BMC Medical Imaging最新文献

Background: Magnetic resonance imaging (MRI) radiomics has shown promise in glioma grading and isocitrate dehydrogenase (IDH) mutation prediction, but traditional whole-tumor approaches overlook intratumoral heterogeneity, limiting diagnostic accuracy and interpretability. This study aims to explore cellularity habitat-based MRI radiomics for precise grading and IDH mutation status prediction in adult-type diffuse glioma (ADG).

Methods: A total of 625 ADG patients were retrospectively collected. Whole-tumor volumes of interest (VOIs) were delineated on four conventional MRI sequences (T1WI, T2WI, T2-FLAIR, and CE-T1WI) and segmented into three cellularity habitats using apparent diffusion coefficient (ADC)-based K-means clustering: H₁ (low ADC), H₂ (medium ADC), and H₃ (high ADC). Radiomic features were extracted from individual and combined habitats, and predictive models were developed using a disentangled-learning-based multi-sequence fusion network (DMSFN). Performance was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy (ACC), sensitivity (SEN), and specificity (SPE).

Results: The optimal habitats for ADG grading (Grade 2 vs. Grade 3 + 4, Grade 2 + 3 vs. Grade 4) and IDH prediction were H_1 + 2, H_1 + 2, and H_2 + 3, respectively. Combining T1WI, CE-T1WI, and T2-FLAIR sequences yielded the highest AUCs of 0.9360, 0.9605, and 0.8721 in the training set, and 0.8070, 0.8236, and 0.8180 in the independent test set. Shapley Additive exPlanation (SHAP) analysis identified key radiomic features contributing to model predictions, with CE-T1WI features consistently demonstrating high discriminative power.

Conclusions: Integrating ADC-derived cellularity habitats with MRI radiomics significantly improves the accuracy and biological interpretability of ADG grading and IDH mutation status prediction, offering a robust, non-invasive approach for glioma characterization.

Trial registration: Retrospectively registered.

Background: The importance of right atrial (RA) function assessment in arrhythmogenic right ventricular cardiomyopathy (ARVC) is increasingly being recognized. MR-feature tracking (MR-FT) has emerged as a novel approach for quantifying atrial function. Therefore, we aimed to evaluate whether early RA dysfunction, even without RA dilation, can be identified in patients with ARVC using MR-FT.

Methods: Sixty-four patients with ARVC, of whom 47 were non-RA dilated and 17 were RA dilated patients, along with 41 healthy controls were included. RA reservoir, conduit, and booster strain (εs, εe, and εa) and peak positive, early negative, and late negative strain rate (SRs, SRe, and SRa) were measured using MR-FT. Right ventricular (RV) remodeling index was calculated as the ratio of RV to left ventricular end-diastolic volumes.

Results: Patients with ARVC (both RA Dilated and non-RA Dilated group) exhibited significantly lower RA εs, εe, εa, SRs, SRe, and SRa compared to healthy controls. RA dilation patients further reduced these parameters (all P < 0.001). Among RA strain parameters, SRe showed the highest diagnostic value for RV remodeling in patients with ARVC (AUC = 0.799, 95% CI: 0.683-0.915). A strong correlation was observed between RA strain, strain rate, and RA emptying fractions in ARVC patients (P < 0.001). Intra- and inter-observer reproducibility was excellent for RA strain measurements.

Conclusion: Patients with ARVC exhibit impaired RA reservoir, conduit, and booster function even with normal RA volumes. MR-FT may serve as a promising approach for detecting early RA dysfunction in this population.