Machine-reported electrocardiographic findings suggesting right-heart strain are routinely generated during electrocardiogram (ECG) acquisition, but their relationship to echocardiographic pulmonary hypertension phenotypes and right-heart abnormalities remains incompletely defined. This study evaluated whether machine-reported right axis deviation (RAD) or right ventricular hypertrophy (RVH) is associated with echocardiographic pulmonary hypertension phenotypes and right-heart abnormalities in hospitalized patients. This retrospective observational study used linked MIMIC-IV-ECG and MIMIC-IV-ECHO data. Echocardiograms were linked to the closest ECG obtained from 7 days before echocardiography through the time of echocardiography. The primary exposure was machine-reported RAD or RVH. The primary outcome was Echo-PH specific, a composite echo-derived phenotype including tricuspid regurgitation velocity greater than 3.4 m/s, moderate or severe pulmonary hypertension text, or right ventricular pressure overload. Logistic regression adjusted for demographics, comorbidities, and ICU status, with patient-level cluster-robust standard errors. The cohort included 68 905 ECG-echocardiography pairs from 42 078 patients; 2815 pairs were RAD/RVH-positive. For Echo-PH specific, RAD/RVH had sensitivity 7.5%, specificity 96.7%, positive predictive value 35.5%, and negative predictive value 81.4%. RAD/RVH remained associated with Echo-PH specific after full adjustment using cluster-robust standard errors (odds ratio, 2.04; 95% confidence interval, 1.84-2.26). The adjusted probability of Echo-PH specific was 18.8% without RAD/RVH and 30.0% with RAD/RVH. Machine-reported ECG RAD/RVH was highly specific but insensitive for echocardiographic pulmonary hypertension phenotypes and right-heart abnormalities. These routine ECG findings may serve as supportive clues to echocardiographic right-heart disease but should not be used to exclude it.
Functional MRI (fMRI) remains one of the primary tools for non-invasive studies of brain activity and organization in humans. Recently, multi-echo imaging has generated interest due to the improved signal-to-noise and potential for superior denoising. In parallel, developments in MRI processing techniques, such as the use of phase data and advanced denoising methods, have continued to advance the field. An important step towards adopting these methodologies is directly comparing them to existing techniques using real-world data. We present a neuroimaging dataset that allows for within-subject comparison of single-echo vs multi-echo imaging with cutting-edge imaging acquisition parameters such as magnitude and phase reconstruction and no-excitation (noise only) volumes. The sample includes test-retest data from eight young adults. Each session includes a T1-weighted anatomical scan, four resting-state functional MRI scans (two each for single-echo and complex multi-echo), and a multi-echo task-based functional MRI scan from a fractal n-back working memory task. Raw imaging files are released, as well as derivatives from our open-source processing pipelines. These rich data provide opportunities for direct comparison of single-echo and multi-echo methodologies. Moving forward, the data facilitate studies of evaluating how advanced image acquisition and processing impact test-retest reliability.
Semantic segmentation technology based on Inverse Synthetic Aperture Radar (ISAR) images can provide crucial perception and analytical capabilities for intelligent safety maintenance of on-orbit spacecraft. However, conventional semantic segmentation methods suffer from three main limitations: firstly, the lack of modeling for radar physical characteristics in the "image first, segment later" pipeline leads to loss of scattering information and phase details; secondly, reliance on extensive pixel-level manual annotation increases application costs; thirdly, ineffective utilization of spacecraft structural priors fails to guide networks to focus on the main body and edges of spacecraft segmentation. To address these issues, this paper proposes a complex-domain semantic segmentation framework named One-Stop Segmentation (OSS) based on ISAR echoes. The framework incorporates two innovative modules: an Automatic ISAR Labeling (AIL) method designed based on ISAR scattering characteristics to generate labels corresponding to ISAR echoes, and a complex-domain semantic segmentation network named One-Stop Segmentation Network (OSSNet) that performs semantic segmentation directly on echoes, avoiding information loss from imaging while shortening the data processing chain. Core contributions of OSSNet include: (1) a Domain Alignment Module (DAM) to effectively mitigate domain mismatch caused by data distribution differences between raw echo signals and labels; (2) a Multi-Perspective Attention (MPA) framework incorporating a Sliding Correlation Attention (SCA) module and a Subdomain Balanced Attention (SBA) module, lever-aging spacecraft structural priors to guide the network's focus on main structures and edge details from complementary perspectives, significantly improving segmentation ac-curacy. Experimental results on a simulated ground-based radar dataset demonstrate that the proposed OSS framework achieves a mean Intersection over Union (mIoU) of 92.13% and a mean F1-score of 95.75% in ISAR spacecraft semantic segmentation tasks, outperforming existing methods.
An MRI scanner was designed and built to encode k $$ k $$ -space points in the spin echoes occurring between 18 0 ∘ $$ 18{0}^{\circ } $$ pulses in an echo train by using blipped B 0 $$ {B}_0 $$ gradient pulses applied just prior to those spin echoes. The proposed MRI scanner is a modification of an original design that used TRansmit Array Spatial Encoding (TRASE), a built-in B 0 $$ {B}_0 $$ gradient, and a thin RF coil defining a single axial slice. However, for TRASE, the thin profile coil needed a spatially uniform B 1 $$ {B}_1 $$ phase, and this proved difficult to achieve. We therefore replaced the RF encoding coil with a low-power B 0 $$ {B}_0 $$ gradient coil. This removed the need for a uniform spatial B 1 $$ {B}_1 $$ phase for the single slice RF coil to achieve Fourier image encoding. The pulse sequence then sent all 18 0 ∘ $$ 18{0}^{\circ } $$ transmit RF pulses through the one remaining single slice RF coil with B 0 $$ {B}_0 $$ gradient pulses applied between the RF pulses. The spin echoes between the RF pulses were received and used to define the k $$ k $$ -space points in one transverse direction. Image encoding in the perpendicular transverse direction was accomplished via frequency encoding within the built-in transverse B 0 $$ {B}_0 $$ gradient. Mineral oil phantoms were used to establish a proof-of-concept for the blipped-gradient imaging approach. The phantom images give a proof-of-concept level verification of the blipped-gradient MRI design. With work to address engineering imperfections, a blipped-gradient approach could be used to achieve the extreme Size, Weight, and Power (SWaP) requirements for a spaceworthy MRI.
Early recognition of myxomatous mitral valve disease (MMVD) is crucial for extending the lifespan and improving the quality of life in dogs. Timely diagnosis allows clinicians to initiate medical therapy before the onset of congestive heart failure. However, early-stage MMVD is challenging to identify on radiographs alone, and while echocardiography is highly informative, its interpretation remains highly operator-dependent. This paper describes the development and validation of GGNet, an automated multimodal deep learning framework that synthesizes echocardiographic and thoracic radiographic data for accurate MMVD staging. In this retrospective, single-center study, diagnostic images collected between June 2014 and January 2024 were evaluated. The final cohort comprised 902 dogs (n=902), distributed across stages: normal (n=232), stage B1 (n=243), stage B2 (n=190), and stage C (n=237). Imaging modalities included two-dimensional echocardiograms [right parasternal short-axis at left atrium (LA)/aortic root (Ao) level] and thoracic radiographs [right lateral (RL) and ventrodorsal (VD) projections]. We evaluated GGNet, a dual-input (Echo-RL) architecture employing a high-level feature fusion strategy and a selective partial unfreezing fine-tuning protocol [L2-L4, fully connected (FC) layers], on this dataset. Model performance was evaluated using a five-fold cross-validation approach. The final GGNet configuration achieved an overall accuracy of 80.3%±2.8%. Crucially, for the clinical task of distinguishing stage B2, the threshold for initiating pimobendan therapy, the model demonstrated a sensitivity of 82.1%±7.5% and a positive predictive value (PPV) of 91.1%±4.0%, effectively minimizing both false negatives and false positives. The proposed GGNet framework provides a reliable diagnostic aid for MMVD staging, reducing subjective variability in image interpretation and offering practical decision support for veterinary cardiology. However, its clinical efficacy inherently relies on standardized, high-quality image acquisition by the operator. Furthermore, as a single-center study utilizing internal cross-validation, future external validation on diverse, multi-center datasets is required before broader clinical deployment.
This study aimed to evaluate the association between LAA metabolic parameters-particularly lactic acid, glucose, and calcium-and spontaneous echo contrast, and to develop and externally validate a multivariable prediction model incorporating these indicators. Consecutive patients with AF undergoing radiofrequency catheter ablation and/or left atrial appendage occlusion were retrospectively enrolled. All patients underwent preprocedural transesophageal echocardiography with direct LAA blood sampling for metabolic analysis. An internal cohort was used for feature selection by LASSO regression and multivariable logistic regression. Model performance was assessed using ROC analysis, calibration, and decision curve analysis, with external validation in an independent cohort. A total of 272 patients were included in the internal cohort, among whom 96 (35.3%) had SEC. Patients with SEC showed higher LAA lactic acid levels and lower LAA glucose and calcium levels. Age, persistent AF, LAA blood flow velocity, LAA lactic acid, LAA glucose, and LAA calcium were independently associated with SEC. The resulting nomogram demonstrated excellent discrimination in the internal cohort (AUC 0.895) and maintained robust performance in the external cohort (AUC 0.947). Decision curve analysis indicated a positive net clinical benefit across a wide range of threshold probabilities. LAA metabolic characteristics, particularly elevated lactic acid levels, are independently associated with SEC in AF. A prediction model integrating metabolic, clinical, and echocardiographic parameters provides robust and externally validated risk stratification for SEC.
Pneumonia onset is associated with decreased muscle mass in patients with severe cerebral palsy (CP). In this longitudinal study, we examined whether ultrasound-derived muscle thickness (MT) and echo intensity (EI) are linked to pneumonia onset in patients with severe CP. We included 71 patients with severe CP (45 males, 26 females; mean age 43.3 years) and investigated the association between MT and EI of six muscles (quadriceps, biceps brachii, rectus abdominis, internal oblique [IO], external oblique, and transverse abdominis) and pneumonia onset over a 6-month follow-up. Logistic regression analysis showed that lower MT in the IO was significantly associated with pneumonia development after adjusting for prior pneumonia and other confounders. These findings suggest that low IO MT may help identify patients with severe CP at risk of pneumonia onset.
Objectives: This study evaluates the protocol-level image quality and quantitative diffusion metrics of a clinically implemented deep-learning-reconstructed readout-segmented echo-planar imaging protocol with water-excitation spectral fat saturation (DL-rs-EPI with WEXfs) compared with conventional rs-EPI using spectral attenuated inversion recovery (SPAIR) at 3 T. Methods: Overall, 80 patients underwent breast magnetic resonance imaging (MRI) with both conventional rs-EPI with SPAIR and DL-rs-EPI with WEXfs protocols (b-values: 0, 800, and 1200 s/mm2). ROI-based relative image-quality metrics, including signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and lesion contrast, were assessed at b = 800 and b = 1200 s/mm2; apparent diffusion coefficient (ADC) values were calculated using multi-b-value data. Fat suppression, background diffusion signal, lesion conspicuity, and artifact severity were qualitatively evaluated. A temperature-controlled diffusion phantom (CaliberMRI) was scanned; ADC values were compared with reference values at 24 °C. Results: DL-rs-EPI with WEXfs demonstrated higher ROI-based relative SNR estimates (b800: 5.79 vs. 5.28; b1200: 5.41 vs. 4.94; p < 0.001) and CNR estimates (b800: 3.35 vs. 3.12, p = 0.024; b1200: 3.67 vs. 3.37, p = 0.001), with unchanged lesion contrast. Tumor ADC values were comparable between protocols, whereas normal fibroglandular tissue ADC values were slightly higher, and ADC contrast increased with DL-rs-EPI with WEXfs. Phantom ADC values from both protocols closely matched reference values at 24 °C, without significant differences. DL-rs-EPI with WEXfs demonstrated more homogeneous fat suppression and reduced background diffusion signal, with comparable lesion conspicuity and artifact severity. Conclusions: The combined DL-rs-EPI with WEXfs protocol demonstrated improved qualitative and relative quantitative image quality while preserving tumor ADC measurements. As a protocol-level evaluation, these composite improvements support its clinical feasibility for high-quality breast DWI without implying the isolated effect of DL reconstruction alone.
Firearms are the leading cause of death among children in the United States (US). As of 2023, half of US states had enacted laws allowing permitless concealed carry of firearms. Our cross-sectional study evaluated the association between permitless concealed carry laws and child general health using data from the nationwide Environmental influences on Child Health Outcomes (ECHO) Cohort collected between 2003 and 2023. Children aged 1-21 years with caregiver- or self-reported general health status were included. Secondary outcomes included child internalizing and externalizing behaviors and child stress. Regression models estimated the association of exposure to state-level permitless concealed carry laws six months prior to each outcome, adjusted for individual- and area-level covariates. One-fifth (20.9%) of the sample (n = 11,325) lived in states allowing permitless concealed carry of a handgun. Children living in these states were 25% less likely (OR: 0.75, 95% CI: 0.60, 0.95) to report excellent/very good general health and had psychological stress scores 0.21 standard deviations higher (β = 0.21, 95% CI: 0.10, 0.31) than children in other states. There was no statistically significant association with internalizing or externalizing behavior scores. Our study found that children living in states that allow permitless concealed carry of firearms had worse general health and higher stress, suggesting the need for policy changes to address gun violence as a public health and human rights crisis.
Inversion recovery prepared ultra-short echo time (IR-UTE)-based MRI enables radiation-free visualization of osseous tissue. However, achieving a sufficient signal-to-noise ratio typically requires long acquisition times. We report on a feasibility study, which proposes a data-driven approach to reconstruct undersampled IR-UTE knee data, thereby accelerating MR-based 3D imaging of bones. Data were acquired with a 3D radial IR-UTE pulse sequence, implemented using the open-source framework Pulseq. A denoising convolutional neural network (DnCNN) was trained in a supervised fashion using data from eight healthy subjects. Conjugate gradient sensitivity encoding (CG-SENSE) reconstructions of different retrospectively undersampled subsets (corresponding to 2.5-min, 5-min, and 10-min acquisition times) were paired with the respective reference dataset reconstruction (30-min acquisition time). The DnCNN was then integrated into a FISTA-based reconstruction algorithm, enabling physics-based iterative reconstruction. Quantitative evaluation was performed on retrospectively undersampled datasets from four additional healthy subjects using scalar metric calculations and an expert reader study. Metrics were also assessed for one prospectively accelerated scan. A pathological case of a tibial plateau fracture was included for qualitative demonstration. The trained DnCNN enabled effective noise suppression, and its application exhibited the most favorable quantitative results, whereas the iterative reconstruction scheme provided complementary mitigation of denoising-induced streaking artifacts, particularly for 5-min. Fracture features could be visualized in the patient case, albeit in less detail compared to photon-counting CT. Utilizing a task-specific trained DnCNN shows potential to shorten scan times for hyperintense MR-based imaging of bone, thereby addressing a key hurdle to clinical implementation.
暂无摘要（点击查看详情）
暂无摘要（点击查看详情）
To develop a 3D reduced FOV sequence for combined ADC and T2 mapping in the prostate in a single scan. A 3D ADC and T2 mapping reduced FOV acquisition is enabled using T2 and diffusion preparation modules with slab-selective tip-down pulses and magnitude stabilizer gradients. Imaging shots are followed by 2D phase navigators for phase correction of diffusion-prepared shots and dummy RF pulses for T2-prepared shots, as well as a constant delay to maintain the steady state of the longitudinal magnetization. Mono-exponential fitting is used for ADC and T2 mapping. T2 mapping accuracy was assessed in a phantom against a single-echo spin-echo reference. In vivo, the sequence was compared in the prostate of 11 healthy volunteers against a multi-echo spin-echo acquisition, as well as standard and reduced FOV (rFOV) single-shot EPI (ssEPI). In the phantom experiments, T2 values were not significantly different from the reference single-echo spin-echo measurements. ADC values in vivo were not significantly different from those obtained using ssEPI. T2 values in vivo showed a mean bias of -21.7 ms compared to those obtained using multi-echo spin-echo with the first echo discarded in the fitting. The proposed sequence achieved similar overall image quality scores to those of ssEPI and rFOV ssEPI, improved perceived distortion scores, but lower perceived SNR scores. The proposed approach enables 3D reduced FOV, single-scan ADC, and T2 mapping with mono-exponential fitting in the prostate.
Exercise-induced pulmonary hypertension (EiPH) represents an early stage of pulmonary vascular disease that remains challenging to identify noninvasively, particularly in patients with borderline resting haemodynamics. We aimed to develop and validate a multimodal non-invasive model integrating clinical characteristics, exercise echocardiography, and cardiopulmonary exercise testing (CPET) to accurately predict invasively confirmed EiPH. This prospective cohort study consecutively enrolled adult patients who presented with exercise limitation following chronic pulmonary artery thrombosis or who exhibited increased tricuspid regurgitation velocity on transthoracic echocardiography. All patients underwent comprehensive clinical evaluation, stress echocardiography, CPET, and invasive exercise right heart catheterization as the diagnostic gold standard. To minimize the impact of physiological variability on the results, all three tests were conducted at the same time. Feature selection was conducted sequentially using Spearman correlation analysis, statistical testing, and LASSO regression to identify core features associated with EiPH. Subsequently, a logistic regression model with elastic net regularization was used. Five-fold cross-validation and grid search were employed to optimize model parameters and evaluate the diagnostic performance of different models. In addition, the DeLong test was used to assess whether the AUC differed significantly between models. Finally, subgroup analyses were performed to validate the robustness of the model. The study included a total of 78 patients, comprising 34 cases of EiPH and 44 cases without EiPH. Patients in the EiPH group were significantly older (68.5 vs. 51.5 years, P < 0.001) and demonstrated reduced exercise capacity, impaired pulmonary function, abnormal right ventricular function, and increased pulmonary vascular resistance. After integrating multimodal data from clinical features, stress echocardiography, and cardiopulmonary exercise testing, the Clinical+Echo+CPET model achieved the best performance, with an AUC of 0.951 (95% CI: 0.902-0.987), an accuracy of 0.871, and a Brier score of 0.128, indicating strong discriminative ability and good calibration. The model maintained high stability in the internal validation cohort, with an AUC of 0.900, a sensitivity of 0.833, and a specificity of 0.700. The DeLong test showed that the multimodal model (Clinical+Echo+CPET) had superior discriminative performance compared with the unimodal models (Clinical, Echo, or CPET). Subgroup analysis demonstrated that the model maintained good diagnostic performance across different age and sex groups. A non-invasive multimodal model integrating clinical indicators, exercise echocardiography, and cardiopulmonary metabolic parameters can reliably identify EiPH.
Cardiac amyloidosis (CA) is an infiltrative cardiomyopathy associated with adverse outcomes. Quantification of myocardial amyloid burden is essential for risk stratification. Although cardiac magnetic resonance (CMR)-derived extracellular volume (ECV) is the reference standard for non-invasive assessment, its use is limited by cost and availability. Therefore, simple and widely accessible tools to estimate amyloid burden are needed. This study aimed to evaluate whether a novel integrated echocardiographic-electrocardiographic (echo-ECG) index, based on the ratio of maximum septal thickness (MST) to QRS voltage in lead I and/or aVR, correlates with CMR-derived ECV in patients with CA. We retrospectively analysed 138 consecutive patients with transthyretin or light-chain CA who underwent CMR at four Italian referral centres. MST/QRS ratios (MST/QRS I, MST/QRS aVR, and MST/(QRS I + aVR)) were calculated using echocardiography and standard 12‑lead ECG. On multivariable linear regression with ECV as a continuous variable, the integrated echo-ECG indices were independently associated with ECV (all p < 0.001); lower QRS voltages in leads I and aVR were also independently associated with higher ECV (both p < 0.01), whereas total QRS voltage was not. In a secondary analysis dichotomising ECV at the cohort median (47%), the integrated echo-ECG indices showed moderate discrimination for higher ECV (AUC 0.71-0.73). MST-to-QRS voltage ratios in leads I and/or aVR are simple and widely accessible markers that correlate with myocardial amyloid burden and may support non-invasive assessment of disease severity in CA.
Ki-67 is a critical proliferation marker in breast cancer, but its preoperative assessment is limited by the invasiveness and sampling bias of core needle biopsy. This study aimed to establish and validate non-invasive prediction models of Ki-67 status of breast cancer based on conventional ultrasound radiomics features, clinical features, or their combination. Retrospective analysis was performed on 558 patients with breast cancer who underwent two-dimensional (2D) ultrasound and Ki-67 detection. Among them, 398 patients in the training set were from Zhejiang Cancer Hospital, and 160 patients in the external validation set were from Lishui Central Hospital. According to the 14% threshold, the patients were divided into Ki-67 low expression group and Ki-67 high expression group. Clinical parameters, conventional ultrasound characteristics, and 2D ultrasound images of the tumor's maximum cross-section were collected. Radiomics features were extracted from the delineated regions of interest (ROIs) with the PyRadiomics package. We used univariate analysis, least absolute shrinkage and selection operator (LASSO) regression, and multivariate logistic regression to determine the independent predictors. Three models-clinical, radiomics, and a combined clinical-radiomics model-were developed. We constructed a nomogram based on the combined model. Model evaluation was undertaken via receiver operating characteristic (ROC) curve analysis [calculating area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), precision, recall, and F1 score], calibration curves, and decision curve analysis (DCA). In addition, SHapley Additive exPlanations (SHAP) were used to interpret the model. In the training (n=398) and external validation (n=160) sets, multivariate logistic regression identified age [odds ratio (OR) =0.971, P=0.026], maximum lesion diameter (OR =1.051, P<0.001), microcalcification (OR =1.548, P=0.109), and posterior echo (OR =0.358, P=0.001) as independent predictors of Ki‑67 expression in breast cancer. LASSO with 5‑fold cross‑validation selected three radiomics features (two texture, one shape). A clinical‑radiomics combined model achieved AUCs of 0.731 [95% confidence interval (CI): 0.670-0.792] and 0.709 (95% CI: 0.614-0.804) in the training and validation sets, with accuracies of 0.643 and 0.750 and F1 scores of 0.728 and 0.840, respectively. Calibration and decision curve analyses demonstrated good consistency and clinical net benefit. A visualized risk nomogram was constructed to estimate individual probabilities. SHAP analysis revealed that radiomics features (e.g., original_glcm_MaximumProbability) and clinical features (microcalcification and posterior echo) contributed most; positive microcalcification increased the likelihood of high Ki‑67 expression, whereas posterior echo attenuation decreased it. Ultrasound-derived radiomics features provide incremental value for predicting Ki-67 expression in breast cancer. This comprehensive clinical-radiomics model demonstrates excellent diagnostic performance and has been interpreted using the SHAP method. It has the potential to serve as a non-invasive preoperative tool to complement core needle aspiration biopsy and play a complementary role in clinical decision-making.
Colorectal cancer (CRC) screening effectively reduces CRC mortality and morbidity, yet screening rates remain below US national targets in rural and low-resourcedd settings. An effective intervention to improve screening is mailed fecal immunochemical tests (FIT) combined with patient navigation. However, these multicomponent interventions have been unevenly adopted across health systems and organizations, and studies of how to spread effective system-level approaches are limited. We conducted a mixed-methods evaluation of a multi-component scale-up approach designed to increase CRC screening rates in rural, low-resourced primary care clinics, based on findings from the SMARTER CRC pragmatic trial. The approach included five scale-up activities: (1) an Extension for Community Healthcare Outcomes (ECHO) tele-mentoring program; (2) patient navigation training; (3) webinars on process design and communication strategies; (4) technical assistance; and (5) dissemination of the Colorectal Cancer Screening Outreach for Rural Populations Facilitation Guide. We measured engagement in scale-up activities, adoption of mailed FIT and patient navigation outreach, and modifications to organizations' CRC screening programs. A total of 47 participants from 25 organizations participated in scale-up activities. Participants were most commonly from clinical practices (28%), hospital-based systems (24%), and community organizations (20%). All organizations participated in the ECHO series (100%, n = 25), and some also engaged in additional scale-up activities. Most organizations (84%, n = 21) reported having a CRC screening program at baseline. Engagement in ECHO and other scale-up activities influenced adoption and modification of CRC screening patient outreach strategies for most organizations (69%, n = 17). Participation led to modifications in existing programs. Participation in multifaceted scale-up activities increased organizational knowledge and engagement in CRC screening patient outreach within rural, low-resourced clinic settings. These activities also supported the refinement of existing CRC screening programs through the adoption and modification of outreach strategies. These findings can inform future efforts to optimize scale-up approaches for CRC screening and other complex interventions in rural, low-resourced healthcare settings. Registered at clinicaltrial.gov (NCT04890054) and at the NCI's Clinical Trials Reporting Program (CTRP # NCI202101032) on May 11, 2021.
Millimeter-wave (mmWave) radar provides a privacy-preserving and illumination-robust sensing modality for contactless gesture recognition. However, sparse radar point clouds degrade substantially as sensing distance increases: the number of valid detections decreases, echo intensity attenuates, and Doppler-related motion cues become less reliable. Such range-induced degradation leads to a distribution shift between near-range training samples and far-field test samples, making it difficult for models trained at short distances to generalize to unseen longer distances. Existing point-cloud gesture recognition methods usually treat radar detections as generic sparse point sequences and rarely model distance-related point loss, echo attenuation, and physical-attribute unreliability explicitly. This work introduces RPT-Mamba, a range-aware physical token Mamba network for sparse mmWave radar point cloud sequences. RPT-Mamba constructs physical point tokens from spatial coordinates, Doppler velocity, echo intensity, point-level range, and sample-level range information. During training, a range-aware stochastic degradation strategy adaptively removes points and masks dynamic attributes according to the estimated sensing distance, while a context-guided attribute reconstruction objective recovers masked Doppler and intensity attributes from spatial and frame-level context. A bidirectional Mamba temporal encoder then models long-range gesture dynamics over frame tokens. On the public mTransSee dataset, RPT-Mamba achieves 92.09% accuracy and 92.04% Macro-F1 under the random split protocol, and 85.34% accuracy and 84.77% Macro-F1 under a challenging near-to-far protocol, exceeding point-cloud, radar-gesture, Transformer, and Mamba baselines.
Perivascular spaces (PVS) are compartments involved in brain waste clearance. PVS are commonly observed in typically developing (TD) children; however, their burden in autism spectrum disorder (ASD) remains unclear. To investigate whether quantitative white matter (WM) PVS burden differs between children with ASD and TD controls using automatic segmentation. Observational. Ninety-eight children with ASD (age range: 2-8 years; mean age 4.8 ± 1.5 years; 78M/20F) and 38 TD children (age range: 2-8 years; mean age 5.5 ± 0.9 years; 23M/15F). 3T; 3D T1-weighted ultrafast gradient-echo and 3D T2-weighted turbo spin-echo sequences. Human Connectome Project pipeline was used to generate enhanced perivascular contrast (EPC) images. The Weakly Supervised Perivascular Spaces Segmentation algorithm was applied to EPC to segment PVS. PVS volume (WM-PVSv) and count (WM-PVSc) were quantified in total WM and six subregions (frontal, parietal, temporal, occipital, limbic, and deepWM). Welch's t-test, chi-square test, and ANCOVA for group differences; Spearman's rank correlation for age, structural brain volumes, and PVS metrics exploratory correlations; multivariable linear regression for global PVS metrics, and linear mixed-effects models for regional analyses, adjusted for age, sex, WM, and extra-axial cerebrospinal fluid volumes. In the adjusted models, no significant differences between ASD and TD were observed, as the diagnostic group was not independently associated with either WM-PVSv (ASD: 2.3 ± 1.2 cm3; TD: 2.0 ± 0.9 cm3; p = 0.228) or WM-PVSc (ASD: 832 ± 298; TD: 754 ± 260; p = 0.121), whereas WM volume was significantly associated with both metrics (β = 0.012 mm3 for WM-PVSv; β = 0.004 mm3 for WM-PVSc). In both ASD and TD, frontal WM exhibited the highest WM-PVScn (ASD: 37.0% ± 4.9%; TD: 28.9% ± 6.6%), whereas deep WM showed the highest WM-PVSvf (ASD: 0.010 ± 0.004; TD: 0.010 ± 0.003). PVS measures appear to reflect inter-individual variability associated with WM volume. No evidence was found for WM-PVS burden as an early-childhood ASD biomarker. 3. Stage 3. Perivascular spaces are small fluid‐filled spaces around brain blood vessels. Their number and volumes are known to increase in adult neurodegenerative diseases. Researchers tested whether autism, a neurodevelopmental condition, shows the same pattern. They measured perivascular spaces using magnetic resonance in 98 children with autism and 38 typically developing children aged 2 to 8 years, using a fully automated computer method. The groups showed no clear difference in their volume or number. The findings suggest that these spaces are likely in relation to brain development in very young children and do not support their use as a diagnostic autism marker.
Background/Objectives: The acute complications of COVID-19 have been well characterized and are frequently associated with increased mortality. Although substantial knowledge regarding long COVID has accumulated since the beginning of the pandemic, important uncertainties remain regarding the long-term clinical, functional, radiological, and metabolic consequences of SARS-CoV-2 infection. Identification of post-COVID-19 complications is therefore essential for appropriate recognition and management. This study aimed to evaluate the long-term complications of COVID-19 at 3 and 9 months after infection. Methods: This prospective study was conducted at Inonu University Turgut Ozal Medical Center. Patients who presented with active post-COVID-19 complaints or for routine follow-up were enrolled. Participants were evaluated at the pulmonology outpatient clinic at 3 and 9 months. At each visit, persistent or new-onset symptoms were assessed, and pulmonary function tests (PFT), the six-minute walk test (6MWT), echocardiography (ECHO), and thoracic computed tomography (CT) were performed as clinically indicated. Patients were stratified into three groups according to the severity of acute illness: outpatient, ward-hospitalized, and ICU-hospitalized. Results: A total of 205 patients (120 male, 85 female) were included. Male patients had significantly higher rates of ward and ICU hospitalization than female patients (p = 0.006). At 9 months, 85.3% of patients had at least one persistent symptom; dyspnea (69.6%), cough (35.6%), and chest pain (32.5%) were the most common. FVC showed a statistically significant increase between months 3 and 9 (p = 0.014), and the 6MWT distance improved significantly (423.56 m vs. 464.10 m; p = 0.008). Ground-glass opacity, present in 90.2% of patients at admission, persisted in 44.3% at 9 months (p < 0.001). Reticular opacities, pleuroparenchymal bands, and mosaic perfusion patterns increased over time. ICU patients had significantly lower ejection fraction values compared with ward and outpatient groups at 9 months (p = 0.046). During follow-up, 13 patients developed pulmonary embolism and 7 developed new-onset diabetes mellitus. Conclusions: Despite the well-characterized acute phase, the long-term sequelae of COVID-19 remain a significant clinical challenge. Identification of late complications is critical for reducing morbidity and understanding the long-term societal and healthcare burden of the pandemic. Multidisciplinary long-term follow-up is warranted, particularly for patients who experienced severe acute illness.