RESUMO
The rapid development of deep neural networks has attracted significant attention in the infrared and visible image fusion field. However, most existing fusion models have many parameters and consume high computational and spatial resources. This paper proposes a fast and efficient recursive fusion neural network model to solve this complex problem that few people have touched. Specifically, we designed an attention module combining a traditional fusion knowledge prior with channel attention to extract modal-specific features efficiently. We used a shared attention layer to perform the early fusion of modal-shared features. Adopting parallel dilated convolution layers further reduces the network's parameter count. Our network is trained recursively, featuring minimal model parameters, and requires only a few training batches to achieve excellent fusion results. This significantly reduces the consumption of time, space, and computational resources during model training. We compared our method with nine SOTA methods on three public datasets, demonstrating our method's efficient training feature and good fusion results.
RESUMO
BACKGROUND: Astroglioma, one major form of brain tumors, has remained principally tough to handle for decades, due to the complexity of tumor pathology and the poor response to chemo- and radio-therapies. METHODS: Our previous study demonstrated that nifurtimox could regulate the signaling axis of AKT-GSK3ß in various tumor types including the astroglioma U251 cells. Intriguingly, earlier case studies suggested that nifurtimox could possibly permeate the blood brain barrier and arrest neuroblastoma in the brain. These observations jointly encouraged us to explore whether nifurtimox would hinder the growth of astroglioma in vivo. RESULTS: Our results exhibited that nifurtimox could competently hinder the development of astroglioma in the mouse brain as compared to temozolomide, the first line of drug for brain tumors. Meanwhile the surviving rate, as well as the body-weight was dramatically upregulated upon nifurtimox treatment, as compared to that of temozolomide. These findings offered nifurtimox as a better alternative drug in treating astroglioma in vivo. CONCLUSION: Persistently, the manipulation of the signaling axis of AKT-GSK3ß in astroglioma was found in line with earlier findings in neuroblastoma when treated with nifurtimox.