ABSTRACT
Efficient segmentation of Magnetic Resonance (MR) brain tumor images is of the utmost value for the diagnosis of tumor region. In recent years, advancement in the field of neural networks has been used to refine the segmentation performance of brain tumor sub-regions. The brain tumor segmentation has proven to be a complicated task even for neural networks, due to the small-scale tumor regions. These small-scale tumor regions are unable to be identified, the reason being their tiny size and the huge difference between area occupancy by different tumor classes. In previous state-of-the-art neural network models, the biggest problem was that the location information along with spatial details gets lost in deeper layers. To address these problems, we have proposed an encoder-decoder based model named BrainSeg-Net. The Feature Enhancer (FE) block is incorporated into the BrainSeg-Net architecture which extracts the middle-level features from low-level features from the shallow layers and shares them with the dense layers. This feature aggregation helps to achieve better performance of tumor identification. To address the problem associated with imbalance class, we have used a custom-designed loss function. For evaluation of BrainSeg-Net architecture, three benchmark datasets are utilized: BraTS2017, BraTS 2018, and BraTS 2019. Segmentation of Enhancing Core (EC), Whole Tumor (WT), and Tumor Core (TC) is carried out. The proposed architecture have exhibited good improvement when compared with existing baseline and state-of-the-art techniques. The MR brain tumor segmentation by BrainSeg-Net uses enhanced location and spatial features, which performs better than the existing plethora of brain MR image segmentation approaches.
ABSTRACT
BACKGROUND: The co-occurrence of alcohol use and antisocial behavior is well established, but different hypotheses exist regarding the direction of effects between the 2 behaviors. We used longitudinal data to examine the directional relationship between the 2 behaviors across adolescence. METHODS: A cross-lagged model was applied to longitudinal data from the Avon Longitudinal Study of Parents and Children. The sample used in the present study consisted of 4,354 females and 3,984 males. Alcohol use and antisocial behavior were measured with multiple items collected at 12, 13, 15, and 17 years of age. RESULTS: Both alcohol use and antisocial behavior were highly stable, as evidenced by highly significant autoregressive paths. Regarding the cross-lagged paths, neither behavior was predictive of the other during early adolescence (between ages 12 and 13). During mid-to late adolescence (from ages 13 to 17), antisocial behavior was predictive of subsequent alcohol use. Alcohol use was predictive of antisocial behavior in late adolescence (between ages 15 and 17), although this relationship was mainly driven by males and was not significant in the female subgroup. CONCLUSIONS: The result generally supported the direction from antisocial behavior to alcohol use, especially during mid- to late adolescence. However, there was also a suggestion that the direction of relationship between the 2 behaviors changes across adolescence. The results highlight the importance of considering developmental stages to understand the directional relationships between the 2 behaviors.
