nnSegNeXt: A 3D Convolutional Network for Brain Tissue Segmentation Based on Quality Evaluation.

Accurate and automated segmentation of brain tissue images can significantly streamline clinical diagnosis and analysis. Manual delineation needs improvement due to its laborious and repetitive nature, while automated techniques encounter challenges stemming from disparities in magnetic resonance imaging (MRI) acquisition equipment and accurate labeling. Existing software packages, such as FSL and FreeSurfer, do not fully replace ground truth segmentation, highlighting the need for an efficient segmentation tool. To better capture the essence of cerebral tissue, we introduce nnSegNeXt, an innovative segmentation architecture built upon the foundations of quality assessment. This pioneering framework effectively addresses the challenges posed by missing and inaccurate annotations. To enhance the model's discriminative capacity, we integrate a 3D convolutional attention mechanism instead of conventional convolutional blocks, enabling simultaneous encoding of contextual information through the incorporation of multiscale convolutional features. Our methodology was evaluated on four multi-site T1-weighted MRI datasets from diverse sources, magnetic field strengths, scanning parameters, temporal instances, and neuropsychiatric conditions. Empirical evaluations on the HCP, SALD, and IXI datasets reveal that nnSegNeXt surpasses the esteemed nnUNet, achieving Dice coefficients of 0.992, 0.987, and 0.989, respectively, and demonstrating superior generalizability across four distinct projects with Dice coefficients ranging from 0.967 to 0.983. Additionally, extensive ablation studies have been implemented to corroborate the effectiveness of the proposed model. These findings represent a notable advancement in brain tissue analysis, suggesting that nnSegNeXt holds the promise to significantly refine clinical workflows.

W-Net: A boundary-aware cascade network for robust and accurate optic disc segmentation.

Accurate optic disc (OD) segmentation has a great significance for computer-aided diagnosis of different types of eye diseases. Due to differences in image acquisition equipment and acquisition methods, the resolution, size, contrast, and clarity of images from different datasets show significant differences, resulting in poor generalization performance of deep learning networks. To solve this problem, this study proposes a multi-level segmentation network. The network includes data quality enhancement module (DQEM), coarse segmentation module (CSM), localization module (OLM), and fine segmentation stage module (FSM). In FSM, W-Net is proposed for the first time, and boundary loss is introduced in the loss function, which effectively improves the performance of OD segmentation. We generalized the model in the REFUGE test dataset, GAMMA dataset, Drishti-GS1 dataset, and IDRiD dataset, respectively. The results show that our method has the best OD segmentation performance in different datasets compared with state-of-the-art networks.

Time-dependent synergism of five-component mixture systems of aminoglycoside antibiotics to Vibrio qinghaiensis sp.-Q67 induced by a key component.

A large number of antibiotics are entering the aquatic environment accompanying human and animal excreta, which will threaten the survival of aquatic organisms and even human health. It has been found that binary mixtures of aminoglycoside (AG) exhibit additive action and can be evaluated well by a classical model, concentration addition (CA) in our past study. Therefore, to investigate the toxicity interaction within multi-component mixtures of AG antibiotics, five antibiotics, kanamycin sulfate (KAN), neomycin sulfate (NEO), tobramycin (TOB), streptomycin sulfate (STS), and gentamicin sulfate (GEN), were selected to construct five-component mixture systems by a uniform design ray method. The toxic effects (luminescence inhibition) of single antibiotic and five-antibiotic mixture systems towards a photobacterium Vibrio qinghaiensis sp.-Q67 (V. qinghaiensis) in different exposure time (0.25, 2, 4, 8, and 12 h) were determined by the time-dependent microplate toxicity analysis method. The concentration-effect data were fitted by a nonlinear least square method, toxicity interaction within mixture systems was analyzed by a CA model, and the interaction intensity was characterized by deviation from the CA model (dCA). Besides, the toxicity mechanism of five antibiotics and their five-component mixtures to V. qinghaiensis was analyzed by electron microscopy. The results show that toxicity of five antibiotics and their five-component mixture systems to V. qinghaiensis is time-dependent and has strong long-term toxicity. Different from binary AG antibiotic mixture systems, five-antibiotic mixture systems exhibit obviously time-dependent synergism. In addition, toxicity of the five-antibiotic mixtures can be 1.4 times higher than that of the mixtures without synergisms at the same concentration level. According to dCA, synergism intensity (dCA) curves of rays move slowly from the high concentration region to the medium or lower one and the maximum dCA values also increase, decrease, or first increase, then decrease with the lengthening of exposure time. The inhibition activity and synergism intensity of mixture rays have good correlation with the concentration ratios of STS, the key component for synergism. The cell morphology of V. qinghaiensis indicates the strong toxicity of five antibiotics and their mixture rays is not due to the destruction of cell structure, but the inhibition of the light-emitting activity of the photobacterium.