[Muscle injuries: the importance of high-resolution dynamic sonography in diagnostics, treatment and monitoring]. / Muskelverletzungen: Stellenwert der hochauflösenden dynamischen Sonographie in der Diagnostik, Therapie und im Monitoring.

BACKGROUND: Muscle injuries are common in football. Imaging diagnostics have a major role in establishing a diagnosis. The main diagnostic procedures are MRI and ultrasound. Both diagnostics have advantages and disadvantages, which should be balanced against each other. NEW ULTRASONIC TECHNIQUES: The role of MRI as the gold standard is increasingly being replaced by high-resolution ultrasound techniques, and MRI imaging is not always useful. To detect complications in the early stages it is advised to perform regular ultrasound-imaging check-ups. The healing process can be monitored, and it offers additional options for ultrasound-guided interventions such as hematoma punctures and targeted infiltrations. ADVANTAGES AND DISADVANTAGES: However, ultrasound imaging is highly user dependent. Experienced operators can eliminate this disadvantage, which makes ultrasound a superior imaging system in many areas, especially for dynamic examinations. Nevertheless, MRI imaging remains a necessary imaging method in certain areas.

Based on Gadolinium Ethoxybenzyl DTPA-Enhanced MRI: Diagnostic Performance of the Category-Modified LR-5 Criteria in Patients At Risk for Hepatocellular Carcinoma.

Introduction: We aimed to modify the LR-5 strategy to improve the diagnostic sensitivity for hepatocellular carcinoma (HCC) in high-risk patients while maintaining specificity. Methods: This study retrospectively analyzed 412 patients with 445 liver observations who underwent preoperative gadolinium ethoxybenzyl DTPA (GD-EOB-DTPA)-enhanced MRI followed by surgical procedures or biopsies. All observations were classified according to LI-RADS v2018, and the classifications were adjusted by modifying major features (MF)(substituting threshold growth with a more HCC-specific ancillary features (AF): presence of blood products within the mass, arterial phase hyperenhancement (APHE) was interpreted with hypointensity on precontrast imaging- isointensity in arterial phase (AP) and extending washout to transitional phase (TP)(2 min)). The specificity, sensitivity, and positive predictive value (PPV) were assessed to compare LR-5 (definitely HCC) diagnostic efficacy between LI-RADS version 2018 and modified LI-RADS. Results: Apart from nonenhancing "capsule", the interreader agreement of MFs and HCC-specific AFs between the two readers reached substantial or excellent ranges (κ values ranging from 0.631 to 0.911). According to LI-5 v2018, the specificity, sensitivity and PPV of HCC were 90.74%, 82.35%, and 98.17%, respectively. Based on a more HCC-specific AF, signal intensity in AP and TP (2 min), the sensitivity of the three modified strategies were 86.19%, 93.09%, 96.67% (P < .05)), while maintaining high specificity and PPV rates at 88.89% and 98.25% (P > .05) Conclusion: Further investigation into the efficacy of threshold growth as a MF is warranted. By utilizing GD-EOB-DTPA-enhanced MRI, enhancing the sensitivity of the modified LR-5 category may be achieved without compromising specificity and PPV in diagnosing HCC among high-risk patients.

Self-supervised anatomical continuity enhancement network for 7T SWI synthesis from 3T SWI.

Synthesizing 7T Susceptibility Weighted Imaging (SWI) from 3T SWI could offer significant clinical benefits by combining the high sensitivity of 7T SWI for neurological disorders with the widespread availability of 3T SWI in diagnostic routines. Although methods exist for synthesizing 7T Magnetic Resonance Imaging (MRI), they primarily focus on traditional MRI modalities like T1-weighted imaging, rather than SWI. SWI poses unique challenges, including limited data availability and the invisibility of certain tissues in individual 3T SWI slices. To address these challenges, we propose a Self-supervised Anatomical Continuity Enhancement (SACE) network to synthesize 7T SWI from 3T SWI using plentiful 3T SWI data and limited 3T-7T paired data. The SACE employs two specifically designed pretext tasks to utilize low-level representations from abundant 3T SWI data for assisting 7T SWI synthesis in a downstream task with limited paired data. One pretext task emphasizes input-specific morphology by balancing the elimination of redundant patterns with the preservation of essential morphology, preventing the blurring of synthetic 7T SWI images. The other task improves the synthesis of tissues that are invisible in a single 3T SWI slice by aligning adjacent slices with the current slice and predicting their difference fields. The downstream task innovatively combines clinical knowledge with brain substructure diagrams to selectively enhance clinically relevant features. When evaluated on a dataset comprising 97 cases (5495 slices), the proposed method achieved a Peak Signal-to-Noise Ratio (PSNR) of 23.05 dB and a Structural Similarity Index (SSIM) of 0.688. Due to the absence of specific methods for 7T SWI, our method was compared with existing enhancement techniques for general 7T MRI synthesis, outperforming these techniques in the context of 7T SWI synthesis. Clinical evaluations have shown that our synthetic 7T SWI is clinically effective, demonstrating its potential as a clinical tool.

Low illumination fog noise image denoising method based on ACE-GPM.

The Perona-Malik (P-M) model exhibits deficiencies such as noise amplification, new noise introduction, and significant gradient effects when processing noisy images. To address these issues, this paper proposes an image-denoising algorithm, ACE-GPM, which integrates an Automatic Color Equalization (ACE) algorithm with a gradient-adjusted P-M model. Initially, the ACE algorithm is employed to enhance the contrast of low-light images obscured by fog and noise. Subsequently, the Otsu method, a technique to find the optimal threshold based on between-class variance, is applied for precise segmentation, enabling more accurate identification of different regions within the image. After that, distinct gradients enhance the image's foreground and background via an enhancement function that accentuates edge and detailed information. The denoising process is finalized by applying the gradient P-M model, employing a gradient descent approach to further emphasize image edges and details. Experimental evidence indicates that the proposed ACE-GPM algorithm not only elevates image contrast and eliminates noise more effectively than other denoising methods but also preserves image details and texture information, evidenced by an average increase of 0.42 in the information entropy value. Moreover, the proposed solution achieves these outcomes with reduced computational resource expenditures while maintaining high image quality.

Contrast-enhanced Mammography versus MR Imaging of the Breast.

Breast MR imaging and contrast-enhanced mammography (CEM) are both techniques that employ intravenously injected contrast agent to assess breast lesions. This approach is associated with a very high sensitivity for malignant lesions that typically exhibit rapid enhancement due to the leakiness of neovasculature. CEM may be readily available at the breast imaging department and can be performed on the spot. Breast MR imaging provides stronger enhancement than the x-ray-based techniques and offers higher sensitivity. From a patient perspective, both modalities have their benefits and downsides; thus, patient preference could also play a role in the selection of the imaging technique.

Background Parenchymal Enhancement: A Comprehensive Update.

Breast MR imaging is a complementary screening tool for patients at high risk for breast cancer and has been used in the diagnostic setting. Normal enhancement of breast tissue on MR imaging is called breast parenchymal enhancement (BPE), which occurs after administration of an intravenous contrast agent. BPE varies widely due to menopausal status, use of exogenous hormones, and breast cancer treatment. Degree of BPE has also been shown to influence breast cancer risk and may predict treatment outcomes. The authors provide a comprehensive update on BPE with review of the recent literature.

Optimizing Image Enhancement: Feature Engineering for Improved Classification in AI-Assisted Artificial Retinas.

Artificial retinas have revolutionized the lives of many blind people by enabling their ability to perceive vision via an implanted chip. Despite significant advancements, there are some limitations that cannot be ignored. Presenting all objects captured in a scene makes their identification difficult. Addressing this limitation is necessary because the artificial retina can utilize a very limited number of pixels to represent vision information. This problem in a multi-object scenario can be mitigated by enhancing images such that only the major objects are considered to be shown in vision. Although simple techniques like edge detection are used, they fall short in representing identifiable objects in complex scenarios, suggesting the idea of integrating primary object edges. To support this idea, the proposed classification model aims at identifying the primary objects based on a suggested set of selective features. The proposed classification model can then be equipped into the artificial retina system for filtering multiple primary objects to enhance vision. The suitability of handling multi-objects enables the system to cope with real-world complex scenarios. The proposed classification model is based on a multi-label deep neural network, specifically designed to leverage from the selective feature set. Initially, the enhanced images proposed in this research are compared with the ones that utilize an edge detection technique for single, dual, and multi-object images. These enhancements are also verified through an intensity profile analysis. Subsequently, the proposed classification model's performance is evaluated to show the significance of utilizing the suggested features. This includes evaluating the model's ability to correctly classify the top five, four, three, two, and one object(s), with respective accuracies of up to 84.8%, 85.2%, 86.8%, 91.8%, and 96.4%. Several comparisons such as training/validation loss and accuracies, precision, recall, specificity, and area under a curve indicate reliable results. Based on the overall evaluation of this study, it is concluded that using the suggested set of selective features not only improves the classification model's performance, but aligns with the specific problem to address the challenge of correctly identifying objects in multi-object scenarios. Therefore, the proposed classification model designed on the basis of selective features is considered to be a very useful tool in supporting the idea of optimizing image enhancement.

A Retinex-based network for image enhancement in low-light environments.

Most of the existing low-light image enhancement methods suffer from the problems of detail loss, color distortion and excessive noise. To address the above-mentioned issues, this paper proposes a neural network-based low-light image enhancement network. The network is divided into three parts: decomposition network, reflection component denoising network, and illumination component enhancement network. In the decomposition network, the input image is decomposed into a reflection image and an illumination image. In the reflection component denoising network, the Unet3+ network improved by fusion CA attention is adopted to denoise the reflection image. In the illumination component enhancement network, the adaptive mapping curve is adopted to enhance the illumination image iteratively. Finally, the processed illumination and reflection images are fused based on Retinex theory to obtain the final enhanced image. The experimental results show that the proposed network achieves excellent visual effects in subjective evaluation. Additionally, it shows a significant improvement in objective evaluation metrics, including PSNR, SSIM, NIQE, and so on, when compared to the results in several public datasets.

Dynamic contrast-enhanced MR imaging in identifying active anal fistula after surgery.

BACKGROUND: It is challenging to identify residual or recurrent fistulas from the surgical region, while MR imaging is feasible. The aim was to use dynamic contrast-enhanced MR imaging (DCE-MRI) technology to distinguish between active anal fistula and postoperative healing (granulation) tissue. METHODS: Thirty-six patients following idiopathic anal fistula underwent DCE-MRI. Subjects were divided into Group I (active fistula) and Group IV (postoperative healing tissue), with the latter divided into Group II (≤ 75 days) and Group III (> 75 days) according to the 75-day interval from surgery to postoperative MRI reexamination. MRI classification and quantitative analysis were performed. Correlation between postoperative time intervals and parameters was analyzed. The difference of parameters between the four groups was analyzed, and diagnostic efficiency was tested by receiver operating characteristic curve. RESULTS: Wash-in rate (WI) and peak enhancement intensity (PEI) were significantly higher in Group I than in Group II (p = 0.003, p = 0.040), while wash-out rate (WO), time to peak (TTP), and normalized signal intensity (NSI) were opposite (p = 0.031, p = 0.007, p = 0.010). Area under curves for discriminating active fistula from healing tissue within 75 days were 0.810 in WI, 0.708 in PEI, 0.719 in WO, 0.783 in TTP, 0.779 in NSI. All MRI parameters were significantly different between Group I and Group IV, but not between Group II and Group III, and not related to time intervals. CONCLUSION: In early postoperative period, DCE-MRI can be used to identify active anal fistula in the surgical area. TRIAL REGISTRATION: Chinese Clinical Trial Registry: ChiCTR2000033072.

Dual-Channel in Spatial-Frequency Domain CycleGAN for perceptual enhancement of transcranial cortical vascular structure and function.

Observing cortical vascular structures and functions using laser speckle contrast imaging (LSCI) at high resolution plays a crucial role in understanding cerebral pathologies. Usually, open-skull window techniques have been applied to reduce scattering of skull and enhance image quality. However, craniotomy surgeries inevitably induce inflammation, which may obstruct observations in certain scenarios. In contrast, image enhancement algorithms provide popular tools for improving the signal-to-noise ratio (SNR) of LSCI. The current methods were less than satisfactory through intact skulls because the transcranial cortical images were of poor quality. Moreover, existing algorithms do not guarantee the accuracy of dynamic blood flow mappings. In this study, we develop an unsupervised deep learning method, named Dual-Channel in Spatial-Frequency Domain CycleGAN (SF-CycleGAN), to enhance the perceptual quality of cortical blood flow imaging by LSCI. SF-CycleGAN enabled convenient, non-invasive, and effective cortical vascular structure observation and accurate dynamic blood flow mappings without craniotomy surgeries to visualize biodynamics in an undisturbed biological environment. Our experimental results showed that SF-CycleGAN achieved a SNR at least 4.13 dB higher than that of other unsupervised methods, imaged the complete vascular morphology, and enabled the functional observation of small cortical vessels. Additionally, the proposed method showed remarkable robustness and could be generalized to various imaging configurations and image modalities, including fluorescence images, without retraining.

A bilateral filtering-based image enhancement for Alzheimer disease classification using CNN.

This study aims to develop an optimally performing convolutional neural network to classify Alzheimer's disease into mild cognitive impairment, normal controls, or Alzheimer's disease classes using a magnetic resonance imaging dataset. To achieve this, we focused the study on addressing the challenge of image noise, which impacts the performance of deep learning models. The study introduced a scheme for enhancing images to improve the quality of the datasets. Specifically, an image enhancement algorithm based on histogram equalization and bilateral filtering techniques was deployed to reduce noise and enhance the quality of the images. Subsequently, a convolutional neural network model comprising four convolutional layers and two hidden layers was devised for classifying Alzheimer's disease into three (3) distinct categories, namely mild cognitive impairment, Alzheimer's disease, and normal controls. The model was trained and evaluated using a 10-fold cross-validation sampling approach with a learning rate of 0.001 and 200 training epochs at each instance. The proposed model yielded notable results, such as an accuracy of 93.45% and an area under the curve value of 0.99 when trained on the three classes. The model further showed superior results on binary classification compared with existing methods. The model recorded 94.39%, 94.92%, and 95.62% accuracies for Alzheimer's disease versus normal controls, Alzheimer's disease versus mild cognitive impairment, and mild cognitive impairment versus normal controls classes, respectively.

Topic highlight on texture and color enhancement imaging in gastrointestinal diseases.

Olympus Corporation developed texture and color enhancement imaging (TXI) as a novel image-enhancing endoscopic technique. This topic highlights a series of hot-topic articles that investigated the efficacy of TXI for gastrointestinal disease identification in the clinical setting. A randomized controlled trial demonstrated improvements in the colorectal adenoma detection rate (ADR) and the mean number of adenomas per procedure (MAP) of TXI compared with those of white-light imaging (WLI) observation (58.7% vs 42.7%, adjusted relative risk 1.35, 95%CI: 1.17-1.56; 1.36 vs 0.89, adjusted incident risk ratio 1.48, 95%CI: 1.22-1.80, respectively). A cross-over study also showed that the colorectal MAP and ADR in TXI were higher than those in WLI (1.5 vs 1.0, adjusted odds ratio 1.4, 95%CI: 1.2-1.6; 58.2% vs 46.8%, 1.5, 1.0-2.3, respectively). A randomized controlled trial demonstrated non-inferiority of TXI to narrow-band imaging in the colorectal mean number of adenomas and sessile serrated lesions per procedure (0.29 vs 0.30, difference for non-inferiority -0.01, 95%CI: -0.10 to 0.08). A cohort study found that scoring for ulcerative colitis severity using TXI could predict relapse of ulcerative colitis. A cross-sectional study found that TXI improved the gastric cancer detection rate compared to WLI (0.71% vs 0.29%). A cross-sectional study revealed that the sensitivity and accuracy for active Helicobacter pylori gastritis in TXI were higher than those of WLI (69.2% vs 52.5% and 85.3% vs 78.7%, respectively). In conclusion, TXI can improve gastrointestinal lesion detection and qualitative diagnosis. Therefore, further studies on the efficacy of TXI in clinical practice are required.

A Preliminary Study on the Application of Contrast-Enhanced Ultrasonography in Children With Peripheral Neuroblastic Tumors.

The purpose of this study was to retrospectively analyze the characteristics of contrast-enhanced ultrasound (CEUS) images and quantitative parameters of time-intensity curves (TICs) in children's peripheral neuroblastic tumors (pNTs). By comparing the imaging features and quantitative parameters of the TICs of neuroblastoma (NB) and ganglioneuroblastoma (GNB) patients, we attempted to identify the distinguishing points between NB and GNB. A total of 35 patients confirmed to have pNTs by pathologic examination were included in this study. Each child underwent CEUS with complete imaging data (including still images and at least 3 min of video files). Twenty-four patients were confirmed to have NB, and 11 were considered to have GNB according to differentiation. The CEUS image features and quantitative parameters of the TICs of all lesions were analyzed to determine whether there were CEUS-related differences between the two types of pNT. There was a significant difference in the enhancement patterns of the CEUS features (χ2 = 5.303, p < 0.05), with more "peripheral-central" enhancement in the NB group and more "central-peripheral" enhancement in the GNB group. In the TIC, the rise time and time to peak were significantly different (p < 0.05). The receiver operating characteristic curve showed that the probability of ganglion cell NB increased significantly after RT > 15.29, with a sensitivity of 0.636 and a specificity of 0.958. When the peak time was greater than 16.155, the probability of NB increased significantly, with a sensitivity of 0.636 and a specificity of 0.958. The CEUS features of NB and GNB patients are very similar, and it is difficult to distinguish them. Rise time and time to peak may be useful in identifying GNB and NB, but the sample size of this study was small, and the investigation was only preliminary; a larger sample size is needed to support these conclusions.

Intra-individual comparison of Sonazoid contrast-enhanced ultrasound and SonoVue contrast-enhanced ultrasound in diagnosing hepatocellular carcinoma.

PURPOSE: To assess whether the diagnostic performance of Sonazoid contrast-enhanced ultrasound (SZUS) is non-inferior to that of SonoVue contrast-enhanced ultrasound (SVUS) in diagnosing hepatocellular carcinoma (HCC) in individuals with high risk. MATERIALS AND METHODS: This prospective study was conducted from October 2020 to May 2022 and included participants with a high risk of HCC who underwent SZUS and SVUS. All lesions were confirmed by clinical or pathological diagnosis. Each nodule was classified according to the Contrast-Enhanced Ultrasound Liver Imaging Reporting and Data System version 2017 (CEUS LI-RADS v2017) for SVUS and SZUS and the modified CEUS LI-RADS (using Kupffer phase defect instead of late and mild washout) for SZUS. The diagnostic performance of both two modalities for all observations was compared. Analysis of the vascular phase and Kupffer phase imaging characteristics of CEUS was performed. RESULTS: One hundred and fifteen focal liver lesions from 113 patients (94 HCCs, 12 non-HCC malignancies, and 9 benign lesions) were analysed. According to CEUS LI-RADS (v2017), SVUS and SZUS showed similar sensitivity (71.3% vs. 72.3%) and specificity (85.7% vs. 81.0%) in HCC diagnosis. However, the modified CEUS LI-RADS did not significantly improve the diagnostic efficacy of Sonazoid compared to CEUS LI-RADS v2017, having equivalent sensitivity (73.4% vs. 72.3%) and specificity (81.0% vs. 81.0%). The agreement between SVUS and SZUS for all observations was 0.610 (95% CI 0.475, 0.745), while for HCCs it was 0.452 (95% CI 0.257, 0.647). CONCLUSION: Using LI-RADS v2017, SZUS and SVUS showed non-inferior efficacy in evaluating HCC lesions. In addition, adding Kupffer phase defects to SZUS does not notably improve its diagnostic efficacy.

Turbo spin-echo-based enhanced acceleration-selective arterial spin labeling without electrocardiography or peripheral pulse unit triggering and contrast enhancement for lower extremity MRA.

PURPOSE: Lower extremity magnetic resonance angiography (MRA) without electrocardiography (ECG) or peripheral pulse unit (PPU) triggering and contrast enhancement is beneficial for diagnosing peripheral arterial disease (PAD) while avoiding synchronization failure and nephrogenic systemic fibrosis. This study aimed to compare the diagnostic performance of turbo spin-echo-based enhanced acceleration-selective arterial spin labeling (eAccASL) (TSE-Acc) of the lower extremities with that of turbo field-echo-based eAccASL (TFE-Acc) and triggered angiography non-contrast enhanced (TRANCE). METHODS: Nine healthy volunteers and a patient with PAD were examined on a 3.0 Tesla magnetic resonance imaging (MRI) system. The artery-to-muscle signal intensity ratio (SIR) and contrast-to-noise ratio (CNR) were calculated. The arterial visibility (1: poor, 4: excellent) and artifact contamination (1: severe, 4: no) were independently assessed by two radiologists. Phase-contrast MRI and digital subtraction angiography were referenced in a patient with PAD. Friedman's test and a post-hoc test according to the Bonferroni-adjusted Wilcoxon signed-rank test were used for the SIR, CNR, and visual assessment. p < 0.05 was considered statistically significant. RESULTS: No significant differences in nearly all the SIRs were observed among the three MRA methods. Higher CNRs were observed with TSE-Acc than those with TFE-Acc (anterior tibial artery, p = 0.014; peroneal artery, p = 0.029; and posterior tibial artery, p = 0.014) in distal arterial segments; however, no significant differences were observed upon comparison with TRANCE (all p > 0.05). The arterial visibility scores exhibited similar trends as the CNRs. The artifact contamination scores with TSE-Acc were significantly lower (but within an acceptable level) compared to those with TFE-Acc. In the patient with PAD, the sluggish peripheral arteries were better visualized using TSE-Acc than those using TFE-Acc, and the collateral and stenosis arteries were better visualized using TSE-Acc than those using TRANCE. CONCLUSION: Peripheral arterial visualization was better with TSE-Acc than that with TFE-Acc in lower extremity MRA without ECG or PPU triggering and contrast enhancement, which was comparable with TRANCE as the reference standard. Furthermore, TSE-Acc may propose satisfactory diagnostic performance for diagnosing PAD in patients with arrhythmia and chronic kidney disease.

Amide proton transfer-weighted imaging with a short acquisition time based on a self B0 correction using the turbo spin echo-Dixon method: A phantom study.

PURPOSE: Conventional amide proton transfer (APT)-weighted imaging requires a chemical exchange saturation transfer (CEST) sequence with multiple saturation frequency offsets and a B0 correction sequence, plus a long acquisition time that can be reduced by applying the conventional method using CEST images with seven radiation pulses (i.e., the seven-points method). For a further reduction of acquisition times, we propose fast two-dimensional (2D) APT-weighted imaging based on a self B0 correction using the turbo spin echo (TSE)-Dixon method. We conducted a phantom study to investigate the accuracy of TSE-Dixon APT-weighted imaging. METHODS: We prepared two types of phantoms with six samples for a concentrationdependent evaluation and a pH-dependent evaluation. APT-weighted images were acquired by the conventional, seven-points, and TSE-Dixon methods. Linear regression analyses assessed the dependence between each method's APT signal intensities (SIs) and the concentration or pH. We performed a one-way analysis of variance with Tukey's honestly significant difference post hoc test to compare the APT SIs among the three methods. The agreement of the APT SIs between the conventional and seven-points or TSE-Dixon methods was assessed by a Bland- Altman plot analysis. RESULTS: The APT SIs of all three acquisition methods showed positive concentration dependence and pH dependence. No significant differences were observed in the APT SIs between the conventional and TSE-Dixon methods at each concentration. The Bland-Altman plot analyses showed that the APT SIs measured with the seven-points method resulted in 0.42% bias and narrow 95% limits of agreement (LOA) (0.93%-0.09%) compared to the conventional method. The APT SIs measured using the TSE-Dixon method showed 0.14% bias and similar 95% LOA (-0.33% to 0.61%) compared with the seven-points method. The APT SIs of all three methods showed positive pH dependence. At each pH, no significant differences in the APT SIs were observed among the methods. Bland-Altman plot analyses showed that the APT SIs measured with the seven-points method resulted in low bias (0.03%) and narrow 95% LOA (-0.30% to 0.36%) compared to the conventional method. The APT SIs measured by the TSE-Dixon method showed slightly larger bias (0.29%) and similar 95% LOA (from -0.15% to 0.72%) compared to those measured by the seven-points method. CONCLUSION: These results demonstrated that our proposed method has the same concentration dependence and pH dependence as the conventional method and the seven-points method. We thus expect that APT-weighted imaging with less influence of motion can be obtained in clinical examinations.

Accelerated multi-b-value multi-shot diffusion-weighted imaging based on EPI with keyhole and a low-rank tensor constraint.

PURPOSE: Multi-Shot (MS) Echo-Planar Imaging (EPI) may improve the in-plane resolution of multi-b-value DWI, yet it also considerably increases the scan time. Here we explored the combination of EPI with Keyhole (EPIK) and a calibrationless reconstruction algorithm for acceleration of multi-b-value MS-DWI. METHODS: We firstly analyzed the impact of nonuniform phase accrual in EPIK on the reconstructed image. Based on insights gained from the analysis, we developed a calibrationless reconstruction algorithm based on a Space-Contrast-Coil Locally Low-Rank Tensor (SCC-LLRT) constraint for reconstruction of EPIK-acquired data. We compared the algorithm with a modified SPatial-Angular Locally Low-Rank (SPA-LLR) algorithm through simulations, phantoms, and in vivo study. We then compared EPIK with uniformly undersampled EPI for accelerating multi-b-value DWI in 6 healthy subjects. RESULTS: Through theoretical derivations, we found that the reconstruction of EPIK with a SENSE-encoding-based algorithm, such as SPA-LLR, may cause additional aliasing artifacts due to the frequency-dependent distortion of the coil sensitivity. Results from simulations, phantoms, and in vivo study verified the theoretical finding by showing that the calibrationless SCC-LLRT algorithm reduced aliasing artifacts compared with SPA-LLR. Finally, EPIK with SCC-LLRT substantially reduced the ghosting artifacts compared with uniform undersampled multi-b-value DWI, decreasing the fitting errors in ADC (0.05 ± 0.01 vs 0.10 ± 0.01, P < 0.001) and IVIM mapping (0.026 ± 0.004 vs 0.06 ± 0.006, P < 0.001). CONCLUSION: The SCC-LLRT algorithm reduced the aliasing artifacts of EPIK by using a calibrationless modeling of the multi-coil data. The dense sampling of k-space center offers EPIK a potential to improve image quality for acceleration of multi-b-value MS-DWI.

Constrained alternating minimization for parameter mapping (CAMP).

OBJECTIVE: To improve image quality in highly accelerated parameter mapping by incorporating a linear constraint that relates consecutive images. APPROACH: In multi-echo T1 or T2 mapping, scan time is often shortened by acquiring undersampled but complementary measures of k-space at each TE or TI. However, residual undersampling artifacts from the individual images can then degrade the quality of the final parameter maps. In this work, a new reconstruction method, dubbed Constrained Alternating Minimization for Parameter mapping (CAMP), is introduced. This method simultaneously extracts T2 or T1* maps in addition to an image for each TE or TI from accelerated datasets, leveraging the constraints of the decay to improve the reconstructed image quality. The model enforces exponential decay through a linear constraint, resulting in a biconvex objective function that lends itself to alternating minimization. The method was tested in four in vivo volunteer experiments and validated in phantom studies and healthy subjects, using T2 and T1 mapping, with accelerations of up to 12. MAIN RESULTS: CAMP is demonstrated for accelerated radial and Cartesian acquisitions in T2 and T1 mapping. The method is even applied to generate an entire T2 weighted image series from a single TSE dataset, despite the blockwise k-space sampling at each echo time. Experimental undersampled phantom and in vivo results processed with CAMP exhibit reduced artifacts without introducing bias. SIGNIFICANCE: For a wide array of applications, CAMP linearizes the model cost function without sacrificing model accuracy so that the well-conditioned and highly efficient reconstruction algorithm improves the image quality of accelerated parameter maps.

Comparison of the efficacy of the gadoxetic acid MRI-derived relative enhancement index (REI) and functional liver imaging score (FLIS) in predicting liver function: validation with Albumin-Bilirubin (ALBI) grade.

PURPOSE: This study compared the predictive performance of the relative enhancement index (REI) derived from gadoxetic acid (GA)-enhanced MRI with that of the functional liver imaging score (FLIS) in estimating liver function among patients with chronic liver disease (CLD) or liver cirrhosis (LC) by validating them with the albumin-bilirubin (ALBI) grade. MATERIALS AND METHODS: We retrospectively examined 166 patients (79 women, 87 men; 57.4 years) who were diagnosed with LC or CLD and underwent GA-enhanced MRI between August 2020 and September 2023. The enhancement ratio (ER) is calculated using the formula: ER = [hepatobiliary phase liver signal (SI HBP20)-precontrast liver signal (SI pre)]/SI pre. The REI is calculated using the formula: REI = Liver Volume (LV) × ER. FLIS was assigned from the sum of three HBP image features, each scored between 0 and 2: liver parenchymal enhancement, biliary contrast excretion, and portal vein sign. Receiver operating characteristic (ROC) curve analysis was performed to determine the optimal cutoff values of ER, REI, and FLIS in differentiating between ALBI grades. The area under the curve (AUC), accuracy, sensitivity, and specificity were calculated for REI and FLIS to distinguish the ALBI grades. Spearman's rank correlation was used to evaluate the ER, REI, and FLIS correlations between the ALBI grades. To evaluate inter-reader reliability for LV, ER, REI, and FLIS, intraclass correlation coefficient (ICC) was used. RESULTS: ROC curve analysis showed that the optimal cutoff value of REI for predicting ALBI Grade 1 was 899-905 for readers 1 and 2 and 461-477 for ALBI Grade 3, respectively. REI performed best in predicting ALBI Grade 1, achieving an accuracy range of 94%-92.2%, sensitivity of 94.9%-94.1%, and specificity of 91.7%-87.5% for readers 1 and 2, respectively. All parameters showed high accuracy in distinguishing ALBI Grade 3 from other grades. However, REI outperformed the others, showing an accuracy range of 98.8%-97.6%, sensitivity of 94.4%-94.4%, and specificity of 99.3%-98% for readers 1 and 2, respectively. REI showed the best and very strong correlation with ALBI for both readers. CONCLUSION: REI showed a very strong correlation with the ALBI grades for assessing liver function. It outperformed FLIS in predicting the ALBI grades, indicating its potential as a radiologic tool comparable to or better than FLIS in predicting liver function, especially given its dependence on liver volume.

A Swin transformer encoder-based StyleGAN for unbalanced endoscopic image enhancement.

With the rapid development of artificial intelligence, automated endoscopy-assisted diagnostic systems have become an effective tool for reducing the diagnostic costs and shortening the treatment cycle of patients. Typically, the performance of these systems depends on deep learning models which are pre-trained with large-scale labeled data, for example, early gastric cancer based on endoscopic images. However, the expensive annotation and the subjectivity of the annotators lead to an insufficient and class-imbalanced endoscopic image dataset, and these datasets are detrimental to the training of deep learning models. Therefore, we proposed a Swin Transformer encoder-based StyleGAN (STE-StyleGAN) for unbalanced endoscopic image enhancement, which is composed of an adversarial learning encoder and generator. Firstly, a pre-trained Swin Transformer is introduced into the encoder to extract multi-scale features layer by layer from endoscopic images. The features are subsequently fed into a mapping block for aggregation and recombination. Secondly, a self-attention mechanism is applied to the generator, which adds detailed information of the image layer by layer through recoded features, enabling the generator to autonomously learn the coupling between different image regions. Finally, we conducted extensive experiments on a private intestinal metaplasia grading dataset from a Grade-A tertiary hospital. The experimental results show that the images generated by STE-StyleGAN are closer to the initial image distribution, achieving a Fréchet Inception Distance (FID) value of 100.4. Then, these generated images are used to enhance the initial dataset to improve the robustness of the classification model, and achieved a top accuracy of 86 %.