Noninvasive Tracking of Every Individual in Unmarked Mouse Groups Using Multi-Camera Fusion and Deep Learning / 神经科学通报·英文版

Accurate and efficient methods for identifying and tracking each animal in a group are needed to study complex behaviors and social interactions. Traditional tracking methods (e.g., marking each animal with dye or surgically implanting microchips) can be invasive and may have an impact on the social behavior being measured. To overcome these shortcomings, video-based methods for tracking unmarked animals, such as fruit flies and zebrafish, have been developed. However, tracking individual mice in a group remains a challenging problem because of their flexible body and complicated interaction patterns. In this study, we report the development of a multi-object tracker for mice that uses the Faster region-based convolutional neural network (R-CNN) deep learning algorithm with geometric transformations in combination with multi-camera/multi-image fusion technology. The system successfully tracked every individual in groups of unmarked mice and was applied to investigate chasing behavior. The proposed system constitutes a step forward in the noninvasive tracking of individual mice engaged in social behavior.

Effect of nucleos(t)ide analog antiviral treatment on the clinical features and prognosis of patients with hepatitis B virus-related hepatocellular carcinoma / 中华传染病杂志

Objective:To analyze the effect of nucleos(t)ide analog (NAs) antiviral treatment on the clinical features and prognosis of patients with hepatitis B virus-related hepatocellular carcinoma (HBV-HCC).Methods:A retrospective analysis was performed on the data of 450 HBV-HCC patients first diagnosed and treated in the Third Hospital of Hebei Medical University from January 2015 to January 2021, including 193 patients in the continuous NAs treatment group and 257 patients in the NAs treatment after hepatocellular carcinoma (HCC) group. The baseline data of the two groups were balanced by propensity score matching. The relapse-free survival rate of HCC was estimated by Kaplan-Meier method, and the risk factors for HCC recurrence were analyzed by Cox proportional risk models. Spearman correlation analysis was used to explore the association between clinical features of HCC and hepatitis B virus (HBV) DNA load in patients receiving continuous NAs treatment.Results:Before matching, the proportions of liver cirrhosis, body mass index≥25.0 kg/m 2, single tumor, maximum tumor diameter ≤5 cm, Child-Pugh grade A, China liver cancer staging Ⅰ in the continuous NAs treatment group were 93.8%(181/193), 45.1%(87/193), 70.5%(136/193), 82.4%(159/193), 74.6%(144/193) and 74.6%(144/193), respectively. All of them were higher than those in the NAs treatment after HCC group (87.5%(225/257), 44.0%(113/257), 61.1%(157/257), 55.3%(142/257), 63.8%(164/257) and 56.0%(144/257), respectively). The proportions of drinking history and portal vein tumor thrombi in the continuous NAs treatment group were 12.4%(24/193) and 3.1%(6/193), respectively, which were lower than 33.9%(87/257) and 10.5%(27/257) in the NAs treatment after HCC group.The differences were all statistically significant ( χ2=4.86, 7.58, 4.27, 36.63, 8.15, 21.05, 27.21 and 8.88, respectively, all P<0.05). After matching, the median relapse-free survival time of the patients in the continuous NAs treatment group and the NAs treatment after HCC group were 388 days and 277 days, respectively. The five-year cumulative relapse-free survival rates were 50.0% and 37.5%, respectively, with statistically significant difference ( χ2=5.30, P=0.021). Multivariate analysis showed that no antiviral therapy before diagnosis of HCC, multiple tumors, maximum tumor diameter ≥5 cm and palliative treatment were independent risk factors for HBV-HCC recurrence (hazard ratio ( HR)=1.509, 1.491, 0.446 and 1.472, respectively, all P<0.05). After matching, the maximum tumor diameter ( r=0.175, P=0.042), incidence of portal vein tumor thrombi ( r=0.210, P=0.014) and recurrence of HBV-HCC ( r=0.178, P=0.038) in the continuous NAs treatment group were positively correlated with HBV DNA load. Conclusions:Early initiation of NAs antiviral treatment can improve the tumor characteristics when the disease progresses to HBV-HCC, and improve the relapse-free survival rate of HBV-HCC patients. No antiviral therapy before diagnosis of HCC, multiple tumors, maximum tumor diameter ≥5 cm and palliative treatment are independent risk factors for HBV-HCC recurrence.