Journal of Magnetic Resonance Imaging最新文献

Background: Tubular microdiscectomy (TMD) is a treatment for lumbar disc herniation (LDH). Although the combination of MRI and deep learning (DL) has shown promise, its application in evaluating postoperative outcomes in TMD has not been fully explored.

Purpose/hypothesis: To evaluate whether integrating preoperative dual-plane MRI-based DL features with clinical features can assess 1-year outcomes in TMD for LDH.

Study type: Retrospective.

Population/subjects: The study involved 548 patients who underwent TMD between January 2016 and January 2021. Training set (N = 305, mean age 51.85 ± 13.84 years, 56.4% male). Internal validation set (N = 131, mean age 51.85 ± 13.84 years, 54.2% male). External validation set (N = 112, mean age 51.54 ± 14.43 years, 50.9% male).

Field strength/sequence: 3 T MRI with sagittal and transverse T₂-weighted sequences (Fast Spin Echo).

Assessment: Ground truth labels were based on improvement rate in 1-year Japanese Orthopaedic Association (JOA) scores. Information on 42 preoperative clinical features was collected. The largest protrusions were identified from T₂ MRI by three clinicians and were used to train deep learning models (ResNet50, ResNet101, and ResNet152) to extract DL features. After feature selection, three models were built, namely, clinical, DL, and combined models.

Statistical tests: Chi-square or Fisher's exact tests was used for group comparisons. Quantitative differences were analyzed using the t-test or Mann-Whitney U test. P-values <0.05 were considered significant. Models were validated on internal and external datasets using metrics such as the area under the curve (AUC).

Results: The AUCs of the clinical models achieved 0.806 (internal) and 0.779 (external). ResNet152 performed best in three DL models, with AUCs of 0.858 (internal) and 0.834 (external). The combined model achieved AUCs of 0.889 (internal) and 0.857 (external).

Data conclusion: A model combining preoperative dual-plane MRI DL features and clinical features can assess 1-year outcomes of TMD for LDH.

Evidence level: 4 TECHNICAL EFFICACY: Stage 2.

Background: Although improvement of cognitive function after liver transplantation has been demonstrated in several neuropsychological studies, there is limited research on longitudinal changes in the cirrhotic patients' brain structure before and after transplantation.

Purpose: To investigate longitudinal changes of brain microstructure in cirrhotic patients using diffusion kurtosis imaging (DKI).

Study type: Prospective.

Subjects: A total of 153 cirrhosis patients, comprising 60 hepatic encephalopathy (HE) patients (16 females/44 males) and 93 no-HE patients (35 females/58 males), along with 93 healthy controls (HCs) (53 females/40 males) were enrolled. Subsequently, 58 recipients completed 1-month postoperative follow-up, 29 patients completed 1-, 3-months, and 17 patients completed 1-, 3-, 6-month follow-up.

Sequence: Spin-echo single-shot echo-planar sequence using a 3.0 T scanner.

Assessment: Diffusion kurtosis estimator software was used to estimate the DKI parameter maps by a MR imaging physicist (Y.-Y.C. with 12 years of experience).

Statistical tests: The diffusion metrics (eg, radial kurtosis [RK], mean kurtosis, fractional anisotropy, mean diffusivity) of the patients before transplantation were compared with those of the HCs using voxel-wise analysis of variance (ANOVA), along with t tests for post hoc analysis. Linear mixed-effects models were applied to the longitudinal data. We imposed a cluster level Family Wise Error (FWE) correction rate of P_FWE = 0.05 with voxel-wise cutoff of P = 0.001 together with a cluster-size cutoff of N ≥ 56, and generated smoothness estimates from the preprocessed data using the mixed-model autocorrelation function.

Results: The RK metrics of the patients decreased significantly in the anterior cingulate cortex (HE/no-HE < HC, ANOVA-F = 21.91). After transplantation, the RK of the pallidum showed a continuous upward trend (time effect T = 11.26); whereas the RK of the right postcentral gyrus showed a continuous downward trend (time effect T = -9.56). In addition, the RK in superior longitudinal fasciculus showed new-onset decrease after transplantation.

Data conclusion: Longitudinal changes in DKI metrics reveal the course of brain microstructural changes before and after transplantation in cirrhotic patients, potentially associated with cognitive alterations after surgery.

Level of evidence: 1 TECHNICAL EFFICACY: Stage 4.