RESUMEN
In the realm of marine environmental engineering, the swift and accurate detection of underwater targets is of considerable significance. Recently, methods based on Convolutional Neural Networks (CNN) have been applied to enhance the detection of such targets. However, deep neural networks usually require a large number of parameters, resulting in slow processing speed. Meanwhile, existing methods present challenges in accurate detection when facing small and densely arranged underwater targets. To address these issues, we propose a new neural network model, YOLOv8-LA, for improving the detection performance of underwater targets. First, we design a Lightweight Efficient Partial Convolution (LEPC) module to optimize spatial feature extraction by selectively processing input channels to improve efficiency and significantly reduce redundant computation and storage requirements. Second, we developed the AP-FasterNet architecture for small targets that are commonly found in underwater datasets. By integrating depth-separable convolutions with different expansion rates into FasterNet, AP-FasterNet enhances the model's ability to capture detailed features of small targets. Finally, we integrate the lightweight and efficient content-aware reorganization (CARAFE) up-sampling operation into YOLOv8 to enhance the model performance by aggregating contextual information over a large perceptual field and mitigating information loss during up-sampling.Evaluation results on the URPC2021 dataset show that the YOLOv8-LA model achieves 84.7% mean accuracy (mAP) on a single Nvidia GeForce RTX 3090 and operates at 189.3 frames per second (FPS), demonstrating that it outperforms existing state-of-the-art methods in terms of performance. This result demonstrates the model's ability to ensure high detection accuracy while maintaining real-time processing capabilities.
RESUMEN
BACKGROUND: Bladder cancer (BC), a prevalent malignancy in the urinary system, often poses challenges for effective treatment. Immunotherapy, harnessing the immune system, has exhibited promise in early-stage clinical trials. Mucosal associated invariant T (MAIT) cells, a subset of immune cells implicated in various diseases, including certain cancer, have yet to be explored in BC patients. We aimed to investigate the quantity, function, and anti-tumor effects of MAIT cells in BC patients. METHODS: A total of 75 newly diagnosed BC patients and 183 healthy volunteers were included. Blood samples were collected and analyzed to evaluate the quantity and function of MAIT cells. Surgical resection provided BC tissues for further analysis, and the clinical features of BC tumors were collected and their relationship with MAIT cells was explored. RESULTS: MAIT cells were identified in both healthy individuals and BC patients. The proportion of MAIT cells in the peripheral blood of BC patients did not significantly differ from that of healthy controls. However, the study revealed a correlation between the proportion of IFN-γ producing MAIT cells and tumor number and invasion in BC patients. Furthermore, MAIT cells exhibited cytotoxic effects on BC cells in vitro and in vivo. CONCLUSIONS: This study sheds light on the role of MAIT cells in BC. While the quantity of MAIT cells showed no significant change in BC patients, their functional attributes and association with tumor characteristics suggest their potential as an immunotherapy target in BC treatment.