Printed document layout analysis and optical character recognition system based on deep learning.

This paper proposes a layout analysis and text recognition system for printed documents based on deep learning. Initially, scanned documents or image files are processed using a layout analysis algorithm based on YOLOv4 and YOLOv8 deep learning to identify the positions of titles, text paragraphs, tables, and images within the document. Each of these categories undergoes specific character segmentation processing.

Correlations between genetically predicted iron-supplement drug targets and inflammatory bowel disease: A Mendelian randomization study.

This study investigates the causal relationship between genetically proxied iron-supplement drugs and inflammatory bowel disease (IBD) risk. After identifying 8 commonly used iron supplementation drugs based on the guidelines, a search for each of these drugs yielded 18 key regulatory targets and the locus information of each drug-targeted gene was obtained. Hemoglobin was selected as a biomarker downstream of drug regulation and its single nucleotide polymorphism (SNP) data were extracted and screened from genome-wide association studies (GWAS).

From Physical Cross-Linking to Tailored Phosphorylation: Unlocking High-Performance and Biocompatible Xanthan-Konjac Hydrogels for Zinc-Ion Batteries.

Natural polymer-based hydrogel electrolytes, though biocompatible and cost-effective, often exhibit poor mechanical strength and ionic conductivity, limiting their use in high-performance energy storage. Phos-XK, a novel hydrogel electrolyte derived from xanthan gum (XG) and konjac glucomannan (KGM), has been developed via physical cross-linking and targeted phosphorylation. Specifically, physical cross-linking forms a robust 3D network that provides a stable structural foundation.

Establishment and validation of a clinical prediction model for colorectal adenoma risk factors.

Colorectal adenomas are benign tumors of the colorectal mucosal epithelium that have malignant potential and are regarded as precancerous lesions of colorectal cancer, for which the specific risk factors are unclear. The present study aimed to identify independent risk factors for colorectal adenoma to develop a prediction model and test its predictive value. A retrospective analysis was performed using data from patients who underwent electronic colonoscopy at the Department of Proctology (Affiliated Hospital of Shandong University of Traditional Chinese Medicine; Jinan, China) from January 2013 to December 2023 and had polyps removed during colonoscopy.

Deep learning and radiomics-driven algorithm for automated identification of May-Thurner syndrome in Iliac CTV imaging.

Objective: This research aimed to create a dataset of Iliac CTV scans for automated May-Thurner syndrome (MTS) detection using deep learning and radiomics. In addition, it sought to establish an automated segmentation model for Iliac Vein CTV scans and construct a radiomic signature for MTS diagnosis.

Methods: We collected a dataset of 490 cases meeting specific inclusion and exclusion criteria, anonymized to comply with HIPAA regulations.

Optimization of ultrasonic-assisted extraction of total flavonoids from by a hybrid response surface methodology-artificial neural network-genetic algorithm (RSM-ANN-GA) approach, coupled with an assessment of antioxidant activities.

The objective of this research endeavor is to refine the ultrasonic-assisted extraction technique for total flavonoids from (TFO), utilizing a synergistic approach combining response surface methodology (RSM) and artificial neural network integrated with genetic algorithm (RSM-ANN-GA). The optimized extraction parameters determined through RSM yielded a TFO concentration of 13.538 mg g under the following conditions: an ethanol concentration of 61.

Enhancing Thickness Uniformity of NbO/SiO Multilayers Using Shadow Masks for Flexible Color-Filtering Applications.

Using a stainless shadow mask combined with a magnetron-ion-assisted deposition (IAD) sputtering system, we investigate the surface morphologies and optical properties of microfilms. Optimal color-filter (CF) coating microfilms with niobium pent-oxide (NbO)/silicon dioxide (SiO) multilayers on a hard polycarbonate (HPC) substrate, grown at 85 °C and 50 SCCM oxygen flow, can obtain a fairly uniform thickness (with an average roughness of 0.083 and 0.

A topochemical reaction induced the formation of BiS micro-straws from a Bi-MOF for an ultra-long Zn storage life.

Aqueous zinc ion batteries (ZIBs) are considered as promising energy storage devices in the post-lithium-ion era, due to their high energy density, low cost, high safety, and environmental benignity, however their commercialization is hindered by the sluggish diffusion kinetics of cathode materials due to the large hydrate Zn radius. In this work, we propose a unique structure inheritance strategy for preparing BiS micro-straws in which a metal-organic framework (MOF) denoted as Bi-PYDC (PYDC = 3,5-pyridinedicarboxylate) with a string of [BiO] chains is judiciously selected as the structure-directing template to induce the formation of micro-straws based on a topochemical reaction. The distinctive hollow structure significantly enhances the ionic storage kinetics.

ARF6 plays a general role in targeting palmitoylated proteins from the Golgi to the plasma membrane.

Protein palmitoylation is a post-translational lipid modification of proteins. Accumulating evidence reveals that palmitoylation functions as a sorting signal to direct proteins to destinations; however, the sorting mechanism remains largely unknown. Here, we show that ARF6 plays a general role in targeting palmitoylated proteins from the Golgi to the plasma membrane (PM).

Trisodium citrate as a modulation additive to increase the cycling capability of a BiS cathode in a zinc-ion battery.

3D BiS materials were prepared by the trisodium citrate (NaCit)-assisted solvothermal method and applied to aqueous zinc ion batteries (AZIBs) to explore the effect of the electrode material morphology on the electrochemical performance. As the concentration of NaCit increases, the 3D assembly morphology evolves from coral-like to sphere-like to snowflake-like structures. The electrochemical test results show that the electrode materials of various morphologies possess excellent cycle life, but the specific capacity varies greatly depending on the morphology.

Machine learning models predict lymph node metastasis in patients with stage T1-T2 esophageal squamous cell carcinoma.

Background: For patients with stage T1-T2 esophageal squamous cell carcinoma (ESCC), accurately predicting lymph node metastasis (LNM) remains challenging. We aimed to investigate the performance of machine learning (ML) models for predicting LNM in patients with stage T1-T2 ESCC.

Methods: Patients with T1-T2 ESCC at three centers between January 2014 and December 2019 were included in this retrospective study and divided into training and external test sets.

Ion sieve membrane: Homogenizing Li flux and restricting polysulfides migration enables long life and highly stable Li-S battery.

Limited by the notorious Li dendrites growth and serious polysulfide shuttle effect, the development of lithium-sulfur (Li-S) batteries is stagnant. Herein, a multifunctional separator composed of Cu-based metal-organic framework (Cu-MOF) and Li-Nafion was proposed to address the above intractable issues. The Cu-MOF with homogeneous porous structure and abundant Lewis acidic sites not only promotes uniform Li flux, but also exhibits a strong chemical interaction with polysulfides to inhibit the shuttle effect.

Mid-term Results of the Treatment of Isolated Dissection of the Celiac Artery: A Comparative Analysis of Endovascular Versus Conservative Therapy.

Objectives: Endovascular treatment (EVT) is an alternative method used to treat isolated dissection of the celiac artery (IDCA). However, only a few mid-term results have been reported. This study aimed to analyze and compare the outcomes of endovascular and non-operative therapies for IDCA.

A 10-year experience of leiomyosarcoma of the inferior vena cava.

Objectives: Leiomyosarcoma of the inferior vena cava (IVC) is rare. The study reviewed patients with IVC leiomyosarcoma in our hospital in the past ten years.

Methods: Twenty patients diagnosed with IVC leiomyosarcoma between October 2010 and October 2020 were enrolled.

Percutaneous contrast-enhanced ultrasound-guided transabdominal sac embolization is an effective technique for treating complicated type II endoleaks after endovascular aneurysm repair.

Objective: In the present study, we evaluated and compared the outcomes of transarterial embolization with those of percutaneous contrast-enhanced ultrasound-guided transabdominal sac embolization (PUSE) for type II endoleaks (T2ELs).

Methods: A retrospective review was conducted of consecutive patients who had undergone T2EL embolization between January 2015 and December 2020 at our center. The cohort was divided into two groups according to the embolization approach: PUSE vs transarterial.

Skeletal muscle metastasis with bone metaplasia from colon cancer: A case report and review of the literature.

Background: Colon cancer is a common malignant disease of the gastrointestinal tract and usually occurs at the junction of the rectum and sigmoid colon. Lymphatic and hematogenous metastases occur frequently in colon cancer and the most common metastatic sites include the liver, lung, peritoneum, bone, and lymph nodes. As a manifestation of advanced tumor spread and metastasis, soft tissue metastasis, especially skeletal muscle metastasis with bone metaplasia caused by colon cancer, is rare, accounting for less than 1% of metastases.

Hsa_circ_0008360 sponges miR-186-5p to target CCND2 to modulate high glucose-induced vascular endothelial dysfunction.

Vascular endothelial dysfunction is associated with the progress of many diseases. Circular RNAs (circRNAs) take part in the dysfunction of vascular endothelium. CircRNA hsa_circ_0008360 (circ_0008360) is dysregulated in high glucose-treated vascular endothelium, while the role and mechanism of circ_0008360 in high glucose-induced dysfunction remain unknown.

LncRNA SNHG15 relieves hyperglycemia-induced endothelial dysfunction via increased ubiquitination of thioredoxin-interacting protein.

Numerous studies have revealed that hyperglycemia is a pivotal driver of diabetic vascular complications. However, the mechanisms of hyperglycemia-induced endothelial dysfunction in diabetes remain incompletely understood. This study aims to expound on the underlying mechanism of the endothelial dysfunction induced by hyperglycemia from the perspective of long non-coding RNAs (lncRNA).

Diabetic neuropathic pain induced by streptozotocin alters the expression profile of non-coding RNAs in the spinal cord of mice as determined by sequencing analysis.

Diabetic neuropathic pain (DNP) is one of the most serious complications of diabetes. Patients with DNP always exhibit spontaneous and stimulus-evoked pain. However, the pathogenesis of DNP remains to be fully elucidated.