Background: The MRI imaging traits of pediatric posterior cranial fossa neoplasms overlap highly, leading to difficulties in preoperative diagnosis. Their treatment strategies differ significantly, and traditional deep learning models have limitations in multi - sequence MRI fusion and clinical interpretability, so new solutions are urgently needed. Objectives: This study aims to develop a 2.5D multi - sequence MRI deep learning framework (ResSwinT) that integrates Residual Network and Swin Transformer, to achieve automatic classification of three main Pediatric posterior fossa tumors—Pilocytic astrocytoma (PA), Medulloblastoma (MB), and Ependymoma (EP), and enhance the interpretability of the model through the SHAP method, so as to provide a more reliable auxiliary decision-making basis for clinical practice. Methods: This study retrospectively collected 309 pediatric patients confirmed by pathology, including 109 PA, 130 MB and 70 EP. The MRI data of these patients included five sequences: T1WI, T1C, T2WI,FLAIR, and ADC. After preprocessing steps such as N4 bias field correction, resampling, sequence registration, and intensity normalization, samples were constructed using a 2.5D image construction strategy, and the ResSwinT model is designed. Its performance was compared with seven deep learning models such as Residual Network 18 and VGG16, and SHAP analysis was used to analyze trait contributions. Results: The proposed ResSwinT model outperforms existing commonly used deep learning models in all classification tasks, particularly showing outstanding performance in terms of area under the curve(AUC) and overall accuracy(ACC). For the PA vs Non-PA task: ACC 89.5%, AUC 0.975; for the MB vs Non-MB task: ACC 93.7%, AUC 0.978; for the EP vs Non-EP task: Acc 87.5%, AUC 0.937. SHapley Additive exPlanations(SHAP) analysis shows that the model pays high attention to the gross tumor volume and its surrounding structures, and its decision-making basis is highly consistent with key imaging biomarkers, verifying the interpretability and clinical relevance of the model. Conclusions: ResSwinT achieves high-precision classification of pediatric posterior fossa tumor through 2.5D multi-sequence fusion and cross-attention mechanism. SHAP attribution analysis reveals the biological basis of the model’s decision-making, providing clinicians with an interpretable AI-assisted diagnostic tool, and is expected to optimize individualized treatment strategies.

To explore the functionally disordered regions and the directed effective-connectivity relationships among them in Internet Gaming Disorder (IGD), we adopted a meta-analysis-based Dynamic Causal Modeling approach. We first performed a meta-analysis of existing rs-fMRI literature using Anisotropic Effect Size Signature Differential Mapping (AES-SDM) to localize the consistent regions with functional changes, which were then defined as regions of interest (ROIs). Next, we collected resting-state fMRI data and IGD-related scale scores from 54 IGD patients and 46 healthy controls, extracted the neuronal time series (BOLD time series) and input them into spectral Dynamic Causal Modeling (spDCM), and characterized between-group changes in effective connectivity (EC) between the ROIs through Parametric Empirical Bayes (PEB) analysis. In the IGD group, SFGdor_R showed reduced inhibitory effective connectivity with IFGopercular_L, IFGorb_L, and INS_R, and IFGorb_L also exhibited attenuated self-inhibition; in addition, an exploratory internally validated prediction analysis suggested that the IFGorb_L self-connection was associated with IAT severity. These findings indicate altered frontal effective-connectivity patterns consistent with reduced top-down regulatory signaling, rather than definitive evidence of a causal biological mechanism. The internally validated prediction of IAT severity was exploratory, explained a modest proportion of variance, and requires confirmation in larger longitudinal studies with external validation.

Background: Accurate preoperative grading of pediatric brain tumors is crucial for formulating individualized treatment plans. Traditional methods rely on subjective experience, while existing deep learning models have limitations in capturing long-distance dependencies and local details. This study aims to develop and validate an innovative 3D hybrid deep learning model (3D C-Vit) for pediatric brain tumor grading and analyze its performance and interpretability. Methods: This retrospective study included 340 cases of pediatric brain tumors (143 low-grade cases and 197 high-grade cases). Tumor regions were independently annotated by two senior radiologists with consistency achieved. The data were divided into training, validation, and test sets in a ratio of 70:15:15. The model input included five MRI sequences: CE-T1WI, T1WI, T2WI, FLAIR, and ADC. The proposed 3D C-Vit model integrates the Channel Attention-Enhanced Feature Fusion (CAEFF) module, Multi-Scale Feature Extraction (MSFE) module, and Multi-Head Self-Attention (MHSA) mechanism. Model performance was evaluated using AUC, accuracy (ACC), precision, recall, and F1-score. Chi-square test and LASSO regression were used for feature selection and interpretability analysis. Results: The 3D C-Vit model performed optimally on the test set: AUC was 91.36%, ACC was 86.53%, and F1-score was 89.29. Ablation experiments confirmed that CAEFF, MSFE, and MHSA modules increased ACC by 6.92%, 11.67%, and 1.64%, respectively, and AUC by 6.79%, 11.14%, and 1.66%, respectively. Among the radiomics models, LASSO regression screened out 59 key features. The 3D C-Vit model was significantly superior to the clinical model (ACC 69.23%, AUC 79.09%) and the best radiomics models (SVM, ACC 77.55%, AUC 86.14%) in all assessment metrics. Conclusion: The 3D C-Vit model proposed in this study can effectively and automatically grade pediatric brain tumor, and its performance significantly surpasses traditional clinical methods and existing radiomics models. The model combines the local feature extraction capability of CNN with the global modeling advantage of Transformer and effectively improves the grading accuracy through the innovative CAEFF and MSFE modules. Its high accuracy and interpretability provide clinicians with a reliable preoperative tumor grading tool, which is helpful for quickly formulating precise individualized treatment plans.

Objective: To investigate the MRI features of different pathological types in adult and juvenile patients with craniopharyngioma. Materials and methods: The preoperative MRI images of 68 patients with pathologically confirmed craniopharyngioma were retrospectively analyzed. The tumor location, imaging findings and surrounding tissue involvement were determined, and the tumor volume was measured. The differences of these imaging indicators and pathological types between 48 adult and 20 juvenile groups were compared. Results: Grouped by age: The proportions of adamantinomatous craniopharyngioma (ACP) in the juvenile group and adult group were 85.0% and 56.3%, respectively, with a significant difference (P = 0.024). The predilection sites of craniopharyngioma differed between the juvenile and adult groups. Tumors in the juvenile group were most frequently located in the intrasellar or suprasellar region (80%), whereas those in the adult group were predominantly suprasellar (60.4%), with a significant difference (P<0.001). The incidence of tumor calcification was 55.0% in the juvenile group and 29.1% in the adult group, with a significant difference (P = 0.044). Grouped by pathological subtype: The mean ages at onset were 27 years for ACP and 43 years for SPCP, with a significant difference (P<0.001). The incidence of cystic degeneration was 95.5% in ACP and 83.3% in SPCP, with a significant difference (P = 0.037). Fluid-fluid levels or sediment were present in 20.5% of ACP, but absent in all SPCP, with a significant difference (P = 0.022). Patients in the non-third ventricular floor invasion group were younger and had a wider age range than those in the third ventricular floor invasion group(P = 0.025). Conclusion: There is a close correlation between age at onset, pathological subtype, and MRI features of craniopharyngiomas. ACP is more common in juvenile patients, with a higher tendency toward intrasellar/suprasellar location, calcification, and cystic degeneration. In adult patients, lesions are predominantly suprasellar and more frequently accompanied by pituitary involvement. ACP show a higher cystic degeneration rate with characteristic fluid-fluid levels or sediment, which can be used for preoperative pathological differentiation. Meanwhile, invasion of the floor of the third ventricle is more commonly seen in older patients, suggesting that age may assist in evaluating the invasive growth pattern of craniopharyngiomas.