Image Quality Research Articles

Effect of adaptive statistical iterative reconstruction-V algorithm and deep learning image reconstruction algorithm on image quality and emphysema quantification in COPD patients under ultra-low-dose conditions.

To explore the effect of different reconstruction algorithms (ASIR-V and DLIR) on image quality and emphysema quantification in chronic obstructive pulmonary disease (COPD) patients under ultra-low-dose scanning conditions. This prospective study with patient consent included 62 COPD patients. Patients were examined by pulmonary function test (PFT), standard-dose CT (SDCT) and ultra-low-dose CT (ULDCT). SDCT images were reconstructed with filtered-back-projection (FBP), while ULDCT images were reconstructed using FBP, 30%ASIR-V, 60%ASIR-V, 90%ASIR-V, low-strength (DLIR-L), medium-strength (DLIR-M) and high-strength DLIR (DLIR-H) to form 8 image sets. Images were analyzed using a commercial computer aided diagnosis (CAD) software. Parameters such as image noise, lung volume (LV), emphysema index (EI), mean lung density (MLD), 15th percentile of lung density (PD15) were measured. Two radiologists evaluated tracheal and pulmonary artery image quality using a 5-point scale. Measurements were compared and the correlation between EI and PFT indices was analyzed. ULDCT used 0.46 ± 0.22mSv in radiation dose, 93.8% lower than SDCT (P < 0.001). There was no difference in LV and MLD among image groups (P > 0.05). ULDCT-ASIR-V90% and ULDCT-DLIR-M had similar image noise and EI and PD15 values to SDCT-FBP, and ULDCT-DLIR-M and ULDCT-DLIR-H had similar subjective scores to SDCT-FBP (all P > 0.05). ULDCT-DLIR-M provided the best correlation between EI and the FEV1/FVC and FEV1% indices in PFT, and the lowest deviations with SDCT-FBP in both EI and PD15. DLIR-M provides the best image quality and emphysema quantification for COPD patients in ULDCT. Ultra-low-dose CT scanning combined with DLIR-M reconstruction is comparable to standard dose images for quantitative analysis of emphysema and image quality.

Risk of clinically significant prostate cancer undercategorized by multiparametric magnetic resonance imaging.

To investigative potential clinicopathological characteristics and imaging-related risk factors of clinically significant prostate cancer (csPCa) undercategorized in patients with negative or equivocal MRI. This retrospective study included 581 patients with pathologically confirmed csPCa (Gleason score ≥ 3 + 4), including 108 undercategorized csPCa and 473 detected csPCa. All patients underwent multiparametric MRI (mpMRI). The undercategorized csPCa was defined as a MRI result with PI-RADS ≤ 3. The clinicopathological characteristics and imaging-related factors were compared between the undercategorized group(Group A) (PI-RADS 1-3) and detected group (Group B) (PI-RADS 4-5). The age, total PSA levels, PSAD, free PSA, prostate imaging quality (PI-QUAL) scores, and Gleason scores were significantly lower in the Group A than Group B. The lesions were larger and involved in peripheral and transition zones in the Group B. A significant difference in the second reading opinion. Age (odds ratio [OR], 0.94), PSAD (OR, 0.09), and PI-QUAL scores (OR, 0.25) were significantly associated with the undercategorized csPCa. The rate of undercategorized csPCa with these three risk factors (age, PSAD, and PI-QUAL scores of < 71, < 0.355, and < 3, respectively) was 68.62%. The lack of zoomed-DWI resulted in lower PI-QUAL scores. Finally, the probability of undercategorized csPCa without zoomed DWI was 3.186 times higher than that with zoomed DWI when the PSAD ratio is lower than 0.355. Low image quality, younger age, and lower PSAD contribute to csPCa undercategorized by mpMRI. Moreover, the use of zoomed DWI decreased undercategorized csPCa by improving PI-QUAL scores of MRI images.

Free-Breathing Respiratory Triggered High-Pitch Lung CT: Insights From Phantom and Patient Scans.

Respiratory motion can affect image quality and thus affect the diagnostic accuracy of CT images by masking or mimicking relevant lung pathologies. CT examinations are often performed during deep inspiration and breath-hold to achieve optimal image quality. However, this can be challenging for certain patient groups, such as children, the elderly, or sedated patients. The study aimed to validate a dedicated triggering algorithm for initiating respiratory-triggered high-pitch computed tomography (RT-HPCT) scans in end inspiration and end expiration in complex and irregular respiratory patterns using an anthropomorphic dynamic chest phantom. Additionally, a patient study was conducted to compare the image quality and lung expansion between RT-HPCT and standard HPCT. The study utilized an algorithm that processes the patient's breathing motion in real-time to determine the appropriate time to initiate a scan. This algorithm was tested on a dynamic, tissue-equivalent chest motion phantom to replicate and simulate 3-dimensional target motion using 28 breathing motion patterns taken from patient with irregular breathing. To evaluate the performance on human patients, prospective RT-HPCT was performed in 18 free-breathing patients. As a reference, unenhanced HPCT of the chest was performed in 20 patients without respiratory triggering during free-breathing. The mean CTDI was 1.73 mGy ± 0.1 mGy for HPCT and 1.68 mGy ± 0.1 mGy for RT-HPCT. For phantom tests, the deviation from the target position of the phantom inlay is known. Image quality is approximated by evaluating stationary versus moving acquisitions. For patient scans, respiratory motion artifacts and inspiration depth were analyzed using expert knowledge of lung anatomy and automated lung volume estimation. Statistical analysis was performed to compare image quality and lung volumes between conventional HPCT and RT-HPCT. In phantom scans, the average deviation from the desired excursion phase was 1.6 mm ± 4.7 mm or 15% ± 24% of the phantom movement range. In patients, the overall image quality significantly improved with respiratory triggering compared with conventional HPCT (P < 0.001). Quantitative average lung volume was 4.0 L ± 1.1 L in the RT group and 3.6 L ± 1.0 L in the control group. This study demonstrated the feasibility of using a patient-adaptive respiratory triggering algorithm for high-pitch lung CT in both phantom and patients. Respiratory-triggered high-pitch CT scanning significantly reduces breathing artifacts compared with conventional nontriggered free-breathing scans.

Intra- and interobserver agreement of proposed objective transvaginal ultrasound image-quality scoring system for use in artificial intelligence algorithm development.

The development of valuable artificial intelligence (AI) tools to assist with ultrasound diagnosis depends on algorithms developed using high-quality data. This study aimed to test the intra- and interobserver agreement of a proposed image-quality scoring system to quantify the quality of gynecological transvaginal ultrasound (TVS) images, which could be used in clinical practice and AI tool development. A proposed scoring system to quantify TVS image quality was created following a review of the literature. This system involved a score of 1-4 (2 = poor, 3 = suboptimal and 4 = optimal image quality) assigned by a rater for individual ultrasound images. If the image was deemed inaccurate, it was assigned a score of 1, corresponding to 'reject'. Six professionals, including two radiologists, two sonographers and two sonologists, reviewed 150 images (50 images of the uterus and 100 images of the ovaries) obtained from 50 women, assigning each image a score of 1-4. The review of all images was repeated a second time by each rater after a period of at least 1 week. Mean scores were calculated for each rater. Overall interobserver agreement was assessed using intraclass correlation coefficient (ICC), and interobserver agreement between paired professionals and intraobserver agreement for all professionals were assessed using weighted Cohen's kappa and ICC. Poor levels of interobserver agreement were obtained between the six raters for all 150 images (ICC, 0.480 (95% CI, 0.363-0.586)), as well as for assessment of the uterine images only (ICC, 0.359 (95% CI, 0.204-0.523)). Moderate agreement was achieved for the ovarian images (ICC, 0.531 (95% CI, 0.417-0.636)). Agreement between the paired sonographers and sonologists was poor for all images (ICC, 0.336 (95% CI, -0.078 to 0.619) and 0.425 (95% CI, 0.014-0.665), respectively), as well as when images were grouped into uterine images (ICC, 0.253 (95% CI, -0.097 to 0.577) and 0.299 (95% CI, -0.094 to 0.606), respectively) and ovarian images (ICC, 0.400 (95% CI, -0.043 to 0.669) and 0.469 (95% CI, 0.088-0.689), respectively). Agreement between the paired radiologists was moderate for all images (ICC, 0.600 (95% CI, 0.487-0.693)) and for their assessment of uterine images (ICC, 0.538 (95% CI, 0.311-0.707)) and ovarian images (ICC, 0.621 (95% CI, 0.483-0.728)). Weak-to-moderate intraobserver agreement was seen for each of the raters with weighted Cohen's kappa ranging from 0.533 to 0.718 for all images and from 0.467 to 0.751 for ovarian images. Similarly, for all raters, the ICC indicated moderate-to-good intraobserver agreement for all images overall (ICC ranged from 0.636 to 0.825) and for ovarian images (ICC ranged from 0.596 to 0.862). Slightly better intraobserver agreement was seen for uterine images, with weighted Cohen's kappa ranging from 0.568 to 0.808 indicating weak-to-strong agreement, and ICC ranging from 0.546 to 0.893 indicating moderate-to-good agreement. All measures were statistically significant (P < 0.001). The proposed image quality scoring system was shown to have poor-to-moderate interobserver agreement and mostly weak-to-moderate levels of intraobserver agreement. More refinement of the scoring system may be needed to improve agreement, although it remains unclear whether quantification of image quality can be achieved, given the highly subjective nature of ultrasound interpretation. Although some AI systems can tolerate labeling noise, most will favor clean (high-quality) data. As such, innovative data-labeling strategies are needed. © 2025 The Author(s). Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

Usefulness of four-dimensional noise reduction filtering using a similarity algorithm in low-dose dynamic computed tomography for the evaluation of breast cancer: a preliminary study.

To evaluate the effects of four-dimensional noise reduction filtering using a similarity algorithm (4D-SF) on the image quality and tumor visibility of low-dose dynamic computed tomography (CT) in evaluating breast cancer. Thirty-four patients with 38 lesions who underwent low-dose dynamic breast CT and were pathologically diagnosed with breast cancer were enrolled. Dynamic CT images were reconstructed using iterative reconstruction alone or in combination with 4D-SF. We selected the peak enhancement phase image of breast cancer for each patient for quantitative and qualitative evaluations of image quality and measurement of the maximum diameter of breast cancer. The signal-to-noise and contrast-to-noise ratios were calculated for quantitative evaluation. The maximum diameters of the breast cancer were measured from the images obtained with and without 4D-SF (4D-SF ±) (size-4D-SF + and size-4D-SF-) and for the pathological specimen (size-PS) and compared. The median and interquartile ranges of the signal-to-noise ratio [4D-SF-: 3.03 (2.54-4.17) vs 4D-SF + : 5.52 (4.75-6.66)] and contrast-to-noise ratio [4D-SF-: 2.88 (2.00-3.60) vs 4D-SF + : 7.84 (4.65-10.35)] were significantly higher for 4D-SF + than for 4D-SF- (p < 0.001). The overall image quality (Observer 1, p < 0.001; Observer 2, p < 0.001) and tumor margin sharpness scores (Observer 1, p = 0.003; Observer 2, p < 0.001) were significantly higher for 4D-SF + than for 4D-SF-. The tumor contrast scores for 4D-SF + and 4D-SF- were not significantly different (Observers 1, 2; p = 0.083). Size-4D-SF- was significantly smaller than size-PS (p < 0.001); size-4D-SF + was also smaller than size-PS, but the difference was not significant (p = 0.088). The Spearman's rank correlation coefficient was 0.65 for size-PS and size-4D-SF- and 0.77 for size-PS and size-4D-SF + . The 4D-SF can improve the image quality and tumor visibility of low-dose dynamic CT in evaluating breast cancer extent due to noise reduction.

Quantitative and Visual Benefits of Data-Driven Motion Correction on Oncologic PET/CT: AProspective Cross-sectional Study.

Conventional positron emission tomography (PET) respiratory gating utilizes a fraction of acquired PET counts (i.e., optimal gate [OG]), whereas elastic motion correction with deblurring (EMCD) utilizes all PET counts to reconstruct motion-corrected images without increasing image noise. Our aim was to assess the quantitative and visual impacts of EMCD-based motion correction on FDG-PET and DOTATATE-PET images relative to OG and ungated (UG) images. This prospective, single-center study enrolled adults undergoing FDG or DOTATATE oncologic PET/CT between June 2020 and October 2022. Subjects underwent a standard-of-care (SOC) PET acquisition while wearing a respiratory gating belt. UG, belt-gating-derived optimal gate (BG-OG), EMCD utilizing belt gating (BG-EMCD), and EMCD utilizing data-driven gating (DDG-EMCD) images were reconstructed. Tracer-avid lesions in the lower chest or upper abdomen were segmented. Quantitative metrics were extracted. Two independent, blinded readers assessed image quality via a 4-point scale and counted lesions on each reconstruction. Differences between reconstructions were assessed via the Wilcoxon signed-rank test (alpha, 0.05). This study enrolled 78 subjects; 36 subjects (mean age, 64.8 years; 20 males) with 136 tracer-avid lesions were analyzed. Data provided are medians across all tracers. Lesion SUV-max was significantly higher (P<0.001) on motion-corrected images (BG-OG: 10.77, BG-EMCD: 10.75, DDG-EMCD: 10.74) than UG images (9.00). Lesion contrast-to-noise ratios (CNRs) were significantly lower (P<0.001) for BG-OG (6.31) and UG images (7.89) than BG-EMCD (9.14) and DDG-EMCD (8.89) images. FDG and DOTATATE subgroup analyses produced similar results. Among motion-corrected images, both readers preferred EMCD-based images to BG-OG images for all tracers (P<0.001) and both subgroups. EMCD-based images occasionally demonstrated more tracer-avid lesions than BG-OG or UG images. EMCD-based motion correction beneficially impacts lesion quantitation (including higher SUVs and CNRs) and overall image quality. When employed on capable scanners, EMCD can improve the quality of oncologic PET imaging.

Gadopiclenol Enables Reduced Gadolinium Dose While Maintaining Quality of Pulmonary Arterial Enhancement for Pulmonary MRA: An Opportunity for Improved Safety and Sustainability.

Pulmonary magnetic resonance angiography (MRA) is an imaging method with proven utility for the exclusion of pulmonary embolism and avoids the need for ionizing radiation and iodinated contrast agents. High-relaxivity gadolinium-based contrast agents (GBCAs), such as gadopiclenol, can be used to reduce the required gadolinium dose for pulmonary MRA. The aim of this study was to compare the contrast enhancement performance of gadopiclenol with an established gadobenate dimeglumine-enhanced pulmonary MRA protocol. In this retrospective single-center study, data from 152 patients who underwent pulmonary MRA at 1.5 T were analyzed. Imaging was performed with either 0.05 mmol/kg gadopiclenol (n = 75) or 0.1 mmol/kg gadobenate dimeglumine (n = 77), using dedicated multiphasic imaging protocols with precontrast, pulmonary arterial phase, immediate delayed phase, and a low flip-angle T1-weighted spoiled gradient echo acquisition. Subjective image quality evaluation was performed blinded by 2 radiologists on a 5-point Likert scale. For the estimation of interrater reliability, Cohen weighted κ was calculated. For semiquantitative assessment, signal intensities were measured in the pulmonary arteries, and relative signal enhancement was calculated. Data from groups were compared with Mann-Whitney U tests using Bonferroni corrections. Signal enhancement relative to precontrast in the first-pass pulmonary arterial phase was higher with 0.05 mmol/kg gadopiclenol compared with 0.1 mmol/kg gadobenate dimeglumine (20.0-fold ± 5.6-fold vs 17.8-fold ± 5.8-fold; P = 0.015). Readers observed no difference in subjective rating in terms of intravascular contrast, peripheral vessel depiction, and diagnostic confidence with substantial interrater reliability (Cohen κ = 0.73 [95% confidence interval: 0.57-0.89], 0.65 [0.55-0.75], and 0.74 [0.65-0.84], all P's < 0.001). No severe adverse events were recorded for any clinical MRA examination. The high-relaxivity contrast agent gadopiclenol can facilitate a reduction in gadolinium dose by 50% without compromising contrast enhancement for pulmonary MRA. This approach may enhance the safety and sustainability of pulmonary MRA in the long term.

Deep Learning-Based Multi-View Projection Synthesis Approach for Improving the Quality of Sparse-View CBCT in Image-Guided Radiotherapy.

While radiation hazards induced by cone-beam computed tomography (CBCT) in image-guided radiotherapy (IGRT) can be reduced by sparse-view sampling, the image quality is inevitably degraded. We propose a deep learning-based multi-view projection synthesis (DLMPS) approach to improve the quality of sparse-view low-dose CBCT images. In the proposed DLMPS approach, linear interpolation was first applied to sparse-view projections and the projections were rearranged into sinograms; these sinograms were processed with a sinogram restoration model and then rearranged back into projections. The sinogram restoration model was modified from the 2D U-Net by incorporating dynamic convolutional layers and residual learning techniques. The DLMPS approach was trained, validated, and tested on CBCT data from 163, 30, and 30 real patients respectively. Sparse-view projection datasets with 1/4 and 1/8 of the original sampling rate were simulated, and the corresponding full-view projection datasets were restored via the DLMPS approach. Tomographic images were reconstructed using the Feldkamp-Davis-Kress algorithm. Quantitative metrics including root-mean-square error (RMSE), peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and feature similarity (FSIM) were calculated in both the projection and image domains to evaluate the performance of the DLMPS approach. The DLMPS approach was compared with 11 state-of-the-art (SOTA) models, including CNN and Transformer architectures. For 1/4 sparse-view reconstruction task, the proposed DLMPS approach achieved averaged RMSE, PSNR, SSIM, and FSIM values of 0.0271, 45.93 dB, 0.9817, and 0.9587 in the projection domain, and 0.000885, 37.63 dB, 0.9074, and 0.9885 in the image domain, respectively. For 1/8 sparse-view reconstruction task, the DLMPS approach achieved averaged RMSE, PSNR, SSIM, and FSIM values of 0.0304, 44.85 dB, 0.9785, and 0.9524 in the projection domain, and 0.001057, 36.05 dB, 0.8786, and 0.9774 in the image domain, respectively. The DLMPS approach outperformed all the 11 SOTA models in both the projection and image domains for 1/4 and 1/8 sparse-view reconstruction tasks. The proposed DLMPS approach effectively improves the quality of sparse-view CBCT images in IGRT by accurately synthesizing missing projections, exhibiting potential in substantially reducing imaging dose to patients with minimal loss of image quality.

Non-parametric Bayesian deep learning approach for whole-body low-dose PET reconstruction and uncertainty assessment.

Positron emission tomography (PET) imaging plays a pivotal role in oncology for the early detection of metastatic tumors and response to therapy assessment due to its high sensitivity compared to anatomical imaging modalities. The balance between image quality and radiation exposure is critical, as reducing the administered dose results in a lower signal-to-noise ratio (SNR) and information loss, which may significantly affect clinical diagnosis. Deep learning (DL) algorithms have recently made significant progress in low-dose (LD) PET reconstruction. Nevertheless, a successful clinical application requires a thorough evaluation of uncertainty to ensure informed clinical judgment. We propose NPB-LDPET, a DL-based non-parametric Bayesian framework for LD PET reconstruction and uncertainty assessment. Our framework utilizes an Adam optimizer with stochastic gradient Langevin dynamics (SGLD) to sample from the underlying posterior distribution. We employed the Ultra-low-dose PET Challenge dataset to assess our framework's performance relative to the Monte Carlo dropout benchmark. We evaluated global reconstruction accuracy utilizing SSIM, PSNR, and NRMSE, local lesion conspicuity using mean absolute error (MAE) and local contrast, and the clinical relevance of uncertainty maps employing correlation between the uncertainty measures and the dose reduction factor (DRF). Our NPB-LDPET reconstruction method exhibits a significantly superior global reconstruction accuracy for various DRFs (paired t-test, , N=10,631). Moreover, we demonstrate a 21% reduction in MAE (573.54 vs. 723.70, paired t-test, , N=28) and an 8.3% improvement in local lesion contrast (2.077 vs. 1.916, paired t-test, , N=28). Furthermore, our framework exhibits a stronger correlation between the predicted uncertainty 95th percentile score and the DRF ( vs. , N=10,631). The proposed framework has the potential to improve clinical decision-making for LD PET imaging by providing a more accurate and informative reconstruction while reducing radiation exposure.

Patial-frequency aware zero-centric residual unfolding network for MRI reconstruction.

Magnetic Resonance Imaging is a cornerstone of medical diagnostics, providing high-quality soft tissue contrast through non-invasive methods. However, MRI technology faces critical limitations in imaging speed and resolution. Prolonged scan times not only increase patient discomfort but also contribute to motion artifacts, further compromising image quality. Compressed Sensing (CS) theory has enabled the acquisition of partial k-space data, which can then be effectively reconstructed to recover the original image using advanced reconstruction algorithms. Recently, deep learning has been widely applied to MRI reconstruction, aiming to reduce the artifacts in the image domain caused by undersampling in k-space and enhance image quality. As deep learning continues to evolve, the undersampling factors in k-space have gradually increased in recent years. However, these layers are limited in compensating for reconstruction errors in the unsampled areas, impeding further performance improvements. To address this, we propose a learnable spatial-frequency difference-aware module that complements the learnable data consistency layer, mapping k-space domain differences to the spatial image domain for perceptual compensation. Additionally, inspired by wavelet decomposition, we introduce explicit priors by decomposing images into mean and residual components, enforcing a refined zero-mean constraint on the residuals while maintaining computational efficiency. Comparative experiments on the FastMRI and Calgary-Campinas datasets demonstrate that our method achieves superior reconstruction performance against seven state-of-the-art techniques. Ablation studies further confirm the efficacy of our model's architecture, establishing a new pathway for enhanced MRI reconstruction.

Rapid prospective motion correction using free induction decay and stationary field probe navigators at 7T.

MR-based FID navigators (FIDnavs) do not require gradient pulses and are attractive for prospective motion correction (PMC) due to short acquisition times and high sampling rates. However, accuracy and precision are limited and depend on a separate calibration measurement. Besides FIDnavs, stationary NMR field probes are also capable of measuring local, motion-induced field changes. In this work, a linear model is calibrated between field probe data and motion parameters analog to FIDnav calibration and both tracking methods are compared and combined for PMC. FIDnavs and field probe navigators were implemented in a fast 3D-EPI sequence and calibrated by a linear model to realignment motion parameters of the 3D-EPI time series. A workflow was established to correct head motion prospectively by FIDnavs, field probe navigators or a combination of both. Large motions were instructed to test the accuracy and the impact on image quality in EPI data. In a group of five subjects, FIDnavs demonstrated approximately doubled accuracy and precision in comparison with field probe navigators for large motions, especially nodding motions were tracked less accurately by field probes. A combination of both methods could not improve the accuracy consistently. Motion artifacts in high-resolution data were reduced similarly by both PMC methods, although artifacts remained due to susceptibility-induced B0 changes. Stationary field probe navigators can be calibrated equivalently as FIDnavs and enable rapid PMC of large and fast motions. Although they reveal decreased accuracy, their contrast-independence facilitates the potential insertion into many sequences.

Effects of data-driven respiratory gating on visualization and quantification of breast and upper abdominal cancers in FDG PET/CT examinations.

Data-driven respiratory gating (DDG) has recently been introduced to improve image quality in the PET portion of PET/CT examinations. The latest DDG system does not require any external equipment or extended examination time. In this study, we investigated the effects of the new DDG system on the visualization and quantification of breast and upper abdominal cancers, comparing the results with those obtained using the standard free-breathing (STD) PET protocol. A total of 223 cancer lesions (138 breast and 85 upper abdominal) evaluated with FDG PET/CT were included in this study. PET images were reconstructed using the STD and DDG algorithms. Lesion blurring and conspicuity were each visually graded on a three-point scale. The longest diameter (LD), SUVmax, and metabolic tumor volume (MTV) of the lesions were used for quantitative analysis. % change in SUVmax or MTV was calculated from the metrics in STD and DDG images. Fifty-six texture features (TFs) were also evaluated. Visual scores and quantitative metrics were compared between STD and DDG images. % change in SUVmax or MTV was compared in the lesion location groups or in the high and low groups based on LD, SUVmax, or MTV in STD images. Visual scores for lesion blurring and conspicuity were both significantly higher in DDG than in STD PET images. SUVmax and MTV were significantly higher and lower, respectively, in DDG than in STD images. An increase in SUVmax and a decrease in MTV were observed in 96% and 86% of all lesions, respectively. Group analysis revealed that % change in SUVmax was greater in the upper abdominal than the breast lesions and % change in MTV was greater in the high LD and high MTV groups than in the lowLD and lowMTV groups, respectively. Quantitative changes in TFs were observed between STD and DDG images for most of the features. This study demonstrated that DDG improved visualization and quantification of breast and upper abdominal cancers in FDG PET/CT examinations. DDG PET images exhibited an increase in SUVmax, a decrease in MTV, and changes in TFs.

Polarimetric Compressed Sensing with Hollow, Self-Assembled Diffractive Films.

Sensing light's polarization and wavefront direction enables surface curvature assessment, material identification, shadow differentiation, and improved image quality in turbid environments. Traditional polarization cameras utilize multiple sensor measurements per pixel and polarization-filtering optics, which result in reduced image resolution. We propose a nanophotonic pipeline that enables compressive sensing and reduces the sampling requirements with a low-refractive-index, self-assembled optical encoder. These nanostructures scatter light into lattice modes, which encode the wavefront direction and the polarization ellipticity in the linearly polarized components of the diffracted, interference patterns. Combining optical encoders with a neural network, the system predicts pointing and polarization when the interference patterns are adequately sampled. A comparison of "ordered" and "random" optical encoders shows that the latter both blurs the interference patterns and achieves higher resolution. Our work centers on the unexpected modulation and spatial multiplexing of incident light polarization by self-assembled hollow nanocavity arrays as a class of materials distinct from traditional metasurfaces that will not only enable encoding for polarization and optical computing but also for compressed sensing and imaging.

Automatic visual detection of activated sludge microorganisms based on microscopic phase contrast image optimisation and deep learning.

The types and quantities of microorganisms in activated sludge are directly related to the stability and efficiency of sewage treatment systems. This paper proposes a sludge microorganism detection method based on microscopic phase contrast image optimisation and deep learning. Firstly, a dataset containing eight types of microorganisms is constructed, and an augmentation strategy based on single and multisamples processing is designed to address the issues of sample deficiency and uneven distribution. Secondly, a phase contrast image quality optimisation algorithm based on fused variance is proposed, which can effectively improve the standard deviation, entropy, and detection performance. Thirdly, a lightweight YOLOv8n-SimAM model is designed, which introduces a SimAM attention module to suppress the complex background interference and enhance attentions to the target objects. The lightweight of the network is realised using a detection head based on multiscale information fusion convolutional module. In addition, a new loss function IW-IoU is proposed to improve the generalisation ability and overall performance. Comparative and ablative experiments are conducted, demonstrating the great application potential for rapid and accurate detection of microbial targets. Compared to the baseline model, the proposed method improves the detection accuracy by 12.35% and hastens the running speed by 37.9 frames per second while evidently reducing the model size.

Clinical Evaluation of 3D Motion-Correction Via Scout Accelerated Motion Estimation and Reduction Framework Versus Conventional T1-Weighted MRI at 1.5 T in Brain Imaging.

The aim of this study was to investigate the occurrence of motion artifacts and image quality of brain magnetic resonance imaging (MRI) T1-weighted imaging applying 3D motion correction via the Scout Accelerated Motion Estimation and Reduction (SAMER) framework compared with conventional T1-weighted imaging at 1.5 T. A preliminary study involving 14 healthy volunteers assessed the impact of the SAMER framework on induced motion during 3 T MRI scans. Participants performed 3 different motion patterns: (1) step up, (2) controlled breathing, and (3) free motion. The patient study included 82 patients who required clinically indicated MRI scans. 3D T1-weighted images (MPRAGE) were acquired at 1.5 T. The MRI data were reconstructed using either regular product reconstruction (non-Moco) or the 3D motion correction SAMER framework (SAMER Moco), resulting in 145 image sequences. For the preliminary and the patient study, 3 experienced radiologists evaluated the image data using a 5-point Likert scale, focusing on overall image quality, artifact presence, diagnostic confidence, delineation of pathology, and image sharpness. Interrater agreement was assessed using Gwet's AC2, and an exploratory analysis (non-Moco vs SAMER Moco) was performed. Compared with non-Moco, the preliminary study demonstrated significant improvements across all imaging parameters and motion patterns with SAMER Moco (P < 0.001). Odds ratios favoring SAMER Moco were >999.999 for freedom of artifact and overall image quality (P < 0.0001). Excellent or good ratings for freedom of artifact were 52.4% with SAMER Moco, compared with 21.4% for non-Moco. Similarly, 66.7% of SAMER Moco images were rated excellent or good for overall image quality versus 21.4% for non-Moco. Multireader interrater agreement was excellent across all parameters.The patient study confirmed that SAMER Moco provided significantly superior image quality across all evaluated imaging parameters, particularly in the presence of motion (P < 0.001). Diagnostic confidence was rated as excellent or good in 95.1% of SAMER Moco cases, compared with 78.1% for non-Moco cases. Similarly, overall image quality was rated as excellent or good in 89.8% of SAMER Moco cases versus 65.9% for non-Moco cases. The odds ratios for diagnostic confidence and for overall image quality were 6.698 and 6.030, respectively, both favoring SAMER Moco (P < 0.0001). Multireader interrater agreement was excellent across all parameters. The application of SAMER in T1-weighted imaging datasets is feasible in clinical routine and significantly increases image quality and diagnostic confidence in 1.5 T brain MRI by effectively reducing motion artifacts.

Deep learning-based synthetic CT for dosimetric monitoring of combined conventional radiotherapy and lattice boost in large lung tumors

PurposeConventional radiotherapy (CRT) has limited local control and poses a high risk of severe toxicity in large lung tumors. This study aimed to develop an integrated treatment plan that combines CRT with lattice boost radiotherapy (LRT) and monitors its dosimetric characteristics.MethodsThis study employed cone-beam computed tomography from 115 lung cancer patients to develop a U-Net + + deep learning model for generating synthetic CT (sCT). The clinical feasibility of sCT was thoroughly evaluated in terms of image clarity, Hounsfield Unit (HU) consistency, and computational accuracy. For large lung tumors, accumulated doses to the gross tumor volume (GTV) and organs at risk (OARs) during 20 fractions of CRT were precisely monitored using matrices derived from the deformable registration of sCT and planning CT (pCT). Additionally, for patients with minimal tumor shrinkage during CRT, an sCT-based adaptive LRT boost plan was introduced, with its dosimetric properties, treatment safety in high dose regions, and delivery accuracy quantitatively assessed.ResultsThe image quality and HU consistency of sCT improved significantly, with dose deviations ranging from 0.15% to 1.25%. These results indicated that sCT is feasible for inter-fraction dose monitoring and adaptive planning. After rigid and hybrid deformable registration of sCT and pCT, the mean distance-to-agreement was 0.80 ± 0.18 mm, and the mean Dice similarity coefficient was 0.97 ± 0.01. Monitoring dose accumulation over 20 CRT fractions showed an increase in high-dose regions of the GTV (P < 0.05) and a reduction in low-dose regions (P < 0.05). Dosimetric parameters of all OARs were significantly higher than those in the original treatment plan (P < 0.01). The sCT based adaptive LRT boost plan, when combined with CRT, significantly reduced the dose to OARs compared to CRT alone (P < 0.05). In LRT plan, high-dose regions for the GTV and D95% exhibited displacements greater than 5 mm from the tumor boundary in 19 randomly scanned sCT sequences under free breathing conditions. Validation of dose delivery using TLD phantom measurements showed that more than half of the dose points in the sCT based LRT plan had deviations below 2%, with a maximum deviation of 5.89%.ConclusionsThe sCT generated by the U-Net + + model enhanced the accuracy of monitoring the actual accumulated dose, thereby facilitating the evaluation of therapeutic efficacy and toxicity. Additionally, the sCT-based LRT boost plan, combined with CRT, further minimized the dose delivered to OARs while ensuring safe and precise treatment delivery.

A generative adversarial network with multiscale and attention mechanisms for underwater image enhancement

Underwater images collected are often of low clarity and suffer from severe color distortion due to the marine environment and Illumination conditions. This directly impacts tasks such as marine ecological monitoring and underwater target detection, which rely on image processing. Therefore, enhancing Underwater images to improve their quality is necessary. A generative adversarial network with an encoder-decoder structure is proposed to improve the quality of Underwater images. The network consists of a generative network and an adversarial network. The generative network is responsible for enhancing the images, while the adversarial network determines whether the input is an enhanced image or a real high-quality image. In the generative network, we first design a residual convolution module to extract more texture and edge information from underwater images. Next, we design a multi-scale dilated convolution module to capture underwater features at different scales. Then, we design a feature fusion adaptive attention module to reduce the interference of redundant features and enhance the local perception capabilities. Finally, we construct the generative network using these modules along with conventional modules. In the adversarial network, we first design a multi-scale feature extraction module to improve the feature extraction ability. We then use the multi-scale feature extraction module along with conventional convolution modules to design the adversarial network. Additionally, we propose an improved loss function by introducing color loss into the conventional loss function. The improved loss function can better measure the color discrepancy between the enhanced image and the real image. It is useful to reduce color distortion in the enhanced images. In experimental simulations, the images enhanced by the proposed methods have the highest PSNR, SSIM, and UIQM values, indicating that the proposed method has superior Underwater image enhancement capabilities compared to other methods.

CDCG-UNet: Chaotic Optimization Assisted Brain Tumor Segmentation Based on Dilated Channel Gate Attention U-Net Model.

Brain tumours are one of the most deadly and noticeable types of cancer, affecting both children and adults. One of the major drawbacks in brain tumour identification is the late diagnosis and high cost of brain tumour-detecting devices. Most existing approaches use ML algorithms to address problems, but they have drawbacks such as low accuracy, high loss, and high computing cost. To address these challenges, a novel U-Net model for tumour segmentation in magnetic resonance images(MRI) is proposed. Initially, images are claimed from the dataset and pre-processed with the Probabilistic Hybrid Wiener filter (PHWF) to remove unwanted noise and improve image quality. To reduce model complexity, the pre-processed images are submitted to a feature extraction procedure known as 3D Convolutional Vision Transformer (3D-VT). To perform the segmentation approach usingchaotic optimization assisted Dilated Channel Gate attention U-Net (CDCG-UNet)model to segment brain tumour regions effectively. The proposed approach segments tumour portions as whole tumour (WT), tumour Core (TC), and Enhancing Tumour (ET) positions. The optimization loss function can be performed using the Chaotic Harris Shrinking Spiral optimization algorithm (CHSOA). The proposed CDCG-UNet model is evaluated with three datasets: BRATS 2021, BRATS 2020, and BRATS 2023. For the BRATS 2021 dataset, the proposed CDCG-UNet model obtained a dice score of 0.972 for ET, 0.987 for CT, and 0.98 for WT. For the BRATS 2020 dataset, the proposed CDCG-UNet model produced a dice score of 98.87% for ET, 98.67% for CT, and 99.1% for WT. The CDCG-UNet model is further evaluated using the BRATS 2023 dataset, which yields 98.42% for ET, 98.08% for CT, and 99.3% for WT.

Noise reduction of low-dose electron holograms using the wavelet hidden Markov model.

The precision in electron holography studies on electrostatic and magnetic fields depends on the image quality of an electron hologram. Enhancing the image quality of electron holograms is essential for the comprehensive analysis of weak electromagnetic fields; however, extended electron beam irradiation can lead to undesirable radiation damage and contamination. Recent studies have demonstrated that noise reduction using the wavelet hidden Markov model (WHMM) can improve the precision of phase analysis for limited thin-foiled crystals. In this study, we examine the effects of WHMM-based denoising on the electron holography data of weakly charged nanoparticles collected under low-electron-dose conditions. The results indicate that effective noise reduction with the WHMM allows for a reduction in the magnitude of the electron dose by approximately half relative to data collection without WHMM denoising, while maintaining the same level of the charge determination precision: less than one elementary charge. Notably, at a low electron dose of 0.40 e-/pixel, WHMM denoising enables the clear visualization of a weak stray electric field outside a charged latex sphere. This method offers significant advantages for electron holography studies of electron-beam-sensitive materials requiring minimal time for electron exposure.

Syn2Real: synthesis of CT image ring artifacts for deep learning-based correction.

Objective.We strive to overcome the challenges posed by ring artifacts in X-ray computed tomography (CT) by developing a novel approach for generating training data for deep learning-based methods. Training such networks require large, high quality, datasets that are often generated in the data domain, time-consuming and expensive. Our objective is to develop a technique for synthesizing realistic ring artifacts directly in the image domain, enabling scalable production of training data without relying on specific imaging system physics.&#xD;Approach.We develop ''Syn2Real,'' a computationally efficient pipeline that generates realistic ring artifacts directly in the image domain. To demonstrate the effectiveness of our approach, we train two versions of UNet, vanilla and a high capacity version with self-attention layers that we call UNetpp, with ℓ2and perceptual losses, as well as a diffusion model, on energy-integrating CT images with and without these synthetic ring artifacts. &#xD;Main Results.Despite being trained on conventional single-energy CT images, our models effectively correct ring artifacts across various monoenergetic images, at different energy levels and slice thicknesses, from a prototype photon-counting CT system. This generalizability validates the realism and versatility of our ring artifact generation process.&#xD;Significance.Ring artifacts in X-ray CT pose a unique challenge to image quality and clinical utility. By focusing on data generation, our work provides a foundation for developing more robust and adaptable ring artifact correction methods for pre-clinical, clinical and other CT applications.