Constructing an artificial intelligence-assisted system for the assessment of gastroesophageal valve function based on the hill classification (with video)
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.An AI model, EfficientNet-Hill, was developed for gastroesophageal flap valve (GEFV) Hill classification, achieving 83.32% accuracy. This AI tool assists endoscopists in improving diagnostic accuracy for GERD assessments.
Area Of Science
- Gastroenterology and Artificial Intelligence
- Medical Imaging and Diagnostics
Background
- The endoscopic Hill classification is crucial for assessing the gastroesophageal junction (EGJ) morphology.
- Accurate classification of the gastroesophageal flap valve (GEFV) is essential for diagnosing conditions like GERD.
Purpose Of The Study
- To develop and deploy an artificial intelligence (AI) model for automated Hill classification of GEFV morphology.
- To assist endoscopists in improving diagnostic efficiency and accuracy during endoscopic grading.
Main Methods
- A deep learning model (EfficientNet-Hill) was developed using CNN and Transformer architectures on 1143 GEFV images and 17 videos.
- Transfer learning, cross-entropy loss, Adam optimizer, and learning rate scheduling were employed for model training.
- Model performance was evaluated using accuracy, precision, recall, F1 score, and compared to endoscopists via McNemar's test. Interpretability techniques (t-SNE, Grad-CAM, SHAP) were used.
Main Results
- The EfficientNet-Hill model achieved 83.32% accuracy, outperforming junior endoscopists (75.82%) and comparable to senior endoscopists (86.51%).
- The AI model demonstrated statistically significant improvement over junior endoscopists (p < 0.05) and no significant difference compared to senior endoscopists (p ≥ 0.05).
- The model achieved real-time classification (>50fps) on multiple platforms, with identified areas for decision-making and misclassification analysis.
Conclusions
- The developed EfficientNet-Hill AI model enables automated Hill classification of GEFV morphology.
- This AI tool can enhance diagnostic efficiency and accuracy in endoscopic grading for GERD assessments.
- Facilitates integration of Hill classification into routine endoscopic reports and patient management.
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
Related Concept Videos
Assessing the gastrointestinal (GI) system is a complex process that begins with collecting subjective data. This data, collected through patient interviews, provides crucial insights into the patient's health history, perception patterns, and lifestyle habits, all contributing significantly to GI health.
Health History
The initial step in assessing the GI system is obtaining a comprehensive health history. This includes inquiring about the patient's history or presence of problems...
Assessing the gastrointestinal (GI) system is a complex process that begins with collecting subjective data. This data, collected through patient interviews, provides crucial insights into the patient's health history, perception patterns, and lifestyle habits, all contributing significantly to GI health.
Health Perception Patterns
Health perception patterns offer valuable insights into a patient's lifestyle habits and how they may impact their GI health. These patterns include:
...
Gastroesophageal reflux disease, or GERD, is a persistent medical condition that affects many individuals worldwide. Its clinical manifestations can vary greatly, making diagnosis and management challenging for healthcare professionals. The following is a comprehensive overview of the clinical manifestations, assessment, and management strategies for GERD.
Clinical Manifestations
GERD presents itself in a multitude of ways, with symptoms varying from person to person. The hallmark symptoms are...
This lesson explores three gastrointestinal imaging techniques: radionuclide testing, colonic transit studies, and virtual colonoscopy.
Radionuclide Testing
Radionuclide testing is a sophisticated medical technique for assessing gastrointestinal motility. It focuses on gastric emptying and colonic transit time. Radioactive markers track the movement of food through the digestive system, providing insights into gastrointestinal disorders.
In gastric emptying studies, a meal's liquid and...