Iterative feedback-based models for image and video polyp segmentation.

Accurate segmentation of polyps in colonoscopy images has gained significant attention in recent years, given its crucial role in automated colorectal cancer diagnosis. Many existing deep learning-based methods follow a one-stage processing pipeline, often involving feature fusion across different levels or utilizing boundary-related attention mechanisms. Drawing on the success of applying Iterative Feedback Units (IFU) in image polyp segmentation, this paper proposes FlowICBNet by extending the IFU to the domain of video polyp segmentation. By harnessing the unique capabilities of IFU to propagate and refine past segmentation results, our method proves effective in mitigating challenges linked to the inherent limitations of endoscopic imaging, notably the presence of frequent camera shake and frame defocusing. Furthermore, in FlowICBNet, we introduce two pivotal modules: Reference Frame Selection (RFS) and Flow Guided Warping (FGW). These modules play a crucial role in filtering and selecting the most suitable historical reference frames for the task at hand. The experimental results on a large video polyp segmentation dataset demonstrate that our method can significantly outperform state-of-the-art methods by notable margins achieving an average metrics improvement of 7.5% on SUN-SEG-Easy and 7.4% on SUN-SEG-Hard. Our code is available at https://github.com/eraserNut/ICBNet.

Uncertainty-Aware Multi-Dimensional Mutual Learning for Brain and Brain Tumor Segmentation.

Existing segmentation methods for brain MRI data usually leverage 3D CNNs on 3D volumes or employ 2D CNNs on 2D image slices. We discovered that while volume-based approaches well respect spatial relationships across slices, slice-based methods typically excel at capturing fine local features. Furthermore, there is a wealth of complementary information between their segmentation predictions. Inspired by this observation, we develop an Uncertainty-aware Multi-dimensional Mutual learning framework to learn different dimensional networks simultaneously, each of which provides useful soft labels as supervision to the others, thus effectively improving the generalization ability. Specifically, our framework builds upon a 2D-CNN, a 2.5D-CNN, and a 3D-CNN, while an uncertainty gating mechanism is leveraged to facilitate the selection of qualified soft labels, so as to ensure the reliability of shared information. The proposed method is a general framework and can be applied to varying backbones. The experimental results on three datasets demonstrate that our method can significantly enhance the performance of the backbone network by notable margins, achieving a Dice metric improvement of 2.8% on MeniSeg, 1.4% on IBSR, and 1.3% on BraTS2020.

Determination of the Acute and Chronic Toxicity of Sulfate from the Sulfur Autotrophic Denitrification Process to Juvenile Zebrafish (Danio rerio).

Sulfur-based materials are widely used as electron donors for denitrification to enhance nitrogen removal from water. This leads to an increased sulfate concentration in the effluent or sulfate accumulation in recirculating aquaculture systems. This study explored acute and chronic toxicity of sulfate to juvenile zebrafish (Danio rerio) and investigated the histopathological changes in the gills of juvenile zebrafish exposed to sulfate. Results show that zebrafish had a high tolerance to sulfate, with no acute toxicity at sulfate concentrations from 250 to 3200 mg/L. For the chronic toxicity study, it was found that zebrafish mortality decreased with the increase in sulfate concentrations ranging from 250 to 1500 mg/L. In contrast, when the sulfate concentration was 1500-3000 mg/L, zebrafish mortality increased with the increasing sulfate concentration. In addition, in the ion balance test, KCl was added to balance the effects of Na+ from the Na2SO4 used to obtain the desired sulfate concentrations, showing that fish mortality correspondingly increased with increasing KCl addition. Furthermore, when living in an environment with elevated sulfate concentrations for a long period, changes were observed in the morphology, behavior, and gill tissue of the zebrafish, including slow and lateral swimming; bottom settling; and large opening and closing, lamellar fusion, and necrosis of gills. This research reveals the toxicity of sulfate to aquatic organisms, providing a scientific basis for the promotion and application of sulfur or sulfur-based materials in autotrophic reduction processes for wastewater treatment.

LncRNA-DUXAP8 Regulation of the Wnt/ß-Catenin Signaling Pathway to Inhibit Glycolysis and Induced Apoptosis in Acute Myeloid Leukemia

Objective: Acute myeloid leukemia (AML) is a malignancy of the hematopoietic system, accounting for approximately 70% of acute leukemias. Long noncoding RNA-DUXAP8 (lncRNA-DUXAP8) has been found to be abnormally expressed in a variety of tumors. However, its function and mechanism in AML have not been studied. We investigate the effect of lncRNA-DUXAP8 on AML and its mechanism so as to provide a new theoretical basis for the diagnosis and treatment of AML. Materials and Methods: The expression of lncRNA-DUXAP8 in AML bone marrow tissues and the THP-1, HL-60, TF-1, AML193, and U937 cell lines was detected by qRT-PCR. It was then altered by transfecting plasmids overexpressing si-DUXAP8 and lncRNA-DUXAP8, respectively. CCK8 and cell colony assay were performed to evaluate the proliferation ability of AML cells. In addition, flow cytometry was used to observe the apoptosis process. Glucose and lactate kits were utilized to detect glucose consumption and lactate levels. Finally, western blotting was performed to detect the expression of proteins related to the Wnt/ß-catenin signaling pathway in cells. Results: LncRNA-DUXAP8 was downregulated in both AML bone marrow tissues and cell lines. Upon interfering with lncRNA-DUXAP8 in AML cell line THP-1, AML cell proliferation and glycolysis were promoted while cell apoptosis was inhibited. The opposite results were obtained after overexpressing lncRNA-DUXAP8. Meanwhile, western blotting confirmed that interference with lncRNA-DUXAP8 stimulated the expression of proteins Wnt5a, ß-catenin, c-Myc, and cyclin-D1 in the Wnt/ß-catenin pathway. Moreover, overexpression of lncRNA-DUXAP8 inhibited the expression of Wnt/ß-catenin pathway proteins. Finally, LiCl, an activator of the Wnt/ß-catenin pathway, reversed the regulation of AML cells by lncRNA-DUXAP8 upregulation compared with the DUXAP group. Conclusion: This study showed that lncRNA-DUXAP8 regulated the Wnt/ß-catenin signaling pathway to inhibit glycolysis and induce apoptosis in AML. This experiment has provided new angles and an experimental basis for treating patients with AML.

Supervised Brain Tumor Segmentation Based on Gradient and Context-Sensitive Features.

Gliomas have the highest mortality rate and prevalence among the primary brain tumors. In this study, we proposed a supervised brain tumor segmentation method which detects diverse tumoral structures of both high grade gliomas and low grade gliomas in magnetic resonance imaging (MRI) images based on two types of features, the gradient features and the context-sensitive features. Two-dimensional gradient and three-dimensional gradient information was fully utilized to capture the gradient change. Furthermore, we proposed a circular context-sensitive feature which captures context information effectively. These features, totally 62, were compressed and optimized based on an mRMR algorithm, and random forest was used to classify voxels based on the compact feature set. To overcome the class-imbalanced problem of MRI data, our model was trained on a class-balanced region of interest dataset. We evaluated the proposed method based on the 2015 Brain Tumor Segmentation Challenge database, and the experimental results show a competitive performance.

Changes in element accumulation, phenolic metabolism, and antioxidative enzyme activities in the red-skin roots of Panax ginseng.

BACKGROUND: Red-skin root disease has seriously decreased the quality and production of Panax ginseng (ginseng). METHODS: To explore the disease's origin, comparative analysis was performed in different parts of the plant, particularly the epidermis, cortex, and/or fibrous roots of 5-yr-old healthy and diseased red-skin ginseng. The inorganic element composition, phenolic compound concentration, reactive oxidation system, antioxidant concentrations such as ascorbate and glutathione, activities of enzymes related to phenolic metabolism and oxidation, and antioxidative system particularly the ascorbate-glutathione cycle were examined using conventional methods. RESULTS: Aluminum (Al), iron (Fe), magnesium, and phosphorus were increased, whereas manganese was unchanged and calcium was decreased in the epidermis and fibrous root of red-skin ginseng, which also contained higher levels of phenolic compounds, higher activities of the phenolic compound-synthesizing enzyme phenylalanine ammonia-lyase and the phenolic compound oxidation-related enzymes guaiacol peroxidase and polyphenoloxidase. As the substrate of guaiacol peroxidase, higher levels of H2O2 and correspondingly higher activities of superoxide dismutase and catalase were found in red-skin ginseng. Increased levels of ascorbate and glutathione; increased activities of l-galactose 1-dehydrogenase, ascorbate peroxidase, ascorbic acid oxidase, and glutathione reductase; and lower activities of dehydroascorbate reductase, monodehydroascorbate reductase, and glutathione peroxidase were found in red-skin ginseng. Glutathione-S-transferase activity remained constant. CONCLUSION: Hence, higher element accumulation, particularly Al and Fe, activated multiple enzymes related to accumulation of phenolic compounds and their oxidation. This might contribute to red-skin symptoms in ginseng. It is proposed that antioxidant and antioxidative enzymes, especially those involved in ascorbate-glutathione cycles, are activated to protect against phenolic compound oxidation.