Search

Currently, complex scene classification strategies are limited to high-definition image scene sets, and low-quality scene sets are overlooked. Although a few studies have focused on artificially noisy images or specific image sets, none have involved actual low-resolution scene images. Therefore, designing classification models around practicality is of paramount importance. To solve the above problems, this paper proposes a two-stage classification optimization algorithm model based on MPSO, thus achieving high-precision classification of low-quality scene images. Firstly, to verify the rationality of the proposed model, three groups of internationally recognized scene datasets were used to conduct comparative experiments with the proposed model and 21 existing methods. It was found that the proposed model performs better, especially in the 15-scene dataset, with 1.54% higher accuracy than the best existing method ResNet-ELM. Secondly, to prove the necessity of the pre-reconstruction stage of the proposed model, the same classification architecture was used to conduct comparative experiments between the proposed reconstruction method and six existing preprocessing methods on the seven self-built low-quality news scene frames. The results show that the proposed model has a higher improvement rate for outdoor scenes. Finally, to test the application potential of the proposed model in outdoor environments, an adaptive test experiment was conducted on the two self-built scene sets affected by lighting and weather. The results indicate that the proposed model is suitable for weather-affected scene classification, with an average accuracy improvement of 1.42%. [ABSTRACT FROM AUTHOR]

Background & Aims: Nearly 20% of the global cancer burden can be linked to infectious agents. Fusobacterium nucleatum promotes tumor formation by epithelial cells via unclear mechanisms. We aimed to identify microRNAs (miRNAs) induced by F nucleatum and evaluate their ability to promote colorectal carcinogenesis in mice., Methods: Colorectal cancer (CRC) cell lines were incubated with F nucleatum or control reagents and analyzed in proliferation and would healing assays. HCT116, HT29, LoVo, and SW480 CRC cell lines were incubated with F nucleatum or phosphate-buffered saline (PBS [control]) and analyzed for miRNA expression patterns and in chromatin immunoprecipitation assays. Cells were incubated with miRNAs mimics, control sequences, or small interfering RNAs; expression of reporter constructs was measured in luciferase assays. CRC cells were incubated with F nucleatum or PBS and injected into BALB/C nude mice; growth of xenograft tumors was measured. C57BL adenomatous polyposis coli min/+ , C57BL miR21a -/- , and C57BL mice with full-length miR21a (controls) were given F nucleatum by gavage; some mice were given azoxymethane and dextran sodium sulfate to induce colitis and colon tumors. Intestinal tissues were collected and tumors were counted. Serum samples from mice were analyzed for cytokine levels by enzyme-linked immunosorbent assay. We performed in situ hybridization analyses to detect enrichment of F nucleatum in CRC cells. Fusobacterium nucleatum DNA in 90 tumor and matched nontumor tissues from patients in China were explored for the expression correlation analysis; levels in 125 tumor tissues from patients in Japan were compared with their survival times., Results: Fusobacterium nucleatum increased proliferation and invasive activities of CRC cell lines compared with control cells. CRC cell lines infected with F nucleatum formed larger tumors, more rapidly, in nude mice than uninfected cells. Adenomatous polyposis coli min/+ mice gavaged with F nucleatum developed significantly more colorectal tumors than mice given PBS and had shorter survival times. We found several inflammatory factors to be significantly increased in serum from mice given F nucleatum (interleukin 17F, interleukin 21, and interleukin 22, and MIP3A). We found 50 miRNAs to be significantly up-regulated and 52 miRNAs to be significantly down-regulated in CRCs incubated with F nucleatum vs PBS; levels of miR21 increased by the greatest amount (>4-fold). Inhibitors of miR21 prevented F nucleatum from inducing cell proliferation and invasion in culture. miR21a -/- mice had a later appearance of fecal blood and diarrhea after administration of azoxymethane and dextran sodium sulfate, and had longer survival times compared with control mice. The colorectum of miR21a -/- mice had fewer tumors, of smaller size, and the miR21a -/- mice survived longer than control mice. We found RASA1, which encodes an RAS GTPase, to be one of the target genes consistently down-regulated in cells that overexpressed miR21 and up-regulated in cells exposed to miR21 inhibitors. Infection of cells with F nucleatum increased expression of miR21 by activating Toll-like receptor 4 signaling to MYD88, leading to activation of the nuclear factor-κB. Levels of F nucleatum DNA and miR21 were increased in tumor tissues (and even more so in advanced tumor tissues) compared with non-tumor colon tissues from patients. Patients whose tumors had high amounts of F nucleatum DNA and miR21 had shorter survival times than patients whose tumors had lower amounts., Conclusions: We found infection of CRC cells with F nucleatum to increase their proliferation, invasive activity, and ability to form xenograft tumors in mice. Fusobacterium nucleatum activates Toll-like receptor 4 signaling to MYD88, leading to activation of the nuclear factor-κB and increased expression of miR21; this miRNA reduces levels of the RAS GTPase RASA1. Patients with both high amount of tissue F nucleatum DNA and miR21 demonstrated a higher risk for poor outcomes., (Copyright © 2017 AGA Institute. Published by Elsevier Inc. All rights reserved.)

Zinc-finger protein X-linked (ZFX) has been demonstrated to play an important role in the development of human malignancies. However, its prognostic significance in cancer patients remains unclear and less is known about its role in colorectal cancer (CRC). In this study, we found that the expression of ZFX in CRC tissues was significantly higher than that in corresponding normal tissues by quantitative real-time polymerase chain reaction and Western blot. Using immunohistochemistry, we explored the associations between protein expression of ZFX and clinicopathological parameters in 120 CRC cases. The results showed that ZFX expression was significantly associated with tumor differentiation (P = 0.022), tumor size (P = 0.037), tumor invasion (P = 0.027), lymph node metastasis (P = 0.042), distant metastasis (P = 0.011), and Dukes' classification (P = 0.028). Moreover, according to Kaplan-Meier model, patients with high expression of ZFX had a significantly poorer prognosis compared to those with low expression of ZFX. Multivariate analysis suggested that high expression of ZFX was an independent prognostic factor for CRC patients. In conclusion, our findings for the first time demonstrated that ZFX expression may be associated with the progress of CRC and suggested that ZFX has the potential value to be an effective prognostic predictor for CRC patients.