Search

The aim of this study was to evaluate diagnostic performance of radiomics models of MRI in the detection of differentiation degree (DD) and lymph node metastases (LNM) of extrahepatic cholangiocarcinoma (ECC). We retrospectively enrolled 100 patients with ECC confirmed by pathology from January 2011 to December 2018. Three hundred radiomics features were extracted from each region of interest using MaZda software. Next, the radiomics model was developed by incorporating the optimal radiomics signatures and ADC values of tumors to predict DD (model A) and LNM (model B) of ECC, respectively, through the random forest algorithm. After which, the performance of the radiomics models were further evaluated. The model A showed better performance in both training and testing cohorts to discriminate high and medium-low differentiation groups of ECC, with an average AUC of 0.78 and 0.80, respectively. The model B also yielded the good average AUC of 0.80 and 0.90 to predict the LNM of ECC in training and testing cohorts. The radiomics models based on MRI performed well in predicting DD and LNM of ECC and have significant potential in clinical noninvasive diagnosis and in the prediction of ECC. [ABSTRACT FROM AUTHOR]

Background: Most cases of extrahepatic cholangiocarcinoma (ECC) show various degrees of hyperintensity on diffusion-weighted imaging (DWI) and hypointensity on apparent diffusion coefficient (ADC). However, the factors influencing ADC values in ECC have not yet been explored extensively. Therefore, this study explored the independent factors influencing ADC values in ECC.Methods: A total of 88 patients with ECC confirmed by surgical pathology were retrospectively assessed. All patients underwent abdominal magnetic resonance imaging (MRI) at 3.0 T and ADC values of the tumor were measured. The correlation between ADC values and multiple clinicopathological features in ECC was analyzed, and independent factors influencing the ADC values in ECC were explored further.Results: The ADC value of the tumor showed a significant difference in different perineural invasion group (p = 0.048), microvascular invasion group (p = 0.001), vascular endothelial growth factor expression group (p < 0.001), lymphatic status group (p = 0.003), and differentiation degree (DD) group (p < 0.001). However, there were no significant differences in different sex (p = 0.715), tumor location (p = 0.659), and degree of T stage (p = 0.879). Moreover, ADC value was negatively correlated with microvascular density (r = -0.725, p < 0.001) and lesion size (r = -0.244, p = 0.023). Nevertheless, there was no correlation between ADC value and patient age (r = 0.026, p = 0.812). Further regression analysis indicated that ADC value was independently associated with pathological DD of ECC (R2 = 0.678, p < 0.001) but not with other clinicopathological factors (p > 0.05).Conclusion: ADC value of ECC is independently correlated with pathological DD of ECC, indicating that ADC value is a potential imaging biomarker for predicting the degree of ECC malignancy. [ABSTRACT FROM AUTHOR]

The aim of this study is to develop and test radiomics models based on magnetic resonance imaging (MRI) to preoperatively and respectively predict the T stage, perineural invasion, and microvascular invasion of extrahepatic cholangiocarcinoma (eCCA) through a non-invasive approach. This research included 101 eCCA patients (29–83 years; 45 females and 56 males) between August 2011 and December 2019. Radiomics features were retrospectively extracted from T1-weighted imaging, T2-weighted imaging, diffusion-weighted imaging, and apparent diffusion coefficient map using MaZda software. The region of interest was manually delineated in the largest section on four MRI images as ground truth while keeping 1–2 mm margin to tumor border, respectively. Pretreatment, dimension reduction method, and classifiers were used to establish radiomics signatures for assessing three pathological characteristics of eCCA. Finally, independent training and testing datasets were used to assess radiomics signature performance based on receiver operating characteristic curve analysis, accuracy, precision, sensitivity, and specificity. This study extracted 1208 radiomics features from four MRI images of each patient. The best performing radiomics signatures for assessing the T stage, perineural invasion, and microvascular invasion were respectively produced by L1_normalization + linear discriminant analysis (LDA) + logistic regression, Box_Cox transformer + LDA + K-nearest neighbor, and L2_normalization + LDA + AdaBoost. The area under the curve values of the radiomics signatures for predicting the training and testing cohorts in each subgroup were respectively 1 and 0.962 (T stage), 1 and 1 (both perineural invasion and microvascular invasion). These proposed radiomic models based on MR images had powerful performance and high potential in predicting T stage, perineural, and microvascular invasion of eCCA. Prognostic study. [Display omitted] • MRI radiomics models were built to predict T stage, perineural, and microvascular invasion. • MRI-based radiomics model achieved AUC 1 and 0.962 (train and test) for predicting T stage. • The AUCs were 1 and 1 (train, test) in perineural and microvascular invasion models, respectively. [ABSTRACT FROM AUTHOR]