Binh Nguyen Phuc
Research Subjects
Binh Nguyen Phuc has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Viet Hang Dao
Internal Medicine Faculty, Hanoi Medical University, Hanoi, Vietnam
3 shared publications - Long Bao Hoang
College of Health Sciences, VinUniversity, Hanoi 100000, Vietnam
2 shared publications - Hai Vu
School of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, Vietnam
1 shared publication - Hue Luu Thi Minh
The Institute of Gastroenterology and Hepatology Hanoi Vietnam
1 shared publication - Long Dao Van
Internal Medicine Faculty Hanoi Medical University Hanoi Vietnam
1 shared publication - Thanh Tung Nguyen
Institute of Gastroenterology and Hepatology
1 shared publication
Latest Publications
- 1 July 2026
- Published by Wiley in Helicobacter
- Vol. 31 (4)
Diagnostic Value of the Pylori DuoTect Test for Helicobacter pylori Detection in the Vietnamese Population
Objectives: To evaluate the diagnostic accuracy in Helicobacter pylori detection using blood test with FliD and CagA antibodies (Pylori DuoTect), comparing with rapid urease test (RUT) and urease breath test (UBT) in Vietnamese patients with upper GI symptoms. Methods: A cross‐sectional study was conducted at the Institute of Gastroenterology and Hepatology in Hanoi, Vietnam on adults with upper GI symptoms, no prior treatment of peptic ulcers, and no history of H. pylori infection. Participants underwent upper GI endoscopy and three H. pylori tests, including rapid urease test (RUT), urea breath test (UBT), and Pylori DuoTect. Pylori DuoTect was considered positive if either FliD or CagA antibodies were detected. The H. pylori infection was defined as both RUT and UBT positive. Endoscopic findings were classified using the Kyoto classification score for gastritis. Diagnostic accuracy was evaluated using sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Results: From December 1, 2023, to August 9, 2024, 333 patients were recruited (mean age 45.9 years, 39.9% male). The most common symptom was epigastric pain (49.5%). The prevalences of gastritis, gastric ulcers, and duodenal ulcers were 92.7%, 12.1%, and 8.1%, respectively. Pylori DuoTect was positive in 51.9% of patients (FliD: 34.8% and CagA: 66.6%). Using the gold standard, 33.6% were diagnosed with H. pylori infection. The sensitivity, specificity, PPV, and NPV of Pylori DuoTect were 83.0%, 64.0%, 54.0%, and 88.0%, respectively. Combining Pylori DuoTect and endoscopy findings (peptic ulcer or Kyoto score ≥ 2) improved the sensitivity from 0.83 to 0.88 and increased NPV. Conclusion: Pylori DuoTect had moderate sensitivity and low specificity in the diagnosis of H. pylori infection in Vietnamese adult patients.
- 1 July 2026
- Published by Wiley in Helicobacter
- Vol. 31 (4)
Diagnostic Value of the Pylori DuoTect Test for Helicobacter pylori Detection in the Vietnamese Population
Objectives: To evaluate the diagnostic accuracy in Helicobacter pylori detection using blood test with FliD and CagA antibodies (Pylori DuoTect), comparing with rapid urease test (RUT) and urease breath test (UBT) in Vietnamese patients with upper GI symptoms. Methods: A cross‐sectional study was conducted at the Institute of Gastroenterology and Hepatology in Hanoi, Vietnam on adults with upper GI symptoms, no prior treatment of peptic ulcers, and no history of H. pylori infection. Participants underwent upper GI endoscopy and three H. pylori tests, including rapid urease test (RUT), urea breath test (UBT), and Pylori DuoTect. Pylori DuoTect was considered positive if either FliD or CagA antibodies were detected. The H. pylori infection was defined as both RUT and UBT positive. Endoscopic findings were classified using the Kyoto classification score for gastritis. Diagnostic accuracy was evaluated using sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Results: From December 1, 2023, to August 9, 2024, 333 patients were recruited (mean age 45.9 years, 39.9% male). The most common symptom was epigastric pain (49.5%). The prevalences of gastritis, gastric ulcers, and duodenal ulcers were 92.7%, 12.1%, and 8.1%, respectively. Pylori DuoTect was positive in 51.9% of patients (FliD: 34.8% and CagA: 66.6%). Using the gold standard, 33.6% were diagnosed with H. pylori infection. The sensitivity, specificity, PPV, and NPV of Pylori DuoTect were 83.0%, 64.0%, 54.0%, and 88.0%, respectively. Combining Pylori DuoTect and endoscopy findings (peptic ulcer or Kyoto score ≥ 2) improved the sensitivity from 0.83 to 0.88 and increased NPV. Conclusion: Pylori DuoTect had moderate sensitivity and low specificity in the diagnosis of H. pylori infection in Vietnamese adult patients.
- Open Access
- 1 April 2025
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 14 (2) , 833-842
Classification of upper gastrointestinal tract diseases using endoscopic images
Automatic classification and disease detection in medical images, aided by machine learning, provide crucial support to prevent overlooked instances and ensure prompt treatment of diseases. Despite impressive achievements in the field of polyp detection from endoscopic images, classification of other diseases, such as reflux esophagitis, esophageal cancer, gastritis, gastric cancer, and duodenal ulcer, is still subject to significant limitations and remains a challenging area of study because of their different and more challenging characteristics. This paper proposes a method to roughly classify the diseases from the whole images by deep learning. In particular, we focus on identifying hard samples from the training dataset and enriching them with some fundamental augmentation techniques. We then employ a cutting-edge model, specifically ResNet, for the final classification stage. Additionally, we enhance the original ResNet’s loss function by incorporating another loss function called focal loss. These modifications play a crucial role in boosting the accuracy of the ResNet model. Our proposed method outputs the disease category and corresponding heat map showing the area of interest. It achieved very promising accuracy (99.55%) for the classification of five lesions on our self-collected dataset. It serves a dual purpose. Firstly, it aids in the training of novice endoscopists, enabling them to gain valuable experience. Secondly, it offers a rapid solution for annotating extensive volumes of endoscopic image data at the label level.
- 1 April 2025
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 14 (2) , 833-842
Open AccessClassification of upper gastrointestinal tract diseases using endoscopic images
Automatic classification and disease detection in medical images, aided by machine learning, provide crucial support to prevent overlooked instances and ensure prompt treatment of diseases. Despite impressive achievements in the field of polyp detection from endoscopic images, classification of other diseases, such as reflux esophagitis, esophageal cancer, gastritis, gastric cancer, and duodenal ulcer, is still subject to significant limitations and remains a challenging area of study because of their different and more challenging characteristics. This paper proposes a method to roughly classify the diseases from the whole images by deep learning. In particular, we focus on identifying hard samples from the training dataset and enriching them with some fundamental augmentation techniques. We then employ a cutting-edge model, specifically ResNet, for the final classification stage. Additionally, we enhance the original ResNet’s loss function by incorporating another loss function called focal loss. These modifications play a crucial role in boosting the accuracy of the ResNet model. Our proposed method outputs the disease category and corresponding heat map showing the area of interest. It achieved very promising accuracy (99.55%) for the classification of five lesions on our self-collected dataset. It serves a dual purpose. Firstly, it aids in the training of novice endoscopists, enabling them to gain valuable experience. Secondly, it offers a rapid solution for annotating extensive volumes of endoscopic image data at the label level.
- Open Access
- 15 September 2024
- Published by Korean College of Helicobacter and Upper Gastrointestinal Research in The Korean Journal of Helicobacter and Upper Gastrointestinal Research
- Vol. 24 (3) , 208-217
Novel Technique to Diagnose Gastroesophageal Reflux Disease
Gastroesophageal reflux disease (GERD), which is commonly encountered in clinical practice, has become increasingly prevalent in Asia in recent years. Definitive diagnosis of GERD requires upper gastrointestinal endoscopy and ambulatory pH monitoring and is therefore challenging. Endoscopic lesions are usually not incorporated into the diagnostic criteria, and pH monitoring is expensive, complicated, and uncomfortable for patients. Studies have investigated novel methods for diagnosis of GERD. Mucosal integrity, evaluated by mucosal admittance or impedance, is impaired in GERD owing to microscopic epithelial changes. Measurement of mucosal integrity is simple and can be performed endoscopically. Mucosal impedance has been investigated as a method to differentiate between GERD, non-GERD, and eosinophilic esophagitis, and mucosal admittance provides evidence to support diagnosis of GERD. Further research on these novel techniques is warranted to incorporate these into the diagnostic modalities used for GERD.
- 15 September 2024
- Published by Korean College of Helicobacter and Upper Gastrointestinal Research in The Korean Journal of Helicobacter and Upper Gastrointestinal Research
- Vol. 24 (3) , 208-217
Open AccessNovel Technique to Diagnose Gastroesophageal Reflux Disease
Gastroesophageal reflux disease (GERD), which is commonly encountered in clinical practice, has become increasingly prevalent in Asia in recent years. Definitive diagnosis of GERD requires upper gastrointestinal endoscopy and ambulatory pH monitoring and is therefore challenging. Endoscopic lesions are usually not incorporated into the diagnostic criteria, and pH monitoring is expensive, complicated, and uncomfortable for patients. Studies have investigated novel methods for diagnosis of GERD. Mucosal integrity, evaluated by mucosal admittance or impedance, is impaired in GERD owing to microscopic epithelial changes. Measurement of mucosal integrity is simple and can be performed endoscopically. Mucosal impedance has been investigated as a method to differentiate between GERD, non-GERD, and eosinophilic esophagitis, and mucosal admittance provides evidence to support diagnosis of GERD. Further research on these novel techniques is warranted to incorporate these into the diagnostic modalities used for GERD.