RESUMO
Transformer-based methodologies in object detection have recently piqued considerable interest and have produced impressive results. DETR, an end-to-end object detection framework, ingeniously integrates the Transformer architecture, traditionally used in NLP, into computer vision for sequence-to-sequence prediction. Its enhanced variant, DINO, featuring improved denoising anchor boxes, has showcased remarkable performance on the COCO val2017 dataset. However, it often encounters challenges when applied to scenarios involving small object detection. Thus, we propose an innovative method for feature enhancement tailored to recursive prediction tasks, with a particular emphasis on augmenting small object detection performance. It primarily involves three enhancements: refining the backbone to favor feature maps that are more sensitive to small targets, incrementally augmenting the number of queries for small objects, and advancing the loss function for better performance. Specifically, The study incorporated the Switchable Atrous Convolution (SAC) mechanism, which features adaptable dilated convolutions, to increment the receptive field and thus elevate the innate feature extraction capabilities of the primary network concerning diminutive objects. Subsequently, a Recursive Small Object Prediction (RSP) module was designed to enhance the feature extraction of the prediction head for more precise network operations. Finally, the loss function was augmented with the Normalized Wasserstein Distance (NWD) metric, tailoring the loss function to suit small object detection better. The efficacy of the proposed model is empirically confirmed via testing on the VISDRONE2019 dataset. The comprehensive array of experiments indicates that our proposed model outperforms the extant DINO model in terms of average precision (AP) small object detection.
RESUMO
Renal cell carcinoma (RCC) is one of the most common malignant tumors of the urinary system. Although deregulation of the Notch signaling pathway is common in RCC and is involved in the tumorigenic process, the exact role of Notch3 and its underlying molecular mechanism in RCC, particularly in hypoxia, remain unknown. In the present study, RO4929097, a Notch3 inhibitor, was used to alter NICD3 expression. A Cell Counting Kit-8 assay, EdU incorporation assay, colony formation assay, flow cytometry and western blot analysis were used to investigate the effects of altered NICD3 expression on cell proliferation, cell cycle progression and HIF-2α protein expression. The results of western blot analysis showed that RO4929097 dose-dependently decreased the expression of Notch3 intracellular domain (NICD3) in 786-O and ACHN cells, which originate from clear cell RCC (ccRCC). The results of the Cell Counting Kit-8, EdU incorporation and colony formation assays demonstrated that downregulation of NICD3 significantly suppressed cell proliferation in both normoxia and hypoxia. In addition, flow cytometry and western blot analysis demonstrated that hypoxia (2% O2) promoted cell cycle progression in ccRCC cells with the increased expression of G1-S transition-associated proteins, namely cyclin-dependent kinase (CDK)4 and cyclin D1, while downregulation of NICD3 exerted negative effects on cell cycle progression, and the expression levels of CDK4 and cyclin D1. Furthermore, western blot analysis revealed that 2% O2-induced upregulated hypoxia-inducible factor-2α (HIF-2α) expression decreased following downregulation of NICD3 in 786-O and ACHN cells. Following transfection of the vector containing the NICD3 coding sequence, HIF-2α, CDK4, cyclin D1 and proliferating cell nuclear antigen expression, that were inhibited by RO4929097 in hypoxia, were rescued. Collectively, the results of the present study suggest that Notch3 is closely associated with the cell proliferation of ccRCC cells by regulating the cell cycle and HIF-2α.