RESUMEN
Brain tumors can be classified into many different types based on their shape, texture, and location. Accurate diagnosis of brain tumor types can help doctors to develop appropriate treatment plans to save patients' lives. Therefore, it is very crucial to improve the accuracy of this classification system for brain tumors to assist doctors in their treatment. We propose a deep feature fusion method based on convolutional neural networks to enhance the accuracy and robustness of brain tumor classification while mitigating the risk of over-fitting. Firstly, the extracted features of three pre-trained models including ResNet101, DenseNet121, and EfficientNetB0 are adjusted to ensure that the shape of extracted features for the three models is the same. Secondly, the three models are fine-tuned to extract features from brain tumor images. Thirdly, pairwise summation of the extracted features is carried out to achieve feature fusion. Finally, classification of brain tumors based on fused features is performed. The public datasets including Figshare (Dataset 1) and Kaggle (Dataset 2) are used to verify the reliability of the proposed method. Experimental results demonstrate that the fusion method of ResNet101 and DenseNet121 features achieves the best performance, which achieves classification accuracy of 99.18 and 97.24% in Figshare dataset and Kaggle dataset, respectively.
RESUMEN
Background and Objective: The blood-brain barrier (BBB) serves as a dynamic, selective shield, safeguarding the central nervous system (CNS) by separating the brain from circulating blood, preserving its microenvironment, and ensuring stability. However, in the presence of brain pathology, drug delivery across the BBB and blood-tumor barrier (BTB) becomes challenging, hindering effective treatments. Borneol exhibits promise in bidirectionally modulating the BBB under pathological conditions, suggesting at potential clinical applications for related diseases. Our primary goal in this review is to investigate borneol's potential clinical utility in bidirectionally regulating the BBB under pathological conditions. Methods: The PubMed database, CNKI (China National Knowledge Infrastructure), Wanfang Data were searched to retrieve articles on animal experiments and cell-based research published from January 1, 2003, to May 1, 2023, using the following medical subject headings (MeSH) terms: borneol, blood-brain barrier, ischemic stroke, cerebral gliomas, anti-inflammatory. The search was limited to articles published in English and Chinese. In total, 86 articles were deemed eligible for inclusion in this study. Key Content and Findings: The breakdown of the BBB is a key pathological process in ischemic stroke and cerebral glioma. When used alone, the lipophilic properties of borneol can reduce the permeability of the BBB and restore its normal function, thereby repairing brain damage and protecting brain tissue. Its specific protective effects may be related to inflammatory regulation mechanisms. The anti-inflammatory and protective effects of borneol can be used to improve and treat lesions caused by ischemic stroke and cerebral glioma. Furthermore, when combined with other drugs, borneol can accelerate the opening of the BBB, improve permeability through physiological processes, and enhance drug penetration and distribution in the brain without causing pathological damage to the brain. Conclusions: This review summarizes the mechanisms by which borneol regulates the BBB and BTB in ischemic stroke and cerebral glioma, and discusses the potential clinical applications of borneol in the treatment of these diseases. It is believed that in the future, as research methods are refined, more effective and targeted therapies for cerebral glioma and ischemic stroke will be explored related to the protective mechanism of the BBB under pathological conditions with borneol alone or in combination with other drugs.