Learning-Based Near-Infrared Band Simulation with Applications on Large-Scale Landcover Classification.

Multispectral sensors are important instruments for Earth observation. In remote sensing applications, the near-infrared (NIR) band, together with the visible spectrum (RGB), provide abundant information about ground objects. However, the NIR band is typically not available on low-cost camera systems, which presents challenges for the vegetation extraction. To this end, this paper presents a conditional generative adversarial network (cGAN) method to simulate the NIR band from RGB bands of Sentinel-2 multispectral data. We adapt a robust loss function and a structural similarity index loss (SSIM) in addition to the GAN loss to improve the model performance. With 45,529 multi-seasonal test images across the globe, the simulated NIR band had a mean absolute error of 0.02378 and an SSIM of 89.98%. A rule-based landcover classification using the simulated normalized difference vegetation index (NDVI) achieved a Jaccard score of 89.50%. The evaluation metrics demonstrated the versatility of the learning-based paradigm in remote sensing applications. Our simulation approach is flexible and can be easily adapted to other spectral bands.

Expression of HMGB1 and RAGE in rat and human brains after traumatic brain injury.

BACKGROUND: Increasing evidence suggests that an inflammatory reaction contributes to the secondary brain injury that plays a critical role in the clinical outcome of patients with traumatic brain injury (TBI). Recently, high-mobility group box 1 (HMGB1) has been identified as a key cytokine in the inflammatory reaction and may represent a new target for the treatment of TBI. However, the expression of HMGB1 during this injury process has not yet been studied. METHODS: In this study, the levels of both HMGB1 and receptor for advanced glycation end products (RAGE) in the rat brain were analyzed by Western blot at different time points after TBI. Immunohistochemistry was also performed to examine the expression pattern of HMGB1 and RAGE in both the rat and the human brain after TBI. RESULTS: In the rat brain, HMGB1 levels significantly declined below the basal level at 6 hours after TBI and then gradually returned to the basal level 2 days later. RAGE expression increased 6 hours after TBI and reached its peak after 1 day; this level then slowly decreased but remained higher than the sham-injury group until 6 days after TBI. In both rat and human brains, HMGB1 either disappeared or was translocated from the nucleus to the cytoplasm at early stages after TBI and then was localized to the cytoplasm of phagocytic microglia at later stages. RAGE expression increased in the region surrounding the contused area after TBI in both rat and human brains. At later stages, RAGE was mainly expressed in microglia. CONCLUSION: HMGB1 is involved in both early and later stages after TBI. Targeting HMGB1 signaling may be a promising therapeutic approach for the treatment of TBI.

[Expression of FAPalpha and TGF-beta1 in sudden deaths due to acute myocardial ischemia].

OBJECTIVE: To explore the expression of fibroblast activation protein alpha (FAPalpha) and transforming growth factor-beta1 (TGF-beta1) in myocardial cytoplasm for the cases of sudden death due to acute myocardial ischemia. METHODS: The heart tissues of 47 cases were collected. All cases were divided into three groups: control group, acute myocardial infarction group and recurrent myocardial infarction group. FAPalpha and TGF-beta1 expressions were explored in myocardial cytoplasm by immunohistochemistry technology. The staining results were collected by image analysis system and then the positive area ratio and average optical density were detected. The positive signal differences were compared among the groups. RESULTS: Strong FAPalpha and TGF-beta1 expressions were detected in myocardial cytoplasm in both acute and recurrent myocardial infarction groups. The expression of FAPalpha was not detected in myocardial cytoplasm in control group and TGF-beta1 expression showed a weak positive result. FAPalpha and TGF-beta1 expressions showed the statistical difference (P < 0.05) in myocardial infarction (acute and recurrent) groups and control group. CONCLUSION: FAPalpha and TGF-beta1 can be the diagnostic markers for determing acute myocardial infarction.