Focus on the inconsistency of the shape, location and size of brain glioma, a dual-channel 3-dimensional (3D) densely connected network is proposed to automatically segment brain glioma tumor on magnetic resonance images. Our method is based on a 3D convolutional neural network frame, and two convolution kernel sizes are adopted in each channel to extract multi-scale features in different scales of receptive fields. Then we construct two densely connected blocks in each pathway for feature learning and transmission. Finally, the concatenation of two pathway features was sent to classification layer to classify central region voxels to segment brain tumor automatically. We train and test our model on open brain tumor segmentation challenge dataset, and we also compared our results with other models. Experimental results show that our algorithm can segment different tumor lesions more accurately. It has important application value in the clinical diagnosis and treatment of brain tumor diseases.
Brain Neoplasms ; diagnostic imaging ; Glioma ; diagnostic imaging ; Humans ; Image Processing, Computer-Assisted ; Magnetic Resonance Imaging ; Neural Networks (Computer)

Objective:To explore the incidence and factors of the influence of preoperative related factors on postoperative orthopedic evaluation, through the evaluation of thoracic shape orthopedic evaluation of children pectus excavatum, during plate implantation after Nuss procedure.Methods:From April 2012 to April 2019, the clinical data were analyzed retrospectively for 159 hospitalized cases of Nuss procedure for pectus excavatum in Xi’an Children’s Hospital.The mean age was(6.8±3.4) years old(3.2-17.0 years old); males 124, females 35; Haller index 4.0±1.0(2.7-7.5); 6 cases(4%) were poor orthopedic evaluation with the thoracic shape, males 5, femal 1; 23 cases (14%) were average satisfied with the thoracic shape, males 16, femals 7; 130 cases (82%)were good orthopedic evaluation with the thoracic, males 103, femals 27. Follow-ups were conducted for at least 2 years, Retrospective analysis of the relationship between postoperative thoracic satisfaction and age, gender, Haller index, how the plates were placed during surgery and symmetry of funnel chest, t test and χ2 test were used for statistical analysis. Results:There were statistically significant differences between thoracic orthopedic evaluation after postoperative and classification of pectus excavatum ( P=0.001), and poor orthopedic evaluation after asymmetric pectus excavatum operationand ; There were no significant differences in gender, Haller index, surgical method and how the plates were placed during surgery( P>0.05). However, it can be seen from the mean and percentage that with the decrease of age, and the increase of Haller index, the orthopedic evaluation gradually becomes worse. Conclusion:According to our single-center study, asymmetric pectus excavatum is a factor for poor orthopedic evaluation during plate implantation after Nuss, especially for young children and children with larger Haller index.