Value of radiomics-based automatic grading of muscle edema in polymyositis/dermatomyositis based on MRI fat-suppressed T2-weighted images.

BACKGROUND: The precise and objective assessment of thigh muscle edema is pivotal in diagnosing and monitoring the treatment of dermatomyositis (DM) and polymyositis (PM). PURPOSE: Radiomic features are extracted from fat-suppressed (FS) T2-weighted (T2W) magnetic resonance imaging (MRI) of thigh muscles to enable automatic grading of muscle edema in cases of polymyositis and dermatomyositis. MATERIAL AND METHODS: A total of 241 MR images were analyzed and classified into five levels using the Stramare criteria. The correlation between muscle edema grading and T2-mapping values was assessed using Spearman's correlation. The dataset was divided into a 7:3 ratio of training (168 samples) and testing (73 samples). Thigh muscle boundaries in FS T2W images were manually delineated with 3D-Slicer. Radiomics features were extracted using Python 3.7, applying Z-score normalization, Pearson correlation analysis, and recursive feature elimination for reduction. A Naive Bayes classifier was trained, and diagnostic performance was evaluated using receiver operating characteristic (ROC) curves and comparing sensitivity and specificity with senior doctors. RESULTS: A total of 1198 radiomics parameters were extracted and reduced to 18 features for Naive Bayes modeling. In the testing set, the model achieved an area under the ROC curve of 0.97, sensitivity of 0.85, specificity of 0.98, and accuracy of 0.91. The Naive Bayes classifier demonstrated grading performance comparable to senior doctors. A significant correlation (r = 0.82, P <0.05) was observed between Stramare edema grading and T2-mapping values. CONCLUSION: The Naive Bayes model, utilizing radiomics features extracted from thigh FS T2W images, accurately assesses the severity of muscle edema in cases of PM/DM.

MRI study on the influence of lumbosacral vertebral body and disc factors on lumbar lordosis in children.

PURPOSE: To evaluate the influence of vertebral and disc wedging on the contribution of lumbar lordosis and the change of disc thickness before and after walking based on MRI. METHODS: Cross-sectional study. A total of 96 normally developing children, aged 5.7 ± 3.0 years old, 55 boys and 41 girls. They were divided into 3 groups: Pre-walking group, Walking group, and Post-walking group. PARAMETERS: lumbar lordosis Angle (LLA), the sum of the lumbar disc wedge Angle (∑D), the sum of the lumbar vertebral body wedge Angle (∑B), disc height (DH). RESULTS: (1) LLA, ∑D, ∑B, and DHL1-S1 were 33.2 ± 8.7°, 14.1 ± 8.6°, 11.9 ± 8.6°, and 6.9 ± 1.2 mm, 7.6 ± 1.4 mm, 8.2 ± 1.6 mm, 8.9 ± 1.7 mm, 8.5 ± 1.8 mm. (2) The difference in LLA values between the Pre-walking and the Post-walking group was statistically significant. DH were significantly different among the three groups. (3) In the Post-walking group, LLA value of girls was significantly higher than that of boys, and DHL3 - 4 and DHL4 - 5 values of girls were significantly lower than that of boys. (4) Age had a low positive correlation with LLA and ∑D and a moderate to strong positive correlation with DH; LLA showed a moderate positive correlation with ∑D, and a low positive correlation with ∑B and DH. CONCLUSION: Age and walking activity are the influencing factors of lumbar lordosis and disc thickening. Walking activity can significantly increase lumbar lordosis, and age is the main factor promoting lumbar disc thickening. DHL4-5 was the thickest lumbar intervertebral disc with the fastest intergroup thickening. Disc wedging contributes more to lumbar lordosis than vertebral wedging.

Expanding Ventricular Diverticulum Overlying the Cerebral Hemisphere through an Open-Lip Schizencephalic Cleft: A Report of Two Pediatric Cases.

INTRODUCTION: Open-lip-type schizencephaly is characterized by trans-cerebral clefts filled with cerebrospinal fluid (CSF) between the subarachnoid space at the hemisphere surface and the lateral ventricles. Disorders related to CSF retention, including hydrocephalus and arachnoid cysts, have reportedly been associated with open-lip schizencephaly and have induced intracranial hypertension in some cases. However, detailed neuroimaging and surgical treatment findings have rarely been described. CASE PRESENTATION: We report 2 cases of open-lip schizencephaly with an expanding CSF-filled cavity overlying the ipsilateral cerebral hemisphere that manifested as signs of intracranial hypertension. Detailed three-dimensional heavily T2-weighted imaging revealed thin borders between the CSF-filled cavity and the subarachnoid space, but no separating structures between the cavity and the lateral ventricle, suggesting that the cavity was directly connected to the lateral ventricle through the schizencephalic cleft but not to the subarachnoid space. Neuroendoscopic observation in case 1 confirmed this finding. Endoscopic fenestration of the cavity to the prepontine cistern was ineffective in case 1. Shunting between the lateral ventricle (case 1) or CSF-filled cavity (case 2) and the peritoneal cavity slightly decreased the size of the CSF-filled cavity. DISCUSSION: We speculate that the thin borders along the margin of the CSF-filled cavity are membranes that previously covered the schizencephalic cleft and are now pushed peripherally. In addition, we believe that the cavity is a ventricular diverticulum protruding through the cleft and that shunting operation is effective against such expanding cavity. Detailed magnetic resonance imaging can be useful for evaluating patients with schizencephaly associated with CSF retention disorders.

Prediction of microvascular invasion in hepatocellular carcinoma patients with MRI radiomics based on susceptibility weighted imaging and T2-weighted imaging.

BACKGROUND: The accurate identification of microvascular invasion (MVI) in patients with hepatocellular carcinoma (HCC) is of great clinical importance. PURPOSE: To develop a radiomics nomogram based on susceptibility-weighted imaging (SWI) and T2-weighted imaging (T2WI) for predicting MVI in early-stage (Barcelona Clinic Liver Cancer stages 0 and A) HCC patients. MATERIALS AND METHODS: A prospective cohort of 189 participants with HCC was included for model training and testing, and an additional 34 participants were enrolled for external validation. ITK-SNAP was used to manually segment the tumour, and PyRadiomics was used to extract radiomic features from the SWI and T2W images. Variance filtering, student's t test, least absolute shrinkage and selection operator regression and random forest (RF) were applied to select meaningful features. Four machine learning classifiers, including K-nearest neighbour, RF, logistic regression and support vector machine-based models, were established. Independent clinical and radiological risk factors were also determined to establish a clinical model. The best radiomics and clinical models were further evaluated in the validation set. In addition, a nomogram was constructed from the radiomic model and independent clinical factors. Diagnostic efficacy was evaluated by receiver operating characteristic curve analysis with fivefold cross-validation. RESULTS: AFP levels greater than 400 ng/mL [odds ratio (OR) 2.50; 95% confidence interval (CI) 1.239-5.047], tumour diameter greater than 5 cm (OR 2.39; 95% CI 1.178-4.839), and absence of pseudocapsule (OR 2.053; 95% CI 1.007-4.202) were found to be independent risk factors for MVI. The areas under the curve (AUCs) of the best radiomic model were 1.000 and 0.882 in the training and testing cohorts, respectively, while those of the clinical model were 0.688 and 0.6691. In the validation set, the radiomic model achieved better diagnostic performance (AUC = 0.888) than the clinical model (AUC = 0.602). The combination of clinical factors and the radiomic model yielded a nomogram with the best diagnostic performance (AUC = 0.948). CONCLUSION: SWI and T2WI-derived radiomic features are valuable for noninvasively and accurately identifying MVI in early-stage HCC. Furthermore, the integration of radiomics and clinical factors yielded a predictive nomogram with satisfactory diagnostic performance and potential clinical benefits.

Brush Sign on pre-treatment imaging is associated with good functional outcome in stroke patients treated with mechanical thrombectomy: A prospective monocentric study.

BACKGROUND: The Brush Sign (BrS) is a radiological biomarker (MRI) showing signal decrease of subependymal and deep medullary veins on paramagnetic-sensitive magnetic resonance sequences. Previous studies have shown controversial results regarding the prognostic value of BrS. We aimed to assess whether BrS on T2*-weighted sequences could predict functional prognosis in patients treated with mechanical thrombectomy (MT). METHODS: We included all consecutive patients with large artery occlusion related stroke in anterior circulation treated with MT between February 2020 and August 2022 at Reims University Hospital. Multivariable logistic regression models were used to investigate factors associated with BrS and its impact on outcomes. RESULTS: Of the 327 included patients, 124 (37,9%) had a BrS on baseline MRI. Mean age was 72 ± 16 years and 184 (56,2 %) were female. In univariate analysis, BrS was associated with a younger age (67 vs 74; p<0.001), a higher NIHSS score (16(10-20) vs 13(8-19); p = 0.047) history of diabetes (15.3% vs 26.1 %; p = 0.022) and a shorter onset to MRI time (145.5 (111.3-188.5) vs 162 (126-220) p = 0.008). In multivariate analyses, patients with a BrS were younger (OR:0.970 (0.951 - 0.989)), tend to have a higher NIHSS score at baseline (OR:1.046 (1.000 - 1.094) and were less likely to have diabetes (OR: 0.433; 0.214-0.879). The presence of BrS was independently associated with functional independence (OR: 2.234(1.158-4,505) at 3 months but not with mortality nor with symptomatic intracerebral hemorrhage. CONCLUSION: BrS on pre-treatment imaging could be considered as a biomarker of physiological adaptation to cerebral ischemia, allowing prolonged viability of brain tissue and might participate in the therapeutic decision.

Volumetric T2 -weighted spin echo imaging with improved SNR using localized quadratic encoding and a spiral readout trajectory.

PURPOSE: To demonstrate T2 -weighted (single-echo) spin-echo (SE) imaging with near-optimal acquisition efficiency by applying SNR-efficient RF slice encoding and spiral readout. METHODS: A quadratic-phase (frequency swept) excitation RF pulse replaced the conventional excitation in T2 -weighted SE sequence to excite a thick slab that is internally spatially encoded by a variable phase along the slice direction. Highly overlapping slabs centered at every desired slice location were acquired in multiple passes, such that the entire imaging volume was excited by contiguous slabs in any given pass. Following 90° excitation, each slab was refocused with a conventional 180° RF to produce a SE signal, followed by a spiral in-out readout. A noise-insensitive reconstruction removed the quadratic phase in the spatial frequency domain, yielding desired slice resolution and improved SNR. RESULTS: Increasing the RF frequency sweep (hence, excitation width) allowed more frequent encoding of each slice over the multiple passes, improving final image SNR, until crosstalk ensued at excessive slab widths compared to their center-to-center spacing. With an optimized slab width, the proposed technique used all passes to acquire every prescribed slice, with substantially improved SNR over conventional SE or 2D-turbo-spin-echo (TSE) scans. Quantitative SNR measurements indicated similar SNR as 3D-TSE, but radiologist scoring favored 3D-TSE, mainly because of spiral-related artifacts and possibly because of regularized reconstructions in 3D-TSE. CONCLUSION: Using SNR-efficient slice excitation scheme and spiral readout helped eliminate SNR and temporal inefficiencies in conventional T2 -weighted imaging, yielding SNR independent of TR or number of passes.

Radiomics-based machine-learning method to diagnose prostate cancer using mp-MRI: a comparison between conventional and fused models.

OBJECTIVES: Multiparametric MRI (mp-MRI) has been significantly used for detection, localization and staging of Prostate cancer (PCa). However, all the assessment suffers from poor reproducibility among the readers. The aim of this study was to evaluate radiomics models to diagnose PCa using high-resolution T2-weighted (T2-W) and dynamic contrast-enhanced (DCE) MRI. MATERIALS AND METHODS: Thirty two patients who had high prostate specific antigen level were recruited. The prostate biopsies considered as the reference to differentiate between 66 benign and 36 malignant prostate lesions. 181 features were extracted from each modality. K-nearest neighbors, artificial neural network, decision tree, and linear discriminant analysis were used for machine-learning study. The leave-one-out cross-validation method was used to prevent overfitting and build robust models. RESULTS: Radiomics analysis showed that T2-W images were more effective in PCa detection compare to DCE images. Local binary pattern features and speeded up robust features had the highest ability for prediction in T2-W and DCE images, respectively. The classifier fusion using decision template method showed the highest performance with accuracy, specificity, and sensitivity of 100%. DISCUSSION: The findings of this framework provide researchers on PCa with a promising method for reliable detection of prostate lesions in MR images by fused model.

SPRING-RIO TSE: 2D T2 -Weighted Turbo Spin-Echo brain imaging using SPiral RINGs with retraced in/out trajectories.

PURPOSE: To develop a new approach to 2D turbo spin -echo (TSE) imaging using annular spiral rings with a retraced in/out trajectory, dubbed "SPRING-RIO TSE", for fast T2 -weighted brain imaging at 3T. METHODS: A long spiral trajectory was split into annular segmentations that were then incorporated into a 2D TSE acquisition module to fully exploit the sampling efficiency of spiral rings. A retraced in/out trajectory strategy coupled with spiral-ring TSE was introduced to increase SNR, mitigate T2 -decay induced artifacts, and self-correct moderate off-resonance while maintaining the target TE and causing no scan time penalty. Model-based k-space estimation and semiautomatic off-resonance correction algorithms were implemented to minimize effects of k-space trajectory infidelity and B0 inhomogeneity, respectively. The resulting SPRING-RIO TSE method was compared to the original spiral-ring (abbreviated "SPRING") TSE and Cartesian TSE using simulations, and phantom and in vivo acquisitions. RESULTS: Simulation and phantom studies demonstrated the performance of the proposed SPRING-RIO TSE pulses sequence, as well as that of trajectory correction and off-resonance correction. Volunteer data showed that the proposed method achieves high-quality 2D T2 -weighted brain imaging with a higher scan efficiency (0:45 min/14 slices versus 1:31 min/14 slices), improved image contrast, and reduced specific absorption rate compared to conventional 2D Cartesian TSE. CONCLUSION: 2D T2 -weighted brain imaging using spiral-ring TSE was implemented and tested, providing several potential advantages over conventional 2D Cartesian TSE imaging.

Central vein sign: A putative diagnostic marker for multiple sclerosis.

The presence of a "central vein sign" (CVS) has been introduced as a biomarker for the diagnosis of multiple sclerosis (MS) and shown to have the ability to accurately differentiate MS from other white matter diseases (MS mimics). Following the development of susceptibility-based magnetic resonance venography that allowed the in vivo detection of CVS, a standard CVS definition was established by introducing the "40% rule" that assesses the number of MS lesions with CVS as a fraction of the total number of lesions to differentiate MS lesions from other types of lesions. The "50% rule," the "three-lesion criteria," and the "six-lesion criteria" were later introduced and defined. Each of these rules had high levels of sensitivity, specificity, and accuracy in differentiating MS from other diseases, which has been recognized by the Magnetic Resonance Imaging in MS (MAGNIMS) group and the Consortium of MS Centers task force. The North American Imaging in Multiple Sclerosis Cooperative even provided statements and recommendations aiming to refine, standardize and evaluate the CVS in MS. Herein, we review the existing literature on CVS and evaluate its added value in the diagnosis of MS and usefulness in differentiating it from other vasculopathies. We also review the histopathology of CVS and identify available automated CVS assessment methods as well as define the role of vascular comorbidities in the diagnosis of MS.

The feasibility investigation of AI -assisted compressed sensing in kidney MR imaging: an ultra-fast T2WI imaging technology.

OBJECT: To explore the feasibility and clinical application of AI -assisted compressed sensing (ACS) technology in kidney MR imaging. METHODS: 33 patients were enrolled in this study, affiliated to our hospital from September 2020 to April 2021. The patients underwent T2-weighed sequences of both the ACS scan and the conventional respiratory navigator (NAVI) scan. We evaluated the subjective image quality scores, including the sharpness of image edge, artifact and the overall image quality, and compared the objective image quality indicators such as scanning time, signal-to-noise ratio (SNR), and contrast signal-to-noise ratio (CNR). The Wilcoxon's rank sum test and the paired t test were used to compare the image quality between ACS and NAVI groups. The p-value less than 0.05 indicated a statistically significant difference. RESULTS: The edge sharpness of the ACS group was significant lower than that of the NAVI group (p < 0.01), however, there were no significant differences in the artifact and the overall rating of image quality between the two groups (p > 0.05). In terms of the objective image quality scores, the scanning time of the ACS group is significantly lower than that of control group. The SNR and CNR of ACS group were significantly higher than those of NAVI group (SNR:3.63 ± 0.76 vs 3.04 ± 0.44, p < 0.001; CNR: 14.44 ± 4.53 vs 12.05 ± 3.32, p < 0.001). In addition, the subjective and objective measurement results of the two radiologists were in good agreement (ICC = 0.61-0.88). CONCLUSION: ACS technology has obvious advantages when applied to kidney MR imaging, which can realize ultra-fast MR imaging. The images can be acquired with a single breath-hold (17 s), which greatly shortens the scanning time. Moreover, the image quality is equal to or better than the conventional technology, which can meet the diagnostic requirements. Thus, it has obvious advantages in diagnosis for kidney disease patients with different tolerance levels for the clinical promotion.