RESUMEN
Dichotomous image segmentation (DIS) with rich fine-grained details within a single image is a challenging task. Despite the plausible results achieved by deep learning-based methods, most of them fail to segment generic objects when the boundary is cluttered with the background. In fact, the gradual decrease in feature map resolution during the encoding stage and the misleading texture clue may be the main issues. To handle these issues, we devise a novel frequency-and scale-aware deep neural network (FSANet) for high-precision DIS. The core of our proposed FSANet is twofold. First, a multimodality fusion (MF) module that integrates the information in spatial and frequency domains is adopted to enhance the representation capability of image features. Second, a collaborative scale fusion module (CSFM) which deviates from the traditional serial structures is introduced to maintain high resolution during the entire feature encoding stage. In the decoder side, we introduce hierarchical context fusion (HCF) and selective feature fusion (SFF) modules to infer the segmentation results from the output features of the CSFM module. We conduct extensive experiments on several benchmark datasets and compare our proposed method with existing state-of-the-art (SOTA) methods. The experimental results demonstrate that our FSANet achieves superior performance both qualitatively and quantitatively. The code will be made available at https://github.com/chasecjg/FSANet.
RESUMEN
The recognition of data matrix (DM) codes plays a crucial role in industrial production. Significant progress has been made with existing methods. However, for low-quality images with protrusions and interruptions on the L-shaped solid edge (finder pattern) and the dashed edge (timing pattern) of DM codes in industrial production environments, the recognition accuracy rate of existing methods sharply declines due to a lack of consideration for these interference issues. Therefore, ensuring recognition accuracy in the presence of these interference issues is a highly challenging task. To address such interference issues, unlike most existing methods focused on locating the L-shaped solid edge for DM code recognition, we in this paper propose a novel DM code recognition method based on locating the L-shaped dashed edge by incorporating the prior information of the center of the DM code. Specifically, we first use a deep learning-based object detection method to obtain the center of the DM code. Next, to enhance the accuracy of L-shaped dashed edge localization, we design a two-level screening strategy that combines the general constraints and central constraints. The central constraints fully exploit the prior information of the center of the DM code. Finally, we employ libdmtx to decode the content from the precise position image of the DM code. The image is generated by using the L-shaped dashed edge. Experimental results on various types of DM code datasets demonstrate that the proposed method outperforms the compared methods in terms of recognition accuracy rate and time consumption, thus holding significant practical value in an industrial production environment.
RESUMEN
INTRODUCTION: Hepatic portal venous gas is an extremely rare symptom of gas accumulation in the portal venous system. This disease has an acute onset, a rapid progression, and an extremely high mortality rate. This report describes a patient with mesenteric and hepatic portal venous gas caused by intestinal microbiota disturbance-induced gut-derived infection after ileostomy. The patient recovered and was discharged after conservative treatment. Nursing management of patients with mesenteric and hepatic portal venous gas is discussed. CLINICAL FINDINGS: A 76-year-old patient developed septic shock, paralytic intestinal obstruction, and mesenteric and hepatic portal venous gas after undergoing ileostomy. DIAGNOSIS: Mesenteric and hepatic portal venous gas was diagnosed on the basis of abdominal contrast-enhanced computed tomography findings. INTERVENTIONS: The treatment plan included early control of infection, early identification and nursing care of gut-derived infection caused by intestinal microbiota disturbance, early identification of paralytic intestinal obstruction, relief of intestinal obstruction and prevention of intestinal ischemia, and early nutritional support. OUTCOMES: On day 18 of hospitalization, the patient was transferred to the general ward and resumed eating, producing gas, and defecating. His abdominal signs and infection indicator levels were normal. On day 27, the patient was discharged home. CONCLUSION: This case provides an in-depth understanding of the care of patients with mesenteric and hepatic portal venous gas and emphasizes the important role of bedside nurses in evaluating and treating these patients. This report may help nurses care for similar patients.
Asunto(s)
Tratamiento Conservador , Ileostomía , Vena Porta , Humanos , Anciano , Masculino , Ileostomía/efectos adversos , Ileostomía/enfermería , Enfermería de Cuidados Críticos/normas , Resultado del Tratamiento , Embolia Aérea/etiología , Embolia Aérea/terapiaRESUMEN
Although the overall incidence and mortality of colorectal cancer have declined, diagnosed cases of young-onset colorectal cancer have increased significantly. Concerns about future fertility are second only to concerns about survival and may significantly affect the quality of life of young cancer survivors. Fertility preservation is an important issue in young-onset colorectal patients with cancer undergoing oncotherapy. Here, we discussed the effects of different treatments on fertility, common options for fertility preservation, factors affecting fertility preservation and improvement measures, and the relationship between fertility and pregnancy outcomes in young-onset colorectal patients with cancer.
RESUMEN
Melanosciadium is considered a monotypic genus and is also endemic to the southwest of China. No detailed phylogenetic studies or plastid genomes have been identified in Melanosciadium. In this study, the plastid genome sequence and nrDNA sequence were used for the phylogenetic analysis of Melanosciadium and its related groups. Angelica tsinlingensis was previously considered a synonym of Hansenia forbesii. Similarly, Ligusticum angelicifolium was previously thought to be the genus Angelica or Ligusticopsis. Through field observations and morphological evidence, we believe that the two species are more similar to M. pimpinelloideum in leaves, umbel rays, and fruits. Meanwhile, we found a new species from Anhui Province (eastern China) that is similar to M. pimpinelloideum and have named it M. Jinzhaiensis. We sequenced and assembled the complete plastid genomes of these species and another three Angelica species. The genome comparison results show that M. pimpinelloideum, A. tsinlingensis, Ligusticum angelicifolium, and M. jinzhaiensis have similarities to each other in the plastid genome size, gene number, and length of the LSC and IR regions; the plastid genomes of these species are distinct from those of the Angelica species. In addition, we reconstruct the phylogenetic relationships using both plastid genome sequences and nrDNA sequences. The phylogenetic analysis revealed that A. tsinlingensis, M. pimpinelloideum, L. angelicifolium, and M. jinzhaiensis are closely related to each other and form a monophyletic group with strong support within the Selineae clade. Consequently, A. tsinlingensis and L. angelicifolium should be classified as members of the genus Melanosciadium, and suitable taxonomical treatments have been proposed. Meanwhile, a comprehensive description of the new species, M. jinzhaiensis, is presented, encompassing its habitat environment and detailed morphological traits.
RESUMEN
Following the publication of the above article, the authors drew to our attention that they had made a couple of inadvertent errors in assembling Figs. 4 and 5; first, for the BT549 cell line, the data shown for the Procaspase1/Cleaved caspase1 in Fig. 5 and the GSDMDF/GSDMDN data in Fig. 4B were identical, and had been derived from the same original source; secondly, in Fig. 4A, the data shown correctly for the GSDMD BT549 cell line had also inadvertently been included in this figure to represent the MDAMB231 cell line. The revised and corrected versions of Figs. 4 and 5, showing the correct western blotting data for the GSDMD experiment in Fig. 4A and the Procaspase1/Cleaved caspase1 data for the BT549 cell line in Fig. 5, are shown in the next two pages. The authors regret that these errors in the assembly of Figs. 4 and 5 went unnoticed before the article was published, and thank the Editor of Oncology Reports for granting them the opportunity to publish this corrigendum. All the authors agree with the publication of this corrigendum; furthermore, they apologize to the readership of the journal for any inconvenience caused.[Oncology Reports 50: 188, 2023; DOI: 10.3892/or.2023.8625].
RESUMEN
In the context of contemporary artificial intelligence, increasing deep learning (DL) based segmentation methods have been recently proposed for brain tumor segmentation (BraTS) via analysis of multi-modal MRI. However, known DL-based works usually directly fuse the information of different modalities at multiple stages without considering the gap between modalities, leaving much room for performance improvement. In this paper, we introduce a novel deep neural network, termed ACFNet, for accurately segmenting brain tumor in multi-modal MRI. Specifically, ACFNet has a parallel structure with three encoder-decoder streams. The upper and lower streams generate coarse predictions from individual modality, while the middle stream integrates the complementary knowledge of different modalities and bridges the gap between them to yield fine prediction. To effectively integrate the complementary information, we propose an adaptive cross-feature fusion (ACF) module at the encoder that first explores the correlation information between the feature representations from upper and lower streams and then refines the fused correlation information. To bridge the gap between the information from multi-modal data, we propose a prediction inconsistency guidance (PIG) module at the decoder that helps the network focus more on error-prone regions through a guidance strategy when incorporating the features from the encoder. The guidance is obtained by calculating the prediction inconsistency between upper and lower streams and highlights the gap between multi-modal data. Extensive experiments on the BraTS 2020 dataset show that ACFNet is competent for the BraTS task with promising results and outperforms six mainstream competing methods.