising and enables the network to better capture the local details and texture features of the image, thereby improving the denoising effect and image quality. Multi-scale edge enhancement attention block (MEAB) is proposed in the global information extraction layer, to perform feature fusion through dilated convolution and a multi-dimensional attention mechanism. A multi-scale residual convolution block (MRCB) is proposed to integrate feature information and improve the robustness and generalization of the network. To demonstrate the effectiveness of our method, extensive comparison experiments are conducted and the performances evaluated on two publicly available datasets. Our model achieves 29.3004 PSNR, 0.8659 SSIM, and 14.0284 RMSE on the AAPM-Mayo dataset. It is evaluated by adding four different noise levels σ = 15, 30, 45, and 60 on the Qin_LUNG_CT dataset and achieves the best results. Ablation studies show that the proposed ADCB, MEAB, and MRCB modules improve the denoising performances significantly. The source code is available at https://github.com/Ye111-cmd/LDMANet .

Deep Learning-Based Denoising Enables High-Quality, Fully Diagnostic Neuroradiological Trauma CT at 25% Radiation Dose

Traumatic neuroradiological emergencies necessitate rapid and accurate diagnosis, often relying on computed tomography (CT). However, the associated ionizing radiation poses long-term risks. Modern artificial intelligence reconstruction algorithms have shown promise in reducing radiation dose while maintaining image quality. Therefore, we aimed to evaluate the dose reduction capabilities of a deep learning-based denoising (DLD) algorithm in traumatic neuroradiological emergency CT scans. This retrospective single-center study included 100 patients with neuroradiological trauma CT scans. Full-dose (100%) and low-dose (25%) simulated scans were processed using iterative reconstruction (IR2) and DLD. Subjective and objective image quality assessments were performed by four neuroradiologists alongside clinical endpoint analysis. Bayesian sensitivity and specificity were computed with 95% credible intervals. Subjective analysis showed superior scores for 100% DLD compared to 100% IR2 and 25% IR2 (p<0.001). No significant differences were observed between 25% DLD and 100% IR2. Objective analysis revealed no significant CT value differences but higher noise at 25% dose for DLD and IR2 compared to 100% (p<0.001). DLD exhibited lower noise than IR2 at both dose levels (p<0.001). Clinical endpoint analysis indicated equivalence to 100% IR2 in fracture detection for all datasets, with sensitivity losses in hemorrhage detection at 25% IR2. DLD (25% and 100%) maintained comparable sensitivity to 100% IR2. All comparisons demonstrated robust specificity. The evaluated algorithm enables high-quality, fully diagnostic CT scans at 25% of the initial radiation dose and improves patient care by reducing unnecessary radiation exposure.

Deep learning-based denoising of spatial heterodyne spectroscopy interferograms without clear images

A newly developed spectroscopic method called spatial heterodyne spectroscopy (SHS) characterized by grating space diffraction, compact size, high etendue, larger optical tolerance, and no moving parts. Spatial heterodyne spectroscopy has many uses, including atmospheric remote sensing, atmospheric composition research, and so on. However, due to the features of the sensor material and the operating environment, various noise will be introduced throughout the CCD image acquisition process. The imaging performance of the device will be reduced or possibly disabled as a result of these noise effects. We demonstrate how deep learning techniques may be used to denoise SHS images. Furthermore, we propose the use of N2N (noise2noise, noise to noise) method for the difficulty of deep learning to obtain a large number of target-noise pair. This method trains the deep learning network using only noisy images, which greatly reduces the difficulty of acquiring training data. We analyzed denoising data for monochromatic and continuous light. In terms of interferograms, the experimental results show that the deep neural network trained using this method can effectively recover interferogram image information, suppress noise, and maintain the continuity of the interference fringe edge. In terms of spectrograms, the deep neural network trained by this approach can suppress noise in monochromatic spectra and retrieve spectral signals damaged by noise in continuous spectra. As a result, the technique is suitable for spatial heterodyne spectroscopy denoising.

A Deep Learning Lidar Denoising Approach for Improving Atmospheric Feature Detection

Space-based atmospheric backscatter lidars provide critical information about the vertical distribution of clouds and aerosols, thereby improving our understanding of the climate system. They are additionally useful for detecting hazards to aviation and human health, such as volcanic plumes and man-made pollution events. The Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP, 2006–2023), Cloud-Aerosol Transport System (CATS, 2015–2017), and Advanced Topographic Laser Altimeter System (ATLAS 2018–present) are three such lidars that operated within the past 20 years. The signal-to-noise ratio (SNR) for these lidars is significantly lower in daytime data compared with nighttime data due to the solar background signal increasing the detector response noise. Averaging horizontally across profiles has been the standard way to increase SNR, but this comes at the expense of resolution. Modern, deep learning-based denoising algorithms can be applied to improve the SNR without coarsening resolution. This paper describes how one such model architecture, Dense Dense U-Net (DDUNet), was trained to denoise CATS 1064 nm raw signal data (photon counts) using artificially noised nighttime data. Simulated CATS daytime 1064 nm data were then created to assess the model’s performance. The denoised simulated data increased the daytime SNR by a factor of 2.5 (on average) and decreased minimum detectable backscatter (MDB) to ~7.3×10−4 km−1sr−1, which is lower than the CALIOP 1064 nm night MDB value of 8.6×10−4 km−1sr−1. Layer detection was performed on simulated 2 km horizontal resolution denoised and 60 km averaged data. Despite the finer resolution input, the denoised layers had more true positives, fewer false positives, and an overall Jaccard Index of 0.54 versus 0.44 when compared to the layers detected on averaged data. Layer detection was also performed on a full month of denoised daytime CATS data (Aug. 2015) to detect layers for comparison with CATS standard Level 2 (L2) product layers. The detection on the denoised data yielded 2.33 times more, higher-quality bins within detected layers at 2.7–33 times finer resolution than the CATS L2 products.

Progressive Feature Fusion Attention Dense Network for Speckle Noise Removal in OCT Images.

Although deep learning for Big Data analytics has achieved promising results in the field of optical coherence tomography (OCT) image denoising, the low recognition rate caused by complex noise distribution and a large number of redundant features is still a challenge faced by deep learning-based denoising methods. Moreover, the network with large depth will bring high computational complexity. To this end, we propose a progressive feature fusion attention dense network (PFFADN) for speckle noise removal in OCT images. We arrange densely connected dense blocks in the deep convolution network, and sequentially connect the shallow convolution feature map with the deep one extracted from each dense block to form a residual block. We add attention mechanism to the network to extract the key features and suppress the irrelevant ones. We fuse the output feature maps from all dense blocks and input them to the reconstruction output layer. We compare PFFADN with the state-of-the-art denoising algorithms on retinal OCT images. Experiments show that our method has better improvement in denoising performance.

PSO-optimized SSLMS adaptive filter for signal denoising of rolling bearings under small sample condition

Abstract To address the issue that the deep learning-based denoising algorithms can hardly effectively eliminate the background noise under small sample data condition, this paper proposes a new denoising method based on spectral subtraction (SS) and least mean square (LMS) adaptive filtering algorithms. To achieve the adaptive selection for the parameters of SS and LMS algorithms, particle swarm optimization (PSO) approach is employed to search and optimize the parameters in the two algorithms, which is helpful for the two algorithms to play an important role in eliminating the noise components with the different properties. Subsequently, the SS algorithm and the LMS algorithm are appropriately combined, and the SS-processed signal is input into the LMS algorithm as a desired signal to actualize the LMS adaptive filtering function. In this way, the denoising performance of both algorithms can be maximally utilized, which achieves effective noise reduction in vibration signal. The effectiveness and superiority of the proposed method are validated through simulation data and rolling bearing experiment data, respectively. The results demonstrate that the proposed method significantly diminishes noise components and retains precise and reliable fault features under small sample data condition, which provides an effective denoising method for rolling bearing vibration signals under small sample data condition in practical engineering scenarios.&amp;#xD;

Impact of Various Non-Contrast-Enhanced MRA Techniques on Lumen Visibility in Vascular Flow Models with a Surpass Evolve Flow Diverter.

Silent MRA has shown promising results in evaluating the stents used for intracranial aneurysm treatment. A deep learning-based denoising and deranging algorithm was recently introduced by GE HealthCare. The purpose of this study was to compare the performance of several MRA techniques regarding lumen visibility in silicone models with flow diverter stents. Two Surpass Evolve stents of different sizes were implanted in two silicone tubes. The tubes were placed in separate boxes in the straight position and in two different curve configurations and connected to a pulsatile pump to construct a flow loop. Using a 3.0T MRI scanner, TOF and silent MRA images were acquired, and deep learning reconstruction was applied to the silent MRA dataset. The intraluminal signal intensity in the stent (SIin-stent), in the tube outside the stent (SIvessel), and of the background (SIbg) were measured for each scan. The SIin-stent/SIbg and SIin-stent/SIv ratios were higher in the silent scans and DL-based reconstructions than in the TOF images. The stent tips created severe artefacts in the TOF images, which could not be observed in the silent scans. Our study demonstrates that the DL reconstruction algorithm improves the quality of the silent MRA technique in evaluating the flow diverter stent patency.

Improved noise reduction in photon-counting detector CT using prior knowledge-aware iterative denoising neural network.

We aim to reduce image noise in high-resolution (HR) virtual monoenergetic images (VMIs) from photon-counting detector (PCD) CT scans by developing a prior knowledge-aware iterative denoising neural network (PKAID-Net) that efficiently exploits the unique noise characteristics of VMIs at different energy (keV) levels. PKAID-Net offers two major features: first, it utilizes a lower-noise VMI (e.g., 70keV) as a prior input; second, it iteratively constructs a refined training dataset to improve the neural network's denoising performance. In each iteration, the denoised image from the previous module serves as an updated target image, which is included in the dataset for the subsequent training iteration. Our study includes 10 patient coronary CT angiography exams acquired on a clinical dual-source PCD-CT (NAEOTOM Alpha, Siemens Healthineers). The HR VMIs were reconstructed at 50, 70, and 100keV, using a sharp vascular kernel (Bv68) and thin (0.6mm) slice thickness (0.3mm increment). PKAID-Net's performance was evaluated in terms of image noise, spatial detail preservation, and quantitative accuracy. PKAID-Net achieved a noise reduction of 96% compared to filtered back projection and 65% relative to iterative reconstruction, all while preserving spatial and spectral fidelity and maintaining a natural noise texture. The iterative refinement of PCD-CT data during the training process substantially enhanced the robustness of deep learning-based denoising compared to the original method, which resulted in some spatial detail loss. The PKAID-Net provides substantial noise reduction while maintaining spatial and spectral fidelity of the HR VMIs from PCD-CT.

Assessment of image quality and impact of deep learning-based software in non-contrast head CT scans

In this retrospective study, we aimed to assess the objective and subjective image quality of different reconstruction techniques and a deep learning-based software on non-contrast head computed tomography (CT) images. In total, 152 adult head CT scans (77 female, 75 male; mean age 69.4 ± 18.3 years) obtained from three different CT scanners using different protocols between March and April 2021 were included. CT images were reconstructed using filtered-back projection (FBP), iterative reconstruction (IR), and post-processed using a deep learning-based algorithm (PS). Post-processing significantly reduced noise in FBP-reconstructed images (up to 15.4% reduction) depending on the protocol, leading to improvements in signal-to-noise ratio of up to 19.7%. However, when deep learning-based post-processing was applied to FBP images compared to IR alone, the differences were inconsistent and partly non-significant, which appeared to be protocol or site specific. Subjective assessments showed no significant overall improvement in image quality for all reconstructions and post-processing. Inter-rater reliability was low and preferences varied. Deep learning-based denoising software improved objective image quality compared to FBP in routine head CT. A significant difference compared to IR was observed for only one protocol. Subjective assessments did not indicate a significant clinical impact in terms of improved subjective image quality, likely due to the low noise levels in full-dose images.

Improved Resolution and Image Quality of Musculoskeletal Magnetic Resonance Imaging using Deep Learning-based Denoising Reconstruction: A Prospective Clinical Study.

To prospectively evaluate a deep learning-based denoising reconstruction (DLR) for improved resolution and image quality in musculoskeletal (MSK) magnetic resonance imaging (MRI). Images from 137 contrast-weighted sequences in 40 MSK patients were evaluated. Each sequence was performed twice, first with the routine parameters and reconstructed with a routine reconstruction filter (REF), then with higher resolution and reconstructed with DLR, and with three conventional reconstruction filters (NL2, GA43, GA53). The five reconstructions (REF, DLR, NL2, GA43, and GA53) were de-identified, randomized, and blindly reviewed by three MSK radiologists using eight scoring criteria and a forced ranking. Quantitative SNR, CNR, and structure's full width at half maximum (FWHM) for resolution assessment were measured and compared. To account for repeated measures, Generalized Estimating Equations (GEE) with Bonferroni adjustment was used to compare the reader's scores, SNR, CNR, and FWHM between DLR vs. NL2, GA43, GA53, and REF. Compared to the routine REF images, the resolution was improved by 47.61% with DLR from 0.39 ± 0.15 mm2 to 0.20 ± 0.06 mm2 (p < 0.001). Per-sequence average scan time was shortened by 7.93% with DLR from 165.58 ± 21.86 s to 152.45 ± 25.65 s (p < 0.001). Based on the average scores, DLR images were rated significantly higher in all image quality criteria and the forced ranking (p < 0.001). This prospective clinical evaluation demonstrated that DLR allows approximately two times finer resolution and improved image quality compared to the standard-of-care images.

A deep learning framework for suppressing prestack seismic random noise without noise-free labels

Random noise attenuation is significant in seismic data processing. Supervised deep learning-based denoising methods have been widely developed and applied in recent years. In practice, it is often time-consuming and laborious to obtain noise-free data for supervised learning. Therefore, we propose a novel deep learning framework to denoise prestack seismic data without clean labels, which trains a high-resolution residual neural network (SRResnet) with noisy data for input and the same valid data with different noise for output. Since valid signals in noisy sample pairs are spatially correlated and random noise is spatially independent and unpredictable, the model can learn the features of valid data while suppressing random noise. Noisy data targets are generated by a simple conventional method without fine-tuning parameters. The initial estimates allow signal or noise leakage as the network does not require clean labels. The Monte Carlo strategy is applied to select training patches for increasing valid patches and expanding training datasets. Transfer learning is used to improve the generalization of real data processing. The synthetic and real data tests perform better than the commonly used state-of-the-art denoising methods.

Denoising Multiphase Functional Cardiac CT Angiography Using Deep Learning and Synthetic Data.

Coronary CT angiography is increasingly used for cardiac diagnosis. Dose modulation techniques can reduce radiation dose, but resulting functional images are noisy and challenging for functional analysis. This retrospective study describes and evaluates a deep learning method for denoising functional cardiac imaging, taking advantage of multiphase information in a three-dimensional convolutional neural network. Coronary CT angiograms (n = 566) were used to derive synthetic data for training. Deep learning-based image denoising was compared with unprocessed images and a standard noise reduction algorithm (block-matching and three-dimensional filtering [BM3D]). Noise and signal-to-noise ratio measurements, as well as expert evaluation of image quality, were performed. To validate the use of the denoised images for cardiac quantification, threshold-based segmentation was performed, and results were compared with manual measurements on unprocessed images. Deep learning-based denoised images showed significantly improved noise compared with standard denoising-based images (SD of left ventricular blood pool, 20.3 HU ± 42.5 [SD] vs 33.4 HU ± 39.8 for deep learning-based image denoising vs BM3D; P < .0001). Expert evaluations of image quality were significantly higher in deep learning-based denoised images compared with standard denoising. Semiautomatic left ventricular size measurements on deep learning-based denoised images showed excellent correlation with expert quantification on unprocessed images (intraclass correlation coefficient, 0.97). Deep learning-based denoising using a three-dimensional approach resulted in excellent denoising performance and facilitated valid automatic processing of cardiac functional imaging. Keywords: Cardiac CT Angiography, Deep Learning, Image Denoising Supplemental material is available for this article. © RSNA, 2024.

Towards safer imaging: A comparative study of deep learning-based denoising and iterative reconstruction in intraindividual low-dose CT scans using an in-vivo large animal model

PurposeComputed tomography (CT) scans are a significant source of medically induced radiation exposure. Novel deep learning-based denoising (DLD) algorithms have been shown to enable diagnostic image quality at lower radiation doses than iterative reconstruction (IR) methods. However, most comparative studies employ low-dose simulations due to ethical constraints. We used real intraindividual animal scans to investigate the dose-reduction capabilities of a DLD algorithm in comparison to IR. Materials and methodsFourteen veterinarian-sedated alive pigs underwent 2 CT scans on the same 3rd generation dual-source scanner with two months between each scan. Four additional scans ensued each time, with mAs reduced to 50 %, 25 %, 10 %, and 5 %. All scans were reconstructed ADMIRE levels 2 (IR2) and a novel DLD algorithm, resulting in 280 datasets. Objective image quality (CT numbers stability, noise, and contrast-to-noise ratio) was measured via consistent regions of interest. Three radiologists independently rated all possible dataset combinations per time point for subjective image quality (−1 = inferior, 0 = equal, 1 = superior). The points were averaged for a semiquantitative score, and inter-rater agreement was measured using Spearman's correlation coefficient and adequately corrected mixed-effects modeling analyzed objective and subjective image quality. ResultsNeither dose-reduction nor reconstruction method negatively impacted CT number stability (p > 0.999). In objective image quality assessment, the lowest radiation dose achievable by DLD when comparing noise (p = 0.544) and CNR (p = 0.115) to 100 % IR2 was 25 %. Overall, inter-rater agreement of the subjective image quality ratings was strong (r ≥ 0.69, mean 0.93 ± 0.05, 95 % CI 0.92–0.94; each p < 0.001), and subjective assessments corroborated that DLD at 25 % radiation dose was comparable to 100 % IR2 in image quality, sharpness, and contrast (p ≥ 0.281). ConclusionsThe DLD algorithm can achieve image quality comparable to the standard IR method but with a significant dose reduction of up to 75%. This suggests a promising avenue for lowering patient radiation exposure without sacrificing diagnostic quality.

Flexible and accurate total variation and cascaded denoisers-based image reconstruction algorithm for hyperspectrally compressed ultrafast photography

Hyperspectrally compressed ultrafast photography (HCUP) based on compressed sensing and time- and spectrum-to-space mappings can simultaneously realize the temporal and spectral imaging of non-repeatable or difficult-to-repeat transient events with a passive manner in single exposure. HCUP possesses an incredibly high frame rate of tens of trillions of frames per second and a sequence depth of several hundred, and therefore plays a revolutionary role in single-shot ultrafast optical imaging. However, due to ultra-high data compression ratios induced by the extremely large sequence depth, as well as limited fidelities of traditional algorithms over the image reconstruction process, HCUP suffers from a poor image reconstruction quality and fails to capture fine structures in complex transient scenes. To overcome these restrictions, we report a flexible image reconstruction algorithm based on a total variation (TV) and cascaded denoisers (CD) for HCUP, named the TV-CD algorithm. The TV-CD algorithm applies the TV denoising model cascaded with several advanced deep learning-based denoising models in the iterative plug-and-play alternating direction method of multipliers framework, which not only preserves the image smoothness with TV, but also obtains more priori with CD. Therefore, it solves the common sparsity representation problem in local similarity and motion compensation. Both the simulation and experimental results show that the proposed TV-CD algorithm can effectively improve the image reconstruction accuracy and quality of HCUP, and may further promote the practical applications of HCUP in capturing high-dimensional complex physical, chemical and biological ultrafast dynamic scenes.

Quantitative analysis of deep learning-based denoising model efficacy on optical coherence tomography images with different noise levels

BackgroundTo quantitatively evaluate the effectiveness of the Noise2Noise (N2N) model, a deep learning (DL)-based noise reduction algorithm, on enhanced depth imaging-optical coherence tomography (EDI-OCT) images with different noise levels. MethodsThe study included 30 subfoveal EDI-OCT images averaged with 100 frames from 30 healthy participants. Artificial Gaussian noise at 25.00, 50.00, and 75.00 standard deviations were added to the averaged (original) images, and the images were grouped as 25N, 50N, and 75N. Afterward, noise-added images were denoised with the N2N model and grouped as 25dN, 50dN, and 75dN, according to previous noise levels. The choroidal vascularity index (CVI) and deep choroidal contrast-to-noise ratio (CNR) were calculated for all images, and noise-added and denoised images were compared with the original images. The structural similarity of the noise-added and denoised images to the original images was assessed by the Multi-Scale Structural Similarity Index (MS-SSI). ResultsThe CVI and CNR parameters of the original images (68.08 ± 2.47 %, and 9.71 ± 2.80) did not differ from the only 25dN images (67.97 ± 2.34 % and 8.50 ± 2.43) (p:1.000, and p:0.062, respectively). Noise reduction improved the MS-SSI at each noise level (p < 0.001). However, the highest MS-SSI was achieved in 25dN images. ConclusionsThe DL-based N2N denoising model can be used effectively for images with low noise levels, but at increasing noise levels, this model may be insufficient to provide both the original structural features of the choroid and structural similarity to the original image.

Deep Learning-Based Denoising of CEST MR Data: A Feasibility Study on Applying Synthetic Phantoms in Medical Imaging.

Chemical Exchange Saturation Transfer (CEST) magnetic resonance imaging (MRI) provides a novel method for analyzing biomolecule concentrations in tissues without exogenous contrast agents. Despite its potential, achieving a high signal-to-noise ratio (SNR) is imperative for detecting small CEST effects. Traditional metrics such as Magnetization Transfer Ratio Asymmetry (MTRasym) and Lorentzian analyses are vulnerable to image noise, hampering their precision in quantitative concentration estimations. Recent noise-reduction algorithms like principal component analysis (PCA), nonlocal mean filtering (NLM), and block matching combined with 3D filtering (BM3D) have shown promise, as there is a burgeoning interest in the utilization of neural networks (NNs), particularly autoencoders, for imaging denoising. This study uses the Bloch-McConnell equations, which allow for the synthetic generation of CEST images and explores NNs efficacy in denoising these images. Using synthetically generated phantoms, autoencoders were created, and their performance was compared with traditional denoising methods using various datasets. The results underscored the superior performance of NNs, notably the ResUNet architectures, in noise identification and abatement compared to analytical approaches across a wide noise gamut. This superiority was particularly pronounced at elevated noise intensities in the in vitro data. Notably, the neural architectures significantly improved the PSNR values, achieving up to 35.0, while some traditional methods struggled, especially in low-noise reduction scenarios. However, the application to the in vivo data presented challenges due to varying noise profiles. This study accentuates the potential of NNs as robust denoising tools, but their translation to clinical settings warrants further investigation.