A deep-learning based system using multi-modal data for diagnosing gastric neoplasms in real-time (with video).

BACKGROUND: White light (WL) and weak-magnifying (WM) endoscopy are both important methods for diagnosing gastric neoplasms. This study constructed a deep-learning system named ENDOANGEL-MM (multi-modal) aimed at real-time diagnosing gastric neoplasms using WL and WM data. METHODS: WL and WM images of a same lesion were combined into image-pairs. A total of 4201 images, 7436 image-pairs, and 162 videos were used for model construction and validation. Models 1-5 including two single-modal models (WL, WM) and three multi-modal models (data fusion on task-level, feature-level, and input-level) were constructed. The models were tested on three levels including images, videos, and prospective patients. The best model was selected for constructing ENDOANGEL-MM. We compared the performance between the models and endoscopists and conducted a diagnostic study to explore the ENDOANGEL-MM's assistance ability. RESULTS: Model 4 (ENDOANGEL-MM) showed the best performance among five models. Model 2 performed better in single-modal models. The accuracy of ENDOANGEL-MM was higher than that of Model 2 in still images, real-time videos, and prospective patients. (86.54 vs 78.85%, P = 0.134; 90.00 vs 85.00%, P = 0.179; 93.55 vs 70.97%, P < 0.001). Model 2 and ENDOANGEL-MM outperformed endoscopists on WM data (85.00 vs 71.67%, P = 0.002) and multi-modal data (90.00 vs 76.17%, P = 0.002), significantly. With the assistance of ENDOANGEL-MM, the accuracy of non-experts improved significantly (85.75 vs 70.75%, P = 0.020), and performed no significant difference from experts (85.75 vs 89.00%, P = 0.159). CONCLUSIONS: The multi-modal model constructed by feature-level fusion showed the best performance. ENDOANGEL-MM identified gastric neoplasms with good accuracy and has a potential role in real-clinic.

Identification of Hub Genes Correlated with the Initiation and Development in Chronic Kidney Disease via Bioinformatics Analysis.

INTRODUCTION: Chronic kidney disease (CKD) is a major public health issue worldwide, which is characterized by irreversible loss of nephron and renal function. However, the molecular mechanism of CKD remains underexplored. METHODS: This study integrated three transcriptional profile datasets to investigate the molecular mechanism of CKD. The differentially expressed genes (DEGs) between Sham control (Con) and unilateral ureteral obstruction (UUO)-operated mice were analyzed by utilizing the limma package in R. The shared DEGs were analyzed by Gene Ontology and functional enrichment. Protein-protein interactions (PPIs) were constructed by utilizing the STRING database. Hub genes were analyzed by MCODE and Cytohubba. We further validated the gene expression by using the other dataset and mouse UUO model. RESULTS: A total of 315 shared DEGs between Con and UUO samples were identified. Gene function and KEGG pathway enrichment revealed that DEGs were mainly enriched in inflammatory response, immune system process, and chemokine signaling pathway. Two modules were clustered based on PPI network analysis. Module 1 contained 13 genes related to macrophage activation, migration, and chemotaxis. Ten hub genes were identified by PPI network analysis. Subsequently, the expression levels of hub genes were validated with the other dataset. Finally, these four validated hub genes were further confirmed by our UUO mice. Three validated hub genes, Gng2, Pf4, and Ccl9, showed significant response to UUO. CONCLUSION: Our study reveals the coordination of genes during UUO and provides a promising gene panel for CKD treatment. GNG2 and PF4 were identified as potential targets for developing CKD drugs.

ZeRGAN: Zero-Reference GAN for Fusion of Multispectral and Panchromatic Images.

In this article, we present a new pansharpening method, a zero-reference generative adversarial network (ZeRGAN), which fuses low spatial resolution multispectral (LR MS) and high spatial resolution panchromatic (PAN) images. In the proposed method, zero-reference indicates that it does not require paired reduced-scale images or unpaired full-scale images for training. To obtain accurate fusion results, we establish an adversarial game between a set of multiscale generators and their corresponding discriminators. Through multiscale generators, the fused high spatial resolution MS (HR MS) images are progressively produced from LR MS and PAN images, while the discriminators aim to distinguish the differences of spatial information between the HR MS images and the PAN images. In other words, the HR MS images are generated from LR MS and PAN images after the optimization of ZeRGAN. Furthermore, we construct a nonreference loss function, including an adversarial loss, spatial and spectral reconstruction losses, a spatial enhancement loss, and an average constancy loss. Through the minimization of the total loss, the spatial details in the HR MS images can be enhanced efficiently. Extensive experiments are implemented on datasets acquired by different satellites. The results demonstrate that the effectiveness of the proposed method compared with the state-of-the-art methods. The source code is publicly available at https://github.com/RSMagneto/ZeRGAN.

Salidroside attenuates dextran sulfate sodium-induced colitis in mice via SIRT1/FoxOs signaling pathway.

Salidroside (Sal), the active ingredient of Rhodiola rosea L, has various pharmacological activities, including antioxidant, anti-inflammatory and anti-tumor activities. Recently, studies have shown that oxidative stress and apoptosis are related to the pathogenesis of inflammatory bowel disease. Therefore, we evaluated the effects of Sal on oxidative stress and apoptosis in colitis mice through the SIRT1/FoxOs pathway. To induce the colitis model, mice continuously consumed water containing 3% DSS for 7 days; some mice were also treated with Sal and the SIRT1/FoxOs pathway blocker selisistat (Ex527). Changes in body weight, DAI, colon length and colon tissue histology as well as SOD, GSH-Px and CAT activities were measured. The expression of SIRT1, FoxO1, FoxO3a, FoxO4, caspase-3, cleaved-caspase-3, Bax and Bcl-2 in colorectal tissues was detected by RT-PCR and Western blotting. The study showed that Sal decreased the DAI score, weight loss, colon shortening and colon tissue damage in colitis mice. Sal inhibited oxidative stress by upregulating SOD, GSH-Px and CAT while suppressing colonic apoptosis by downregulating the expression of Bax, caspase-3, and cleaved-caspase-3 and upregulating the expression of Bcl-2. Sal also activated SIRT1/FoxOs signaling, which increased the expression of SIRT1, FoxO1, FoxO3a and FoxO4 in colon tissue. Furthermore, SIRT1/FoxOs pathway inhibition using Ex527 partially eliminated the effect of Sal on colitis mice. The study manifested that Sal may protect colitis mice by activating the SIRT1/FoxOs pathway, which is related to oxidative stress and apoptosis in colon tissues.

Diagnostic ability of blue laser imaging combined with magnifying endoscopy for early esophageal cancer.

BACKGROUND: Blue laser imaging (BLI) is a new image-enhanced endoscopy technique that utilizes a laser light source developed for narrow-band light observation. AIMS: To evaluate the value of BLI combined with magnifying endoscopy (M-BLI) for the diagnosis of early esophageal cancers (EECs). METHODS: This single-center prospective study analyzed 149 patients with focal esophageal lesions detected with white light endoscopy (WLE) at Renmin Hospital of Wuhan University between April 2015 and June 2017. In this study, patients were examined sequentially with narrow-band imaging combined with magnifying endoscopy (M-NBI), M-BLI and 1.25% Lugol's iodine chromoendoscopy. The concordance between endoscopic diagnosis and pathological diagnosis was evaluated using the agreement (kappa) test. The paired chi-square test was used to compare the concordance of M-NBI, M-BLI and Lugol's iodine chromoendoscopy. RESULTS: This study analyzed 153 lesions (four patients had two lesions each). The sensitivity, specificity, accuracy, concordance rates and kappa value of M-BLI were 95.2%, 91.9%, 85.7%, 92.8% and 0.891, respectively; those of M-NBI were 95.2%, 92.8%, 87.5%, 93.5% and 0.906; and those of Lugol's iodine chromoendoscopy were 95.2%, 94.6%, 91.3%, 94.8% and 0.936. CONCLUSION: M-BLI has a diagnostic profile similar to that of M-NBI and could improve the accuracy of EEC diagnosis.

Polydatin ameliorates dextran sulfate sodium-induced colitis by decreasing oxidative stress and apoptosis partially via Sonic hedgehog signaling pathway.

BACKGROUND: Inflammation, oxidative stress and epithelial barrier dysfunction have been implicated in inflammatory bowel disease (IBD) pathology. The targeted inhibition of these features may represent a promising therapeutic strategy for IBD. Polydatin is an effective natural antioxidant that possesses strong antioxidant and anti-apoptotic properties. Thus, we studied the protective effects of polydatin treatments on a mouse model of experimental colitis. METHODS: Acute colitis was experimentally induced by adding 3% dextran sulfate sodium (DSS) to the drinking water provided to mice for 7 days and by administering different doses of polydatin (15, 30, or 45 mg/kg) during the same period. Mice were also treated with the Sonic hedgehog (Shh) pathway inhibitor cyclopamine to estimate the efficacy of polydatin and Shh inhibitors on colitis. The disease activity index (DAI), colon length, histology, levels of oxidative and apoptotic mediators and levels of Shh pathway components were evaluated. RESULTS: The polydatin treatment significantly attenuated the DAI, colon shortening and histological damage. In addition, polydatin administration effectively decreased malondialdehyde (MDA) levels and increased the activities of the antioxidant enzymes superoxide dismutase (SOD) and glutathione peroxidase (GSH-Px). Polydatin also inhibited apoptosis in mice with colitis by downregulating the expression of the pro-apoptotic proteins Bax, caspase 3 and cleaved caspase 3 and increasing the expression of the anti-apoptotic protein Bcl-2. Furthermore, polydatin modulated Shh signaling pathway activation. After polydatin treatment, the main components of the Shh pathway, including Shh, Patched (Ptc), Smoothened (Smo), and glioblastoma-1 (Gli1), were upregulated at the mRNA and protein levels. Blockade of the Shh pathway using cyclopamine abolished the effects of polydatin on mice with colitis. CONCLUSION: Based on these observations, polydatin may suppress experimental colitis at least partially by regulating the Shh signaling pathway.