Dynamic Contrast-Enhanced Ultrasound Radiomics for Hepatocellular Carcinoma Recurrence Prediction After Thermal Ablation.

PURPOSE: To develop a radiomics model based on dynamic contrast-enhanced ultrasound (CEUS) to predict early and late recurrence in patients with a single HCC lesion ≤ 5 cm in diameter after thermal ablation. PROCEDURES: We enrolled patients who underwent thermal ablation for HCC in our hospital from April 2004 to April 2017. Radiomics based on two branch convolution recurrent network was utilized to analyze preoperative dynamic CEUS image of HCC lesions to establish CEUS model, in comparison to the conventional ultrasound (US), clinical, and combined models. Clinical follow-up of HCC recurrence after ablation were taken as reference standard to evaluate the predicted performance of CEUS model and other models. RESULTS: We finally analyzed 318 patients (training cohort: test cohort = 255:63). The combined model showed better performance for early recurrence than CUES (in training cohort, AUC, 0.89 vs. 0.84, P < 0.001; in test cohort, AUC, 0.84 vs. 0.83, P = 0.272), US (P < 0.001), or clinical model (P < 0.001). For late recurrence prediction, the combined model showed the best performance than the CEUS (C-index, in training cohort, 0.77 vs. 0.76, P = 0.009; in test cohort, 0.77 vs. 0.68, P < 0.001), US (P < 0.001), or clinical model (P < 0.001). CONCLUSIONS: The CEUS model based on dynamic CEUS radiomics performed well in predicting early HCC recurrence after ablation. The combined model combining CEUS, US radiomics, and clinical factors could stratify the high risk of late recurrence.

A novel identification system combining diffusion kurtosis imaging with conventional magnetic resonance imaging to assess intestinal strictures in patients with Crohn's disease.

PURPOSE: To determine the utility of diffusion kurtosis imaging (DKI) for assessing bowel fibrosis and to establish a new magnetic resonance imaging (MRI)-based classification based on DKI and conventional MRI parameters for characterizing intestinal strictures in Crohn's disease (CD) using the histological evaluation of resected intestine samples as the reference standard. METHODS: Thirty-one patients with CD undergoing preoperative conventional MRI and diffusion-weighted imaging (DWI) (b values = 0-2000 s/mm2) were consecutively enrolled. We classified the mural T2-weighted signal intensity and arterial-phase enhancement patterns on conventional MRI. We also measured DWI-derived apparent diffusion coefficients (ADCs) and DKI-derived apparent diffusion for non-Gaussian distribution (Dapp) and apparent diffusional kurtosis (Kapp). A new MRI-based classification was established to characterize intestinal strictures in CD. Its performance was validated in nine additional patients with CD. RESULTS: Histological inflammation grades were significantly correlated to T2-weighted signal intensity (r = 0.477; P < 0.001) and ADC (r = - 0.226; P = 0.044). Histological fibrosis grades were moderately correlated to Kapp (r = 0.604, P < 0.001); they were also correlated to Dapp (r = - 0.491; P < 0.001) and ADC (r = - 0.270; P = 0.015). T2-weighted signal intensity could differentiate between no-to-mild and moderate-to-severe bowel inflammation (sensitivity, 0.970; specificity, 0.479). Kapp could differentiate between no-to-mild and moderate-to-severe bowel fibrosis (sensitivity, 0.959; specificity, 0.781). The agreement between the new MRI-based classification and the histological classification was moderate in the test (κ = 0.507; P < 0.001) and validation (κ = 0.530; P < 0.001) sets. CONCLUSIONS: DKI can be used to assess bowel fibrosis. The new MRI-based classification can help to distinguish between fibrotic and inflammatory intestinal strictures in patients with CD.