To develop and validate a weighted predictive scoring system for identifying poor long-term functional outcomes in acute ischemic stroke (AIS) patients und

Background: In dynamic contrast-enhanced T1-weighted imaging (DCE-T1WI) of breast lesions, type III time–intensity curves (TICs) are associated with malignant lesions, and type I TICs are associated with benign lesions, but the association of type II curves with the status of breast lesions remains controversial. This study aimed to analyze the semi-quantitative parameters derived from DCE-T1WI in patients with type II TIC breast lesions and to develop a nomogram for the benign/malignant classification of lesions with type II TICs.Methods: Data of patients with type II TIC breast lesions were retrospectively collected. The following semi-quantitative parameters were collected: signal intensity of pre-contrast (SIpre), peak signal intensity (SIp), signal intensity of wash-in (SIwi), slope of peak (Sp), slope of wash-in (Swi), time to peak (Tp), time of wash-in (Twi), enhancement rate of peak (ERp), and enhancement rate of wash-in (ERwi). Univariable and multivariable analyses were performed to select useful clinical and DCE-T1WI features. Selected features were used for nomogram model development. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and area under the curve (AUC) were used for model performance evaluation.Results: Ninety-eight female patients with type II TIC breast lesions were included (53 with malignant lesions). After univariable and multivariable logistic regression analyses, only Tp showed an odds ratio of 0.95 (p = 0.014, 95% confidence interval: 0.93–0.97). A nomogram was constructed and included Swi, SIp, SIwi, SIpre, Tp, ERp, and Sp. The sensitivity, specificity, PPV, NPV, and accuracy of the nomogram were 0.827, 0.761, 0.795, 0.796, and 0.796, respectively. The AUC was 0.862.Conclusion: DCE-T1WI semi-quantitative parameters were different among benign and malignant lesions in patients with type II TIC lesions. Tp showed the most significant difference after a multivariable logistic regression analysis. The results suggest that DCE-T1WI semi-quantitative parameters can be used to predict malignant lesions in patients with type II TIC.

Background/Objectives: Neural compensation, in which healthy brain regions take over functions lost due to lesions, is a potential biomarker for functional recovery after stroke. However, previous neuroimaging studies often speculated on neural compensation simply based on greater measures in patients (compared to healthy controls) without demonstrating a more direct link between these measures and the functional recovery. Because taking over the function of a lesion region means taking on a similar role as that lesion region in its functional network, the present study attempted to explore neural compensation based on the similarity of functional connectivity (FC) patterns between a healthy regions and lesion regions. Methods: Seventeen stroke patients (13M4F, 63.2 ± 9.1 y.o.) underwent three resting-state functional MRI (rs-fMRI) sessions during rehabilitation. FC patterns of their lesion regions were derived by lesion network analysis; and these patterns were correlated with healthy FC patterns derived from each brain voxel of 51 healthy subjects (32M19F, 61.0 ± 14.3 y.o.) for the assessment of pattern similarity. Results: We identified five healthy regions showing decreasing FC similarity (29–54%, all corrected p < 0.05, effect size η²: 0.10–0.20) to the lesion network over time. These decreasing similarities were associated with increasing behavioral scores on activities of daily living (ADL, p < 0.001, η² = 0.90), suggesting greater neural compensation at early-stage post-stroke and reduced compensation toward the end of effective rehabilitation. Conclusions: Besides direct FC measures, the present results propose an alternative biomarker of neural compensation in functional recovery from stroke. For sensorimotor recoveries like ADL, this biomarker could be more sensitive than direct measures of lesion connectivity in the motor network.

Background: Currently, there is no fully automated tool available for evaluating the degree of cervical spinal stenosis. The aim of this study was to develop and validate the use of artificial intelligence (AI) algorithms for the assessment of cervical spinal stenosis. Methods: In this retrospective multi-center study, cervical spine magnetic resonance imaging (MRI) scans obtained from July 2020 to June 2023 were included. Studies of patients with spinal instrumentation or studies with suboptimal image quality were excluded. Sagittal T2-weighted images were used. The training data from the Fourth People’s Hospital of Shanghai (Hos. 1) and Shanghai Changzheng Hospital (Hos. 2) were annotated by two musculoskeletal (MSK) radiologists following Kang’s system as the standard reference. First, a convolutional neural network (CNN) was trained to detect the region of interest (ROI), with a second Transformer for classification. The performance of the deep learning (DL) model was assessed on an internal test set from Hos. 2 and an external test set from Shanghai Changhai Hospital (Hos. 3), and compared among six readers. Metrics such as detection precision, interrater agreement, sensitivity (SEN), and specificity (SPE) were calculated. Results: Overall, 795 patients were analyzed (mean age ± standard deviation, 55±14 years; 346 female), with 589 in the training (75%) and validation (25%) sets, 206 in the internal test set, and 95 in the external test set. Four tasks with different clinical application scenarios were trained, and their accuracy (ACC) ranged from 0.8993 to 0.9532. When using a Kang system score of ≥2 as a threshold for diagnosing central cervical canal stenosis in the internal test set, both the algorithm and six readers achieved similar areas under the receiver operating characteristic curve (AUCs) of 0.936 [95% confidence interval (CI): 0.916–0.955], with a SEN of 90.3% and SPE of 93.8%; the AUC of the DL model was 0.931 (95% CI: 0.917–0.946), with a SEN in the external test set of 100%, and a SPE of 86.3%. Correlation analysis comparing the DL method, the six readers, and MRI reports between the reference standard showed a moderate correlation, with R values ranging from 0.589 to 0.668. The DL model produced approximately the same upgrades (9.2%) and downgrades (5.1%) as the six readers. Conclusions: The DL model could fully automatically and reliably assess cervical canal stenosis using MRI scans.

The purpose of this study was to develop and validate a deep learning framework for simultaneous automated quantification of diffusion-weighted imaging-the Alberta Stroke Programme early CT score (DWI-ASPECTS) and infarct core volume in middle cerebral artery acute ischaemic stroke (MCA-AIS) and to evaluate its clinical utility for severity stratification in multi-centre settings. A cohort of 738 patients diagnosed with MCA-AIS from four centres was divided into a train set (n = 408), a validation set (n = 116), an internal test set (n = 60) and an external test set (n = 154). A 3D U-Net architecture was trained for simultaneous infarct segmentation and the ASPECTS region analysis. Model performance was compared against expert neuroradiologists using intraclass correlation coefficients and the Spearman correlation coefficient. Furthermore, we investigated the correlation between ASPECTS deduction frequency, ASPECTS score, core volume and the severity of MCA-AIS. The 3D U-Net model showed a high correlation with manual segmentation, achieving a Dice coefficient of 0.801 and a Spearman correlation coefficient of 0.988 for volume measurements in the external test set. In both the internal and external test sets, the automated ASPECTS by the deep learning (DL) model (Automated), manual ASPECTS by raters (Raters) and manual ASPECTS by raters on DWI images registered with the template (Raters_template) exhibited a strong correlation and excellent agreement. The cortical regions (M1–M6) were particularly relevant in patients classified into the moderate–severe group. The threshold values for the mild group and moderate–severe group on receiver operating characteristic curve analysis for DWI-ASPECTS and Core volume, were 6 and 27.86 mL, respectively. The DL model demonstrated comparable performance to neuroradiologists’ evaluation, potentially serving as an ancillary tool for physicians in making urgent clinical decisions. The severity of MCA-AIS was significantly associated with the specific ASPETCS regions and core volume, which may aid in identifying moderate–severe MCA-AIS.