UNet-VGG16 with transfer learning for MRI-based brain tumor segmentation

Brain tumor detection and segmentation are the main issues in biomedical engineering research fields, and it is always challenging due to its heterogeneous shape and location in MRI. The quality of the MR images also plays an important role in providing a clear sight of the shape and boundary of the tumor. The clear shape and boundary of the tumor will increase the probability of safe medical surgery. Analysis of this different scope of image types requires refined computerized quantification and visualization tools. This paper employed deep learning to detect and segment brain tumor MRI images by combining the convolutional neural network (CNN) and fully convolutional network (FCN) methodology in serial. The fundamental finding is to detect and localize the tumor area with YOLO‐CNN and segment it with the FCN‐UNet architecture. This analysis provided automatic detection and segmentation as well as the location of the tumor. The segmentation using the UNet is run under four scenarios, and the best one is chosen by the minimum loss and maximum accuracy value. In this research, we used 277 images for training, 69 images for validation, and 14 images for testing. The validation is carried out by comparing the segmentation results with the medical ground truth to provide the correct classification ratio (CCR). This study succeeded in the detection of brain tumors and provided a clear area of the brain tumor with a high CCR of about 97%.

In binomial regression, a link function is used to join the linear predictor variables and the expectation of the response variable. This paper proposes a flexible link function from a new class of generalized logistic distribution, namely a flexible generalized logit (glogit) link. This approach considers both symmetric and asymmetric models, including the cases of lighter and heavier tails, as compared to standard logistic. The glogit is created from the inverse cumulative distribution function of the exponentiated-exponential logistic (EEL) distribution. Using a Bayesian framework, we conduct a simulation study to investigate the model performance compared to the most commonly used link functions, e.g., logit, probit, and complementary log–log. Furthermore, we compared the proposed model with several other asymmetric models using two previously published datasets. The results show that the proposed model outperforms the existing ones and provides flexibility fitting the experimental dataset. Another attractive aspect of the model are analytically tractable and can be easily implemented under a Bayesian approach.

Classical linear regression is inadequate when the response variable is the number of success in a sequence of experiments. However, the binomial regression is considered more suitable. Binomial regression can be analyzed through the Generalized Linear Model (GLM) with a specifics link functions. Some of link functions usually used in binomial regressions are logit, probit, and complimentary log-log (cloglog). Both logit and probit are symmetrical links functions, while cloglog is asymmetrical. This study aims to compare all three link functions and evaluate them by employing the Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) index. All three link function will be applied for binomial regression models using simulation and real data on school drop-out rates in East Java Indonesia. Based on the AIC and BIC index, it is evidenced that the cloglog gives the best performance than the logit and probit link function for the school drop-out rates model. Therefore, this case is considered appropriate using the asymmetrical assumptions.

Restructuring and Expanding Technology Acceptance Model Structural Equation Model and Bayesian Approach