Background: The diagnosis performance of B-mode ultrasound (US) for focal liver lesions (FLLs) is relatively limited. We aimed to develop a deep convolutional neural network of US (DCNN-US) for aiding radiologists in classification of malignant from benign FLLs. Materials and methods: This study was conducted in 13 hospitals and finally 2143 patients with 24,343 US images were enrolled. Patients who had non-cystic FLLs with pathological results were enrolled. The FLLs from 11 hospitals were randomly divided into training and internal validations (IV) cohorts with a 4:1 ratio for developing and evaluating DCNN-US. Diagnostic performance of the model was verified using external validation (EV) cohort from another two hospitals. The diagnosis value of DCNN-US was compared with that of contrast enhanced computed tomography (CT)/magnetic resonance image (MRI) and 236 radiologists, respectively. Findings: The AUC of Model LBC for FLLs was 0.924 (95% CI: 0.889À0.959) in the EV cohort. The diagnostic sensitivity and specificity of Model LBC were superior to 15-year skilled radiologists (86.5% vs 76.1%, p = 0.0084 and 85.5% vs 76.9%, p = 0.0051, respectively). Accuracy of Model LBC was comparable to that of contrast enhanced CT (both 84.7%) but inferior to contrast enhanced MRI (87.9%) for lesions detected by US. Interpretation: DCNN-US with high sensitivity and specificity in diagnosing FLLs shows its potential to assist less-experienced radiologists in improving their performance and lowering their dependence on sectional imaging in liver cancer diagnosis.

This study aimed to investigate the effect of the dual arterial blood supply method used in auxiliary liver transplantation on the regeneration of grafted and host liver. A total of 72 male Sprague-Dawley rats were randomly assigned to three experimental groups, namely the 68% hepatectomy group (group A), the 68% hepatectomy with dual arterial blood supply group (group B) and the auxiliary liver transplantation with dual arterial blood supply group (group C). Group C was further divided into the host liver subgroup (group Ca) and the transplanted liver subgroup (group Cb). Six animals from each group were sacrificed at 1, 2 and 7 days after surgery. The calculation of the liver regeneration rate (LRR) was based on measuring liver weight. Liver function was assessed by measuring serum alanine aminotransferase (ALT) levels. Immunohistochemistry was employed to detect the expression of proliferating cell nuclear antigen (PCNA). Apoptotic changes in the grafts and host livers were evaluated using TUNEL staining. The LRR in each group exhibited a tendency to increase over time. At each time point, the LRR of transplanted livers in group C exhibited no significant difference from that of host livers in group C (P>0.05). The ALT levels for each group exhibited a time-dependent decreasing tendency. The ALT level in group C was significantly higher compared to that in groups A and B at each time point (P<0.05). The expression of PCNA in transplanted and host livers in group C was significantly lower compared to that in groups A and B at the same time point (P<0.001). Although the number of apoptotic cells in each group varied at different time points, there was no statistically significant difference (P>0.05). In auxiliary liver transplantation with the dual arterial blood supply method, the capacity of the liver regeneration in the grafts was similar to that of the host livers. Therefore, this technique may reduce the potential risk of graft liver atrophy caused by functional competition.

No abstract

No abstract