BMC Medical Imaging最新文献

Background: Vessels encapsulating tumor clusters (VETC) serve as a crucial adverse prognostic indicator in hepatocellular carcinoma (HCC). This study aimed to develop and validate a Delta radiomics-based nomogram model on dynamic contrast-enhanced CT (DCE-CT) to predict VETC status and patient prognosis in HCC.

Methods: A cohort of 222 patients from two centers with HCC undergoing DCE-CT scans and CD34 immunochemical staining was enrolled. Each liver lesion was segmented on intratumoral and peritumoral regions in the arterial phase (AP) and portal vein phase (PP) CT images. A total of 10,128 (1,688*6) radiomics features, including absolute and relative delta radiomics features, were extracted. Using four machine-learning algorithms, the features were trained and optimized (training set), and validated (internal and external test sets) to classify VETC patterns. Multivariable logistic regression incorporating signature scores and clinical predictors generated the nomogram. Model performance was evaluated through area under the curves (AUC) analysis, calibration curves, and decision curve analysis (DCA). The Kaplan-Meier survival analysis was used to assess recurrence-free survival (RFS) in the VETC+ and VETC- patients.

Results: The logistic regression-based nomogram incorporating three radiomic signatures and two clinical factors showed powerful predictive ability in internal and external test sets with AUCs of 0.854 and 0.803, respectively. The calibration curves, DCA showed favorable predictive performance of the nomogram. Patients classified as high-risk by the nomogram exhibited significantly shorter RFS compared to low-risk counterparts (P < 0.001).

Conclusion: The developed nomogram demonstrated clinical translatability in preoperative VETC prediction and recurrence risk stratification, providing a potential imaging biomarker for guiding personalized therapeutic strategies in HCC management.

Objective: To develop a novel apparent diffusion coefficient (ADC) and signal intensity (SI) based model to quantify the subtle internal difference between tumor-adjacent (TAL) and -distant liver tissue (TDL) in T₃-staged resectable gallbladder carcinoma (GBC).

Methods: 65 consecutive patients with T₃-staged GBC invading liver undergoing preoperative MRI were retrospectively included, among which 54 from hospital 1 were randomly assigned to training (TC, n = 43) and internal validation cohorts (IVC, n = 11), while the remaining 11 from hospital 2 constituted external validation cohort (EVC, n = 11). Mean ADC and its standard deviation (SD) of TAL and TDL were measured on DWI at b-values of 0 and 600 s/mm², 0 and 800 s/mm², and 0 and 1000 s/mm². SIs of TAL, TDL and erector spinae (ES) on T₁WI, T₂WI, and arterial, portal-venous and delayed phases enhanced images were measured, and signal intensity ratios (SIRs) of TAL and TDL to ES were calculated. The t-test, Mann-Whitney U test and binary logistic regression analyses were conducted sequentially to determine independent index for differentiating TAL from TDL, and a model was constructed for the differentiation. Predictive value of model was assessed using the receiver operating characteristic (ROC) curve.

Results: In TC, SIRs on arterial phase (SIR_AP) and portal-venous phase (SIR_PP), SIs on portal-venous phase (SI_PP) and delayed phase (SI_DP), and SD at b-values of 0 and 1000 s/mm² (SD₁₀₀₀) were independent differentiating indexes with odds ratios of 0.008 (95% confidence interval [CI], 0.001-0.131), 0.132 (95%CI, 0.033-0.533), 1.002 (95%CI, 1.000-1.003), 0.998 (95%CI, 0.997-0.999), and 1.472 (95%CI, 0.006-355.856), respectively. ROC analysis showed that the model by integrating the previous indexes obtained excellent performance with areas under the ROC curve of 0.879, 0.934 and 0.909 in TC, IVC and EVC, respectively.

Conclusion: The novel model could be helpful for quantifying the subtle difference between TAL and TDL in T₃-staged GBC.