Prevalence, Molecular Characteristics and Virulence Identification of Bovine Parainfluenza Virus Type 3 in China.

Bovine parainfluenza virus type 3 (BPIV-3) is one of the major pathogens of the bovine respiratory disease complex (BRDC). BPIV-3 surveillance in China has been quite limited. In this study, we used PCR to test 302 cattle in China, and found that the positive rate was 4.64% and the herd-level positive rate was 13.16%. Six BPIV-3C strains were isolated and confirmed by electron microscopy, and their titers were determined. Three were sequenced by next-generation sequencing (NGS). Phylogenetic analyses showed that all isolates were most closely related to strain NX49 from Ningxia; the genetic diversity of genotype C strains was lower than strains of genotypes A and B; the HN, P, and N genes were more suitable for genotyping and evolutionary analyses of BPIV-3. Protein variation analyses showed that all isolates had mutations at amino acid sites in the proteins HN, M, F, and L. Genetic recombination analyses provided evidence for homologous recombination of BPIV-3 of bovine origin. The virulence experiment indicated that strain Hubei-03 had the highest pathogenicity and could be used as a vaccine candidate. These findings apply an important basis for the precise control of BPIV-3 in China.

Position-based anchor optimization for point supervised dense nuclei detection.

Nuclei detection is one of the most fundamental and challenging problems in histopathological image analysis, which can localize nuclei to provide effective computer-aided cancer diagnosis, treatment decision, and prognosis. The fully-supervised nuclei detector requires a large number of nuclei annotations on high-resolution digital images, which is time-consuming and needs human annotators with professional knowledge. In recent years, weakly-supervised learning has attracted significant attention in reducing the labeling burden. However, detecting dense nuclei of complex crowded distribution and diverse appearances remains a challenge. To solve this problem, we propose a novel point-supervised dense nuclei detection framework that introduces position-based anchor optimization to complete morphology-based pseudo-label supervision. Specifically, we first generate cellular-level pseudo labels (CPL) for the detection head via a morphology-based mechanism, which can help to build a baseline point-supervised detection network. Then, considering the crowded distribution of the dense nuclei, we propose a mechanism called Position-based Anchor-quality Estimation (PAE), which utilizes the positional deviation between an anchor and its corresponding point label to suppress low-quality detections far from each nucleus. Finally, to better handle the diverse appearances of nuclei, an Adaptive Anchor Selector (AAS) operation is proposed to automatically select positive and negative anchors according to morphological and positional statistical characteristics of nuclei. We conduct comprehensive experiments on two widely used benchmarks, MO and Lizard, using ResNet50 and PVTv2 as backbones. The results demonstrate that the proposed approach has superior capacity compared with other state-of-the-art methods. In particularly, in dense nuclei scenarios, our method can achieve 95.1% performance of the fully-supervised approach. The code is available at https://github.com/NucleiDet/DenseNucleiDet.