Lung cancer is one of the tumors with the highest incidence rate and mortality rate in the world. It is also the malignant tumor with the fastest growing number of patients, which seriously threatens human life. How to improve the accuracy of diagnosis and treatment of lung cancer and the survival prognosis is particularly important. Machine learning is a multi-disciplinary interdisciplinary specialty, covering the knowledge of probability theory, statistics, approximate theory and complex algorithm. It uses computer as a tool and is committed to simulating human learning methods, and divides the existing content into knowledge structures to effectively improve learning efficiency and being able to integrate computer science and statistics into medical problems. Through the introduction of algorithm to absorb the input data, and the application of computer analysis to predict the output value within the acceptable accuracy range, identify the patterns and trends in the data, and finally learn from previous experience, the development of this technology brings a new direction for the diagnosis and treatment of lung cancer. This article will review the performance and application prospects of different types of machine learning algorithms in the clinical diagnosis and survival prognosis analysis of lung cancer.
ObjectiveTo prepare the aortic extracellular matrix (ECM) scaffold by using different methods to decellularize porcine ascending aorta and to comprehensively compare the efficiency of decellularization and the damage of ECM, evaluation of biomechanical property and biocompatibil ity. MethodsThirty specimens of fresh porcine ascending aorta were randomly divided into 6 groups (n=5). The porcine ascending aorta was decellularized by 5 different protocols in groups A-E: 0.1% trypsin/0.02% ethylenediamine tetraacetic acid (EDTA)/PBS was used in group A, 1%Triton X-100/0.02% EDTA/ distilled water in group B, 1% sodium deoxycholic acid/distilled water in group C, 0.5% sodium deoxycholic acid/0.5% sodium dodecyl sulfate/distilled water in group D, and 1% deoxycholic acid/distilled water in group E; and the porcine ascending aorta was not decellularized as control in group F. The ascending aorta scaffolds were investigated by gross examination, HE staining, DNA quantitative analysis, immunohistochemistry, and scanning electron microscopy were used to observe the efficiency of decellularization, microstructure of the ECM, the damage of collagen type Ⅰ and elastin, the structure of intimal surface, and biomechanical property. The 90 Sprague Dawley rats were randomly divided into 6 groups (n=15). Each scaffold was implanted in the abdominal muscles of rats respectively to evaluate the immunogenicity and biocompatibil ity. ResultsHE staining and quantitative analysis of DNA showed that the cells were completely removed only in groups A and D. The expression of collagen type Ⅰ in group A was significantly lower than that in the other 5 groups (P < 0.05), and serious damage of the basement membrane and decreased beomechanical property were observed. The maximum stress and tensile strength in group A was significantly lower than those in the other groups (P < 0.05), and elongation at break was significantly higher than that in the other groups (P < 0.05). The destruction of collagen type Ⅰ was significant (P < 0.05) in group D, but the basement membrane was integrity, the biomechanical properties were close to the natural blood vessels (group F) (P > 0.05). Implantation results showed that the scaffold of group D had superior immunogenicity and histocompatibility to the scaffold of the other groups. The inflammatory reaction was gentle and the number of the inflammatory cell infiltration was lower in group D than in other groups (P < 0.05). ConclusionIt is concludes that 0.5% sodium deoxycholic acid/0.5% sodium dodecyl sulfate/distilled water is more suitable for the decellularization of porcine aorta, by which the acquired ECM scaffold has the potential for constructing tissue engineered vessel.