Background And Study Aims: Endoscopic reports are essential for the diagnosis and follow-up of gastrointestinal diseases. This study aimed to construct an intelligent system for automatic photo documentation during esophagogastroduodenoscopy (EGD) and test its utility in clinical practice.
Patients And Methods: Seven convolutional neural networks trained and tested using 210,198 images were integrated to construct the endoscopic automatic image reporting system (EAIRS). We tested its performance through man-machine comparison at three levels: internal, external, and prospective test. Between May 2021 and June 2021, patients undergoing EGD at Renmin Hospital of Wuhan University were recruited. The primary outcomes were accuracy for capturing anatomical landmarks, completeness for capturing anatomical landmarks, and detected lesions.
Results: The EAIRS outperformed endoscopists in retrospective internal and external test. A total of 161 consecutive patients were enrolled in the prospective test. The EAIRS achieved an accuracy of 95.2% in capturing anatomical landmarks in the prospective test. It also achieved higher completeness on capturing anatomical landmarks compared with endoscopists: (93.1% vs. 88.8%), and was comparable to endoscopists on capturing detected lesions: (99.0% vs. 98.0%).
Conclusions: The EAIRS can generate qualified image reports and could be a powerful tool for generating endoscopic reports in clinical practice.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1055/a-1731-9535 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
A Medical image segmentation model with auto-dynamic convolution and location attention mechanism.
Comput Methods Programs Biomed
January 2025
School of Computer Science and Technology, Shandong Technology and Business University, Yantai 264005, China; Shandong Future Intelligent Financial Engineering Laboratory, Yantai 264005, China. Electronic address:
Background And Objective: Medical image segmentation is a technique used to identify and locate anatomical structures or diseased areas from medical images with high accuracy. Accurate image segmentation is crucial in medical applications such as clinical diagnosis, surgical planning, and treatment monitoring. It provides reliable quantitative information, which helps in making decisions.
View Article and Find Full Text PDFCell size has pervasive effects on the functional composition and morphology of leaves: a case study in Rhododendron (Ericaceae).
Physiol Plant
January 2025
Institute of Environment, Department of Biological Sciences, Florida International University, Miami, FL, USA.
The leaf economics spectrum (LES) characterizes a tradeoff between building a leaf for durability versus for energy capture and gas exchange, with allocation to leaf dry mass per projected surface area (LMA) being a key trait underlying this tradeoff. However, regardless of the biomass supporting the leaf, high rates of gas exchange are typically accomplished by small, densely packed stomata on the leaf surface, which is enabled by smaller genome sizes. Here, we investigate how variation in genome size-cell size allometry interacts with variation in biomass allocation (i.
View Article and Find Full Text PDFT-branch by partial deployment technique in the endovascular repair of complex aortic and thoracoabdominal aneurysms with narrow or severe angulated para-visceral aorta.
J Vasc Surg
January 2025
Vascular Surgery, University of Bologna, DIMEC, Bologna, Italy; Vascular Surgery Unit, IRCCS Sant'Orsola, Bologna, Italy.
Introduction/aim: The partial deployment technique (PDT) is an unconventional option of T-branch deployment to allow target arteries (TAs) cannulation/stenting from the upper arm access, in case of narrow (NPA: <25mm) or severely angulated (APA: >60°) aorta. Aim of this study was to report outcomes of the endovascular repair of complex aortic (c-AAAs) and thoracoabdominal (TAAAs) aneurysms by T-branch and PDT.
Methods: All consecutive patients underwent urgent endovascular repair of c-AAAs and TAAAs by T-branch (Cook-Medical, Bloomington, IN, US) and PDT from 2021 to 2023 were analyzed.
Quantification of 3D microstructures in Achilles tendons during in situ loading reveals anisotropic fiber response.
Acta Biomater
January 2025
Department of Biomedical Engineering, Lund University, Box 118, 221 00 Lund, Sweden.
While the number of studies investigating Achilles tendon pathologies has grown exponentially, more research is needed to gain a better understanding of the complex relation between its hierarchical structure, mechanical response, and failure. At the microscale, collagen fibers are, with some degree of dispersion, primarily aligned along the principal loading direction. However, during tension, rearrangements and reorientations of these fibers are believed to occur.
View Article and Find Full Text PDFLeft-Right Brain-Wide Asymmetry of Neuroanatomy in the Mouse Brain.
Neuroimage
January 2025
Department of Genetics, Harvard Medical School, Boston, MA, USA; Department of Pathology, Brigham and Women's Hospital, Boston, MA, USA. Electronic address:
Left-right asymmetry of the human brain is widespread through its anatomy and function. However, limited microscopic understanding of it exists, particularly for anatomical asymmetry where there are few well-established animal models. In humans, most brain regions show subtle, population-average regional asymmetries in thickness or surface area, alongside a macro-scale twisting called the cerebral petalia in which the right hemisphere protrudes anteriorly past the left.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!