MACTFusion: Lightweight Cross Transformer for Adaptive Multimodal Medical Image Fusion.

Multimodal medical image fusion aims to integrate complementary information from different modalities of medical images. Deep learning methods, especially recent vision Transformers, have effectively improved image fusion performance. However, there are limitations for Transformers in image fusion, such as lacks of local feature extraction and cross-modal feature interaction, resulting in insufficient multimodal feature extraction and integration. In addition, the computational cost of Transformers is higher. To address these challenges, in this work, we develop an adaptive cross-modal fusion strategy for unsupervised multimodal medical image fusion. Specifically, we propose a novel lightweight cross Transformer based on cross multi-axis attention mechanism. It includes cross-window attention and cross-grid attention to mine and integrate both local and global interactions of multimodal features. The cross Transformer is further guided by a spatial adaptation fusion module, which allows the model to focus on the most relevant information. Moreover, we design a special feature extraction module that combines multiple gradient residual dense convolutional and Transformer layers to obtain local features from coarse to fine and capture global features. The proposed strategy significantly boosts the fusion performance while minimizing computational costs. Extensive experiments, including clinical brain tumor image fusion, have shown that our model can achieve clearer texture details and better visual quality than other state-of-the-art fusion methods.

IL-17 and TNF-ß: Predictive biomarkers for transition to psychosis in ultra-high risk individuals.

Background: Dysregulation of immunity, such as levels of inflammatory factors, has been regarded as a sign of schizophrenia. Changes in cytokine levels are not only described in the early onset of disease, but also observed in ultra-high risk (UHR) individuals. This study aimed to investigate the potential of cytokines as biomarkers for psychotic disorders and in individuals at UHR of developing a psychotic disorder in the future. Methods: The Luminex liquid chip technology was used to detect the concentrations of Interferon-gamma (INF-γ), Interleukin (IL)-2, Interleukin (IL)-4, Interleukin (IL)-6, Interleukin (IL)-17, Interleukin-1beta (IL-1ß), and Tumor Necrosis Factor-beta (TNF-ß) in the plasma of all subjects. Meanwhile, the plasma level of Tumor Necrosis Factor-Alpha (TNF-α) was measured with the enzyme-linked immunosorbent assay (ELISA) kits. Then, the levels of these cytokines were compared among patients with Drug-naïve first-episode schizophrenia (FES; n = 40), UHR population (UHR; n = 49), and healthy controls (HCs; n = 30). Baseline cytokine levels were compared among UHR individuals who later transitioned (UHR-T; n = 14), those who did not transition (UHR-NT; n = 35), and HCs (n = 30). Results: Our analysis results showed that IL-1ß levels were significantly higher in UHR group than HC group (p = 0.015). Meanwhile, TNF-α concentration was significantly increased in FES group compared with HC group (p = 0.027). IL-17 (p = 0.04) and TNF-ß (p = 0.008) levels were significantly higher in UHR-T group compared with UHR-NT group. Conclusion: In conclusion, our findings suggest that the immuno-inflammatory activation level is increased in the early stage of psychosis before psychotic conversion and the Drug-naïve FES. IL-1ß and TNF-α are the representatives of the specific biomarkers for UHR and FES, respectively. IL-17 and TNF-ß may be the potential selective predictive biomarkers for future transition in UHR individuals.

Abnormal neurobiochemical metabolites in the first- episode schizophrenia and clinical high-risk population. / 首发精神分裂症及临床高危人群脑神经生化代谢物异常.

OBJECTIVES: To explore the metabolite characteristics in medial prefrontal cortex (mPFC) by 1H magnetic resonance spectroscopy (1H-MRS) in the first-episode schizophrenia (FES) and clinical high-risk (CHR) people. METHODS: A total of 46 patients with the first-episode schizophrenia (FES), 49 people with clinical high risk (CHR), 61 people with genetic high risk (GHR), and 58 healthy controls (HC) were enrolled. The levels of N-acetylaspartylglutamate+N-acetylaspartate (tNAA), choline-containing compounds (Cho) and myo-inositol (MI), glutamate+glutamine (Glx) in medial prefrontal cortex were measured by single-voxel 1H-MRS. The clinical symptoms were evaluated in the FES group and the CHR group. Continuous performance test (CPT) were carried out to assess the visual and auditory accuracy and reaction time in the 4 groups. RESULTS: There were significant differences in Glx, tNAA, and MI concentrations among 4 groups (all P<0.05). Compared with the HC group, the FES group showed lower level of MI and Glx. The levels of Glx and tNAA in the CHR group were significantly lower than those in the GHR group (all P<0.05). The visual and auditory accuracies of CPT in the FES group were significantly lower than those in the HC group (P<0.05). In the FES group, Glx was negatively correlated with the reaction time of vision (r=-0.41, P=0.05). CONCLUSIONS: The decreased levels of MI and Glx in the FES patients suggest that there may be glial functional damage and glutamatergic transmitter dysfunction in the early stage of the disease. The compensatory increase of metabolites may be a protective factor for schizophrenia in the genetic individuals.