Background: The gastroscopic examination is a preferred method for the detection of upper gastrointestinal lesions. However, gastroscopic examination has high requirements for doctors, especially for the strict position and quantity of the archived images. These requirements are challenging for the education and training of junior doctors.
Objective: The purpose of this study is to use deep learning to develop automatic position recognition technology for gastroscopic examination.
Methods: A total of 17182 gastroscopic images in eight anatomical position categories are collected. Convolutional neural network model MogaNet is used to identify all the anatomical positions of the stomach for gastroscopic examination The performance of four models is evaluated by sensitivity, precision, and F1 score.
Results: The average sensitivity of the method proposed is 0.963, which is 0.074, 0.066 and 0.065 higher than ResNet, GoogleNet and SqueezeNet, respectively. The average precision of the method proposed is 0.964, which is 0.072, 0.067 and 0.068 higher than ResNet, GoogleNet, and SqueezeNet, respectively. And the average F1-Score of the method proposed is 0.964, which is 0.074, 0.067 and 0.067 higher than ResNet, GoogleNet, and SqueezeNet, respectively. The results of the t-test show that the method proposed is significantly different from other methods (p< 0.05).
Conclusion: The method proposed exhibits the best performance for anatomical positions recognition. And the method proposed can help junior doctors meet the requirements of completeness of gastroscopic examination and the number and position of archived images quickly.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11191429 | PMC |
| http://dx.doi.org/10.3233/THC-248004 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
In the context of Chinese clinical texts, this paper aims to propose a deep learning algorithm based on Bidirectional Encoder Representation from Transformers (BERT) to identify privacy information and to verify the feasibility of our method for privacy protection in the Chinese clinical context. We collected and double-annotated 33,017 discharge summaries from 151 medical institutions on a municipal regional health information platform, developed a BERT-based Bidirectional Long Short-Term Memory Model (BiLSTM) and Conditional Random Field (CRF) model, and tested the performance of privacy identification on the dataset. To explore the performance of different substructures of the neural network, we created five additional baseline models and evaluated the impact of different models on performance.
View Article and Find Full Text PDFComparison of Interportal and Periportal Capsulotomies and Axial Distraction Resistance During Hip Arthroscopy: An In Vivo Propensity-Matched Cohort Study.
Am J Sports Med
January 2025
Department of Orthopaedics, University of Utah, Salt Lake City, Utah, USA.
Background: Intraoperative hip capsule management is increasingly recognized as an important component of hip arthroscopy for the prevention of capsular-related instability. The periportal capsulotomy, relative to the interportal capsulotomy, has been proposed as a minimally invasive technique for decreasing postarthroscopy hip instability; however, the biomechanical effects of this technique are not well established.
Purpose/hypothesis: This study aimed to provide a biomechanical characterization of interportal and periportal capsulotomies, helping inform surgeon choice of capsulotomy type and repair, potentially guiding clinical practice in hip arthroscopy.
Three-Plane Calcaneal Osteotomy With Joint Preservation vs Subtalar Arthrodesis to Treat Painful Calcaneal Fracture Malunions.
Foot Ankle Int
January 2025
Foot and Ankle Surgery Department, Honghui Hospital of Xi'an Jiaotong University, Xi'an, China.
Background: Calcaneal fracture malunion (CFM) commonly occurs with multiple pathologic changes and progressive pain and difficulty walking. The purpose of this study was to propose a modified 3-plane joint-preserving osteotomy for the treatment of CFM with subtalar joint incongruence, and to compare its efficacy to subtalar arthrodesis.
Methods: A retrospective comparative analysis of the data of 56 patients with CFM admitted from January 2017 to December 2022 was performed.
Efficacy of Orthognathic Surgery in OSAS Patients: A Systematic Review and Meta-Analysis.
J Oral Rehabil
January 2025
Saveetha Dental College and Hospitals, Saveetha Institute of Medical and Technical Sciences (SIMATS), Saveetha University, Chennai, India.
Background: Obstructive sleep apnea syndrome (OSAS) is a prevalent condition characterised by repeated episodes of partial or complete obstruction of the upper airway during sleep, leading to disrupted sleep and associated morbidities. Orthognathic surgery (OGS) has been proposed as a treatment option for OSAS, aimed at anatomically repositioning the maxillofacial structures to alleviate airway obstruction. This systematic review and meta-analysis aimed to evaluate the efficacy of OGS in reducing apnea-hypopnea index (AHI) and Epworth Sleepiness Scale (ESS) scores among OSAS patients.
View Article and Find Full Text PDFElectrochemical Synthesis of Polyaniline@Nano Zinc Oxide/Modified Multiwalled Carbon Nanotubes Nanocomposite Coating for Solid Phase Microextraction of Some Polycyclic Aromatic Hydrocarbons in Coffee and Grilled Meat.
J Sep Sci
January 2025
Herbal and Traditional Medicines Research Center, Kerman University of Medical Sciences, Kerman, Iran.
Polycyclic aromatic hydrocarbons (PAHs) are carcinogenic compounds resulting from incomplete burning of organic materials. This work describes the successful layer-by-layer fabrication of a novel zinc oxide nanocomposite made of zinc oxide nanoparticles, aniline, sodium dodecyl sulfate, and modified multi-walled carbon nanotubes on a stainless steel wire by electrodeposition. The coating and extraction conditions were screened, optimized, and validated using factorial design and central composite design, respectively.
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!