Protecting Prostate Cancer Classification From Rectal Artifacts via Targeted Adversarial Training.

Magnetic resonance imaging (MRI)-based deep neural networks (DNN) have been widely developed to perform prostate cancer (PCa) classification. However, in real-world clinical situations, prostate MRIs can be easily impacted by rectal artifacts, which have been found to lead to incorrect PCa classification. Existing DNN-based methods typically do not consider the interference of rectal artifacts on PCa classification, and do not design specific strategy to address this problem. In this study, we proposed a novel Targeted adversarial training with Proprietary Adversarial Samples (TPAS) strategy to defend the PCa classification model against the influence of rectal artifacts. Specifically, based on clinical prior knowledge, we generated proprietary adversarial samples with rectal artifact-pattern adversarial noise, which can severely mislead PCa classification models optimized by the ordinary training strategy. We then jointly exploited the generated proprietary adversarial samples and original samples to train the models. To demonstrate the effectiveness of our strategy, we conducted analytical experiments on multiple PCa classification models. Compared with ordinary training strategy, TPAS can effectively improve the single- and multi-parametric PCa classification at patient, slice and lesion level, and bring substantial gains to recent advanced models. In conclusion, TPAS strategy can be identified as a valuable way to mitigate the influence of rectal artifacts on deep learning models for PCa classification.

The effect of elimination of gibbs ringing, noise and systematic errors on the DTI metrics and tractography in a rat brain.

Diffusion tensor imaging (DTI) metrics and tractography can be biased due to low signal-to-noise ratio (SNR) and systematic errors resulting from image artifacts and imperfections in magnetic field gradients. The imperfections include non-uniformity and nonlinearity, effects caused by eddy currents, and the influence of background and imaging gradients. We investigated the impact of systematic errors on DTI metrics of an isotropic phantom and DTI metrics and tractography of a rat brain measured at high resolution. We tested denoising and Gibbs ringing removal methods combined with the B matrix spatial distribution (BSD) method for magnetic field gradient calibration. The results showed that the performance of the BSD method depends on whether Gibbs ringing is removed and the effectiveness of stochastic error removal. Region of interest (ROI)-based analysis of the DTI metrics showed that, depending on the size of the ROI and its location in space, correction methods can remove systematic bias to varying degrees. The preprocessing pipeline proposed and dedicated to this type of data together with the BSD method resulted in an even - 90% decrease in fractional anisotropy (FA) (globally and locally) in the isotropic phantom and - 45% in the rat brain. The largest global changes in the rat brain tractogram compared to the standard method without preprocessing (sDTI) were noticed after denoising. The direction of the first eigenvector obtained from DTI after denoising, Gibbs ringing removal and BSD differed by an average of 56 and 10 degrees in the ROI from sDTI and from sDTI after denoising and Gibbs ringing removal, respectively. The latter can be identified with the amount of improvement in tractography due to the elimination of systematic errors related to imperfect magnetic field gradients. Based on the results, the systematic bias for high resolution data mainly depended on SNR, but the influence of non-uniform gradients could also be seen. After denoising, the BSD method was able to further correct both the metrics and tractography of the diffusion tensor in the rat brain by taking into account the actual distribution of magnetic field gradients independent of the examined object and uniquely dependent on the scanner and sequence. This means that in vivo studies are also subject to this type of errors, which should be taken into account when processing such data.

Enhancing image quality in computed tomography angiography follow-ups after endovascular aneurysm repair: a comparative study of reconstruction techniques.

BACKGROUND: The image quality of computed tomography angiography (CTA) images following endovascular aneurysm repair (EVAR) is not satisfactory, since artifacts resulting from metallic implants obstruct the clear depiction of stent and isolation lumens, and also adjacent soft tissues. However, current techniques to reduce these artifacts still need further advancements due to higher radiation doses, longer processing times and so on. Thus, the aim of this study is to assess the impact of utilizing Single-Energy Metal Artifact Reduction (SEMAR) alongside a novel deep learning image reconstruction technique, known as the Advanced Intelligent Clear-IQ Engine (AiCE), on image quality of CTA follow-ups conducted after EVAR. MATERIALS: This retrospective study included 47 patients (mean age ± standard deviation: 68.6 ± 7.8 years; 37 males) who underwent CTA examinations following EVAR. Images were reconstructed using four different methods: hybrid iterative reconstruction (HIR), AiCE, the combination of HIR and SEMAR (HIR + SEMAR), and the combination of AiCE and SEMAR (AiCE + SEMAR). Two radiologists, blinded to the reconstruction techniques, independently evaluated the images. Quantitative assessments included measurements of image noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), the longest length of artifacts (AL), and artifact index (AI). These parameters were subsequently compared across different reconstruction methods. RESULTS: The subjective results indicated that AiCE + SEMAR performed the best in terms of image quality. The mean image noise intensity was significantly lower in the AiCE + SEMAR group (25.35 ± 6.51 HU) than in the HIR (47.77 ± 8.76 HU), AiCE (42.93 ± 10.61 HU), and HIR + SEMAR (30.34 ± 4.87 HU) groups (p < 0.001). Additionally, AiCE + SEMAR exhibited the highest SNRs and CNRs, as well as the lowest AIs and ALs. Importantly, endoleaks and thrombi were most clearly visualized using AiCE + SEMAR. CONCLUSIONS: In comparison to other reconstruction methods, the combination of AiCE + SEMAR demonstrates superior image quality, thereby enhancing the detection capabilities and diagnostic confidence of potential complications such as early minor endleaks and thrombi following EVAR. This improvement in image quality could lead to more accurate diagnoses and better patient outcomes.

Verification of the effect of data-driven brain motion correction on PET imaging.

INTRODUCTION: Brain positron emission tomography/computed tomography (PET/CT) scans are useful for identifying the cause of dementia by evaluating glucose metabolism in the brain with F-18-fluorodeoxyglucose or Aß deposition with F-18-florbetaben. However, since imaging time ranges from 10 to 30 minutes, movements during the examination might result in image artifacts, which interfere with diagnosis. To solve this problem, data-driven brain motion correction (DDBMC) techniques are capable of performing motion corrected reconstruction using highly accurate motion estimates with high temporal resolution. In this study, we investigated the effectiveness of DDBMC techniques on PET/CT images using a Hoffman phantom, involving continuous rotational and tilting motion, each expanded up to approximately 20 degrees. MATERIALS AND METHODS: Listmode imaging was performed using a Hoffman phantom that reproduced rotational and tilting motions of the head. Brain motion correction processing was performed on the obtained data. Reconstructed images with and without brain motion correction processing were compared. Visual evaluations by a nuclear medicine specialist and quantitative parameters of images with correction and reference still images were compared. RESULTS: Normalized Mean Squared Error (NMSE) results demonstrated the effectiveness of DDBMC in compensating for rotational and tilting motions during PET imaging. In Cases 1 and 2 involving rotational motion, NMSE decreased from 0.15-0.2 to approximately 0.01 with DDBMC, indicating a substantial reduction in differences from the reference image across various brain regions. In the Structural Similarity Index (SSIM), DDBMC improved it to above 0.96 Contrast assessment revealed notable improvements with DDBMC. In continuous rotational motion, % contrast increased from 42.4% to 73.5%, In tilting motion, % contrast increased from 52.3% to 64.5%, eliminating significant differences from the static reference image. These findings underscore the efficacy of DDBMC in enhancing image contrast and minimizing motion induced variations across different motion scenarios. CONCLUSIONS: DDBMC processing can effectively compensate for continuous rotational and tilting motion of the head during PET, with motion angles of approximately 20 degrees. However, a significant limitation of this study is the exclusive validation of the proposed method using a Hoffman phantom; its applicability to the human brain has not been investigated. Further research involving human subjects is necessary to assess the generalizability and reliability of the presented motion correction technique in real clinical scenarios.

Application Value of a Novel Micro-Coil in High-Resolution Imaging of Experimental Mice Based on 3.0 T Clinical MR.

The clinical magnetic resonance scanner (field strength ≤ 3.0 T) has limited efficacy in the high-resolution imaging of experimental mice. This study introduces a novel magnetic resonance micro-coil designed to enhance the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), thereby improving high-resolution imaging in experimental mice using clinical magnetic resonance scanners. Initially, a phantom was utilized to determine the maximum spatial resolution achievable by the novel micro-coil. Subsequently, 12 C57BL/6JGpt mice were included in this study, and the novel micro-coil was employed for their scanning. A clinical flexible coil was selected for comparative analysis. The scanning methodologies for both coils were consistent. The imaging clarity, noise, and artifacts produced by the two coils on mouse tissues and organs were subjectively evaluated, while the SNR and CNR of the brain, spinal cord, and liver were objectively measured. Differences in the images produced by the two coils were compared. The results indicated that the maximum spatial resolution of the novel micro-coil was 0.2 mm. Furthermore, the subjective evaluation of the images obtained using the novel micro-coil was superior to that of the flexible coil (p < 0.05). The SNR and CNR measurements for the brain, spinal cord, and liver using the novel micro-coil were significantly higher than those obtained with the flexible coil (p < 0.001). Our study suggests that the novel micro-coil is highly effective in enhancing the image quality of clinical magnetic resonance scanners in experimental mice.

Knotted artifacts in predicted 3D RNA structures.

Unlike proteins, RNAs deposited in the Protein Data Bank do not contain topological knots. Recently, admittedly, the first trefoil knot and some lasso-type conformations have been found in experimental RNA structures, but these are still exceptional cases. Meanwhile, algorithms predicting 3D RNA models have happened to form knotted structures not so rarely. Interestingly, machine learning-based predictors seem to be more prone to generate knotted RNA folds than traditional methods. A similar situation is observed for the entanglements of structural elements. In this paper, we analyze all models submitted to the CASP15 competition in the 3D RNA structure prediction category. We show what types of topological knots and structure element entanglements appear in the submitted models and highlight what methods are behind the generation of such conformations. We also study the structural aspect of susceptibility to entanglement. We suggest that predictors take care of an evaluation of RNA models to avoid publishing structures with artifacts, such as unusual entanglements, that result from hallucinations of predictive algorithms.

When in Doubt, Add SPECT/CT: A Case of Mistaken Identity.

A 63-y-old woman with a history of breast cancer presented with concerns of osseous metastasis. Initial whole-body planar bone scintigraphy revealed a focus of concern overlying the sternum. SPECT/CT images revealed the anomaly-localized activity in the needleless hub attached to the chemotherapy port. If not for the precision of SPECT/CT, such a rare artifact could have led to a false-positive diagnosis, particularly impactful in breast cancer patients. This case emphasizes the critical role of SPECT/CT in accurate diagnoses.

Channel-Specific and Spatial Residual Attention Network for Medical Image Denoising.

Medical image quality is crucial for physicians to ensure accurate diagnosis and therapeutic strategies. However, due to the interference of noise, there are often various types of noise and artifacts in medical images. This not only damages the visual clarity of images, but also reduces the accuracy of information extraction. Considering that the edges of medical images are rich in high-frequency information, to enhance the quality of medical images, a dual attention mechanism, the channel-specific and spatial residual attention network (CSRAN) in the U-Net framework is proposed. The CSRAN seamlessly integrates the U-Net architecture with channel-wise and spatial feature attention (CSAR) modules, as well as low-frequency channel attention modules. Combined with the two modules, the ability of medical image processing to extract high-frequency features is improved, thereby significantly improving the edge effects and clarity of reconstructed images. This model can present better performance in capturing high-frequency information and spatial structures in medical image denoising and super-resolution reconstruction tasks. It cannot only enhance the ability to extract high-frequency features and strengthen its nonlinear representation capability, but also endow strong edge detection capabilities of the model. The experimental results further prove the superiority of CSRAN in medical image denoising and super-resolution reconstruction tasks.

Narrow band-pass filtered canonical correlation analysis for frequency identification in SSVEP signals.

Steady-state visual evoked potentials (SSVEP) are generated in the parieto-occipital regions, accompanied by background noise and artifacts. A strong pre-processing method is required to reduce this background noise and artifacts. This study proposed a narrow band-pass filtered canonical correlation analysis (NBPFCCA) to recognize frequency components in SSVEP signals. The proposed method is tested on the publicly available 40 stimulus frequencies dataset recorded from 35 subjects and 4 class in-house dataset acquired from 10 subjects. The performance of the proposed NBPFCCA method is compared with the standard canonical correlation analysis (CCA) and the filter bank CCA (FBCCA). The mean frequency detection accuracy of the standard CCA is 86.21% for the benchmark dataset, and it is improved to 95.58% in the proposed method. Results indicate that the proposed method significantly outperforms the standard canonical correlation analysis with an increase of 9.37% and 17% in frequency recognition accuracy of the benchmark and in-house datasets, respectively.

[Real-time Detection Method for Motion Artifact of Photoplethysmography Signals Based on Decision Trees].

PPG (photoplethysmography) holds significant application value in wearable and intelligent health devices. However, during the acquisition process, PPG signals can generate motion artifacts due to inevitable coupling motion, which diminishes signal quality. In response to the challenge of real-time detection of motion artifacts in PPG signals, this study analyzed the generation and significant features of PPG signal interference. Seven features were extracted from the pulse interval data, and those exhibiting notable changes were filtered using the dual-sample Kolmogorov-Smirnov test. The real-time detection of motion artifacts in PPG signals was ultimately based on decision trees. In the experimental phase, PPG signal data from 20 college students were collected to formulate the experimental dataset. The experimental results demonstrate that the proposed method achieves an average accuracy of (94.07±1.14)%, outperforming commonly used motion artifact detection algorithms in terms of accuracy and real-time performance.

[Methods for Processing Physiological Artifacts in Single/Few-Channel EEG Signals].

Electroencephalogram (EEG) is a non-invasive measurement method of brain electrical activity. In recent years, single/few-channel EEG has been used more and more, but various types of physiological artifacts seriously affect the analysis and wide application of single/few-channel EEG. In this paper, the regression and filtering methods, decomposition methods, blind source separation methods and machine learning methods involved in the various physiological artifacts in single/few-channel EEG are reviewed. According to the characteristics of single/few-channel EEG signals, hybrid EEG artifact removal methods for different scenarios are analyzed and summarized, mainly including single-artifact/multi-artifact scenes and online/offline scenes. In addition, the methods and metrics for validating the performance of the algorithm on semi-simulated and real EEG data are also reviewed. Finally, the development trend of single/few-channel EEG application and physiological artifact processing is briefly described.

Methodological artefacts cause counter-intuitive evolutionary conclusions in a simulation study.

In their simulation study, Garcia-Costoya et al. (2023) conclude that evolutionary constraints might aid populations facing climate change. However, we are concerned that this conclusion is largely a consequence of the simulated temperature variation being too small, and, most importantly, that uneven limitations to standing variation disadvantage unconstrained populations.

Evaluation of artifacts produced by conventional dental materials in standard and high-resolution CBCT imaging.

The aim of this study was to identify and quantify artifacts produced by commonly used dental restorative materials in both standard and high-resolution cone beam computed tomographic imaging. In this in vitro study, 25 different dental materials were placed in holes (3 mm in diameter × 2 mm thick) prepared in the center of 10 × 10-mm polymethyl methacrylate plates. The specimens, along with a control plate prepared with an unfilled hole, were scanned at standard and high resolutions. The gray values (GVs) of the specimens were measured at 1-, 2-, 4-, and 8-mm distances from the material surfaces, and in 8 different directions, resulting in 32 measurements per specimen. The absolute value of the difference (ΔGV) between the GV of each measurement point on the specimen disc and the GV of the corresponding point on the control disc was considered to be the number of artifacts at that point. The median ΔGV of each material was calculated, and the materials were then ranked in terms of artifact formation using the Kruskal-Wallis test. At standard resolution, the greatest numbers of artifacts were caused by AH 26 root canal sealer and Heraenium S nickel-chromium alloy, and the fewest were caused by Whitepost DC #3 glass fiber post and ChemFil Superior glass ionomer cement. At high resolution, the greatest numbers of artifacts were found in amalgam (admix; SDI) and Heraenium S, and the fewest in Whitepost DC and GC Initial enamel porcelain. The median ΔGV values at standard and high resolutions were 46.0 and 57.0, respectively. High and standard resolutions were significantly different in terms of artifact formation (P = 0.001; Wilcoxon test). AH 26 sealer was the only material that demonstrated a statistically significant reduction in artifact formation at high resolution compared with standard resolution (P = 0.05; Wilcoxon test). The number of artifacts produced by dental materials at both resolutions decreased with an increasing distance from the surface of the material.

Optimizing EEG ICA decomposition with data cleaning in stationary and mobile experiments.

Electroencephalography (EEG) studies increasingly utilize more mobile experimental protocols, leading to more and stronger artifacts in the recorded data. Independent Component Analysis (ICA) is commonly used to remove these artifacts. It is standard practice to remove artifactual samples before ICA to improve the decomposition, for example using automatic tools such as the sample rejection option of the AMICA algorithm. However, the effects of movement intensity and the strength of automatic sample rejection on ICA decomposition have not been systematically evaluated. We conducted AMICA decompositions on eight open-access datasets with varying degrees of motion intensity using varying sample rejection criteria. We evaluated decomposition quality using mutual information of the components, the proportion of brain, muscle, and 'other' components, residual variance, and an exemplary signal-to-noise ratio. Within individual studies, increased movement significantly decreased decomposition quality, though this effect was not found across different studies. Cleaning strength significantly improved the decomposition, but the effect was smaller than expected. Our results suggest that the AMICA algorithm is robust even with limited data cleaning. Moderate cleaning, such as 5 to 10 iterations of the AMICA sample rejection, is likely to improve the decomposition of most datasets, regardless of motion intensity.

Expanding the clinical application of OPM-MEG using an effective automatic suppression method for the dental brace metal artifact.

Optically pumped magnetometer magnetoencephalography (OPM-MEG) holds significant promise for clinical functional brain imaging due to its superior spatiotemporal resolution. However, effectively suppressing metallic artifacts, particularly from devices such as orthodontic braces and vagal nerve stimulators remains a major challenge, hindering the wider clinical application of wearable OPM-MEG devices. A comprehensive analysis of metal artifact characteristics from time, frequency, and time-frequency perspectives was conducted for the first time using an OPM-MEG device in clinical medicine. This study focused on patients with metal orthodontics, examining the modulation of metal artifacts by breath and head movement, the incomplete regular sub-Gaussian distribution, and the high absolute power ratio in the 0.5-8 Hz band. The existing metal artifact suppression algorithms applied to SQUID-MEG, such as fast independent component analysis (FastICA), information maximization (Infomax), and algorithms for multiple unknown signal extraction (AMUSE), exhibit limited efficacy. Consequently, this study introduced the second-order blind identification (SOBI) algorithm, which utilized multiple time delays for the component separation of OPM-MEG measurement signals. We modified the time delays of the SOBI method to improve its efficacy in separating artifact components, particularly those in the ultralow frequency range. This approach employs the frequency-domain absolute power ratio, root mean square (RMS) value, and mutual information methods to automate the artifact component screening process. The effectiveness of this method was validated through simulation experiments involving four subjects in both resting and evoked experiments. In addition, the proposed method was also validated by the actual OPM-MEG evoked experiments of three subjects. Comparative analyses were conducted against the FastICA, Infomax, and AMUSE algorithms. Evaluation metrics included normalized mean square error, normalized delta band power error, RMS error, and signal-to-noise ratio, demonstrating that the proposed method provides optimal suppression of metal artifacts. This advancement holds promise for enhancing data quality and expanding the clinical applications of OPM-MEG.

[Reconstruction from CT truncated data based on dual-domain transformer coupled feature learning].

OBJECTIVE: To propose a CT truncated data reconstruction model (DDTrans) based on projection and image dualdomain Transformer coupled feature learning for reducing truncation artifacts and image structure distortion caused by insufficient field of view (FOV) in CT scanning. METHODS: Transformer was adopted to build projection domain and image domain restoration models, and the long-range dependency modeling capability of the Transformer attention module was used to capture global structural features to restore the projection data information and enhance the reconstructed images. We constructed a differentiable Radon back-projection operator layer between the projection domain and image domain networks to enable end-to-end training of DDTrans. Projection consistency loss was introduced to constrain the image forwardprojection results to further improve the accuracy of image reconstruction. RESULTS: The experimental results with Mayo simulation data showed that for both partial truncation and interior scanning data, the proposed DDTrans method showed better performance than the comparison algorithms in removing truncation artifacts at the edges and restoring the external information of the FOV. CONCLUSION: The DDTrans method can effectively remove CT truncation artifacts to ensure accurate reconstruction of the data within the FOV and achieve approximate reconstruction of data outside the FOV.

ATN-Res2Unet: an advanced deep learning network for the elimination of saturation artifacts in endoscopy optical coherence tomography.

Endoscopic optical coherence tomography (OCT) possesses the capability to non-invasively image internal lumens; however, it is susceptible to saturation artifacts arising from robust reflective structures. In this study, we introduce an innovative deep learning network, ATN-Res2Unet, designed to mitigate saturation artifacts in endoscopic OCT images. This is achieved through the integration of multi-scale perception, multi-attention mechanisms, and frequency domain filters. To address the challenge of obtaining ground truth in endoscopic OCT, we propose a method for constructing training data pairs. Experimental in vivo data substantiates the effectiveness of ATN-Res2Unet in reducing diverse artifacts while preserving structural information. Comparative analysis with prior studies reveals a notable enhancement, with average quantitative indicators increasing by 45.4-83.8%. Significantly, this study marks the inaugural exploration of leveraging deep learning to eradicate artifacts from endoscopic OCT images, presenting considerable potential for clinical applications.

Test Platform for Developing New Optical Position Tracking Technology towards Improved Head Motion Correction in Magnetic Resonance Imaging.

Optical tracking of head pose via fiducial markers has been proven to enable effective correction of motion artifacts in the brain during magnetic resonance imaging but remains difficult to implement in the clinic due to lengthy calibration and set up times. Advances in deep learning for markerless head pose estimation have yet to be applied to this problem because of the sub-millimetre spatial resolution required for motion correction. In the present work, two optical tracking systems are described for the development and training of a neural network: one marker-based system (a testing platform for measuring ground truth head pose) with high tracking fidelity to act as the training labels, and one markerless deep-learning-based system using images of the markerless head as input to the network. The markerless system has the potential to overcome issues of marker occlusion, insufficient rigid attachment of the marker, lengthy calibration times, and unequal performance across degrees of freedom (DOF), all of which hamper the adoption of marker-based solutions in the clinic. Detail is provided on the development of a custom moiré-enhanced fiducial marker for use as ground truth and on the calibration procedure for both optical tracking systems. Additionally, the development of a synthetic head pose dataset is described for the proof of concept and initial pre-training of a simple convolutional neural network. Results indicate that the ground truth system has been sufficiently calibrated and can track head pose with an error of <1 mm and <1°. Tracking data of a healthy, adult participant are shown. Pre-training results show that the average root-mean-squared error across the 6 DOF is 0.13 and 0.36 (mm or degrees) on a head model included and excluded from the training dataset, respectively. Overall, this work indicates excellent feasibility of the deep-learning-based approach and will enable future work in training and testing on a real dataset in the MRI environment.

Artificial Intelligence-Based Atrial Fibrillation Recognition Method for Motion Artifact-Contaminated Electrocardiogram Signals Preprocessed by Adaptive Filtering Algorithm.

Atrial fibrillation (AF) is a common arrhythmia, and out-of-hospital, wearable, long-term electrocardiogram (ECG) monitoring can help with the early detection of AF. The presence of a motion artifact (MA) in ECG can significantly affect the characteristics of the ECG signal and hinder early detection of AF. Studies have shown that (a) using reference signals with a strong correlation with MAs in adaptive filtering (ADF) can eliminate MAs from the ECG, and (b) artificial intelligence (AI) algorithms can recognize AF when there is no presence of MAs. However, no literature has been reported on whether ADF can improve the accuracy of AI for recognizing AF in the presence of MAs. Therefore, this paper investigates the accuracy of AI recognition for AF when ECGs are artificially introduced with MAs and processed by ADF. In this study, 13 types of MA signals with different signal-to-noise ratios ranging from +8 dB to -16 dB were artificially added to the AF ECG dataset. Firstly, the accuracy of AF recognition using AI was obtained for a signal with MAs. Secondly, after removing the MAs by ADF, the signal was further identified using AI to obtain the accuracy of the AF recognition. We found that after undergoing ADF, the accuracy of AI recognition for AF improved under all MA intensities, with a maximum improvement of 60%.