Intraprocedural contrast-enhanced ultrasound-CT/MR fusion imaging assessment in HCC thermal ablation to reduce local tumor progression: compared with routine contrast-enhanced ultrasound.

Purpose: To evaluate whether local tumor progression (LTP) would be further reduced when contrast-enhanced ultrasound (CEUS)-CT/MR fusion imaging was used as intraprocedural assessment method in hepatocellular carcinoma (HCC) thermal ablation compared with routine CEUS. Materials and methods: This prospective non-randomized study was conducted from December 2010 to July 2012. CEUS-CT/MR fusion imaging and routine CEUS were used for treatment response assessment in the ablation procedure of 146 HCCs and 122 HCCs, respectively. Supplementary ablations were performed immediately if necessary. The primary technique efficacy rate, LTP rate and overall survival (OS) rate were calculated. Results: For CEUS-CT/MR fusion imaging and routine CEUS, the technical success rate, technique efficacy rate and supplementary ablation rate were 86.3% (126/146) and 98.4% (120/122) (p = .000), 99.2% (125/126) and 94.2% (113/120) (p = .032), and 14.3% (18/126) and 4.2% (5/120) (p = .006), respectively. The cumulative LTP rate and OS rate were not significantly different between fusion imaging group and routine CEUS group. However, for lesions that were larger than 3 cm or close to major vessels (41 lesions in fusion imaging group and 44 lesions in routine CEUS group, who received transcatheter arterial chemoembolization before ablation), the cumulative LTP rate was significantly lower in fusion imaging group than in routine CEUS group (p = .032). Conclusion: Although intraprocedural CEUS-CT/MR fusion imaging has certain limitations in application, it might provide a potential more efficient method compared with routine CEUS in reducing LTP in HCC thermal ablation, especially for difficult ablation lesions.

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.

An Optimal Ablative Margin of Small Single Hepatocellular Carcinoma Treated with Image-Guided Percutaneous Thermal Ablation and Local Recurrence Prediction Base on the Ablative Margin: A Multicenter Study.

OBJECTIVE: To explore the best ablative margin (AM) for single hepatocellular carcinoma (HCC) patients with image-guided percutaneous thermal ablation (IPTA) based on MRI-MRI fusion imaging, and to develop and validate a local tumor progression (LTP) predictive model based on the recommended AM. METHODS: Between March 2014 and August 2019, 444 treatment-naïve patients with single HCC (diameter ≤3 cm) who underwent IPTA as first-line treatment from three hospitals were included, which were randomly divided into training (n= 296) and validation (n = 148) cohorts. We measured the ablative margin (AM) by MRI-MRI fusion imaging based on pre-ablation and post-ablation images. Then, we followed up their LPT and verified the optimal AM. Risk factors related to LTP were explored through Cox regression models, the nomogram was developed to predict the LTP risk base on the risk factors, and subsequently validated. The predictive performance and discrimination were assessed and compared with conventional indices. RESULTS: The median follow-up was 19.9 months (95% CI 18.0-21.8) for the entire cohort. The results revealed that the tumor size (HR: 2.16; 95% CI 1.25-3.72; P = 0.003) and AM (HR: 0.72; 95% CI, 0.61-0.85; P < 0.001) were independent prognostic factors for LTP. The AM had a pronounced nonlinear impact on LTP, and a cut-off value of 5-mm was optimal. We developed and validated an LTP predictive model based on the linear tumor size and nonlinear AM. The model showed good predictive accuracy and discrimination (training set, concordance index [C-index] of 0.751; validation set, C-index of 0.756) and outperformed other conventional indices. CONCLUSION: The 5-mm AM is recommended for the best IPTA candidates with single HCC (diameter ≤3 cm). We provided an LTP predictive model that exhibited adequate performance for individualized prediction and risk stratification.

A promising approach for screening pulmonary hypertension based on frontal chest radiographs using deep learning: A retrospective study.

BACKGROUND: To date, the missed diagnosis rate of pulmonary hypertension (PH) was high, and there has been limited development of a rapid, simple, and effective way to screen the disease. The purpose of this study is to develop a deep learning approach to achieve rapid detection of possible abnormalities in chest radiographs suggesting PH for screening patients suspected of PH. METHODS: We retrospectively collected frontal chest radiographs and the pulmonary artery systolic pressure (PASP) value measured by Doppler transthoracic echocardiography from 762 patients (357 healthy controls and 405 with PH) from three institutes in China from January 2013 to May 2019. The wohle sample comprised 762 images (641 for training, 80 for internal test, and 41 for external test). We firstly performed a 8-fold cross-validation on the 641 images selected for training (561 for pre-training, 80 for validation), then decided to tune learning rate to 0.0008 according to the best score on validation data. Finally, we used all the pre-training and validation data (561+80 = 641) to train our models (Resnet50, Xception, and Inception V3), evaluated them on internal and external test dataset to classify the images as having manifestations of PH or healthy according to the area under the receiver operating characteristic curve (AUC/ROC). After that, the three deep learning models were further used for prediction of PASP using regression algorithm. Moreover, we invited an experienced chest radiologist to classify the images in the test dataset as having PH or not, and compared the prediction accuracy performed by deep learing models with that of manual classification. RESULTS: The AUC performed by the best model (Inception V3) achieved 0.970 in the internal test, and slightly declined in the external test (0.967) when using deep learning algorithms to classify PH from normal based on chest X-rays. The mean absolute error (MAE) of the best model for prediction of PASP value was smaller in the internal test (7.45) compared to 9.95 in the external test. Manual classification of PH based on chest X-rays showed much lower AUCs compared to that performed by deep learning models both in the internal and external test. CONCLUSIONS: The present study used deep learning algorithms to classify abnormalities suggesting PH in chest radiographs with high accuracy and good generalizability. Once tested prospectively in clinical settings, the technology could provide a non-invasive and easy-to-use method to screen patients suspected of having PH.