4.6 Review

Applications of Artificial Intelligence for the Diagnosis of Gastrointestinal Diseases

Related references

Note: Only part of the references are listed.
Review Gastroenterology & Hepatology

Performance of artificial intelligence in colonoscopy for adenoma and polyp detection: a systematic review and meta-analysis

Cesare Hassan et al.

Summary: The meta-analysis found that incorporating artificial intelligence as an aid for detecting colorectal neoplasia significantly increases the detection rate of colorectal neoplasia, independently of the main adenoma characteristics.

GASTROINTESTINAL ENDOSCOPY (2021)

Article Gastroenterology & Hepatology

A computer-assisted algorithm for narrow-band imaging-based tissue characterization in Barrett's esophagus

Maarten R. Struyvenberg et al.

Summary: The research demonstrated the feasibility of a deep-learning CAD system for tissue characterization of NBI zoom imagery in Barrett's esophagus, achieving promising diagnostic accuracy in predicting the presence/absence of Barrett's neoplasia.

GASTROINTESTINAL ENDOSCOPY (2021)

Article Gastroenterology & Hepatology

Automated software-assisted diagnosis of esophageal squamous cell neoplasia using high-resolution microendoscopy

Mimi C. Tan et al.

Summary: After training and testing, endoscopists showed higher sensitivity but lower specificity compared to the automated software algorithm for ESCN detection. With knowledge of the software algorithm, endoscopists improved their specificity significantly while maintaining high sensitivity and accuracy, especially among novices. The use of computer-assisted diagnosis could facilitate widespread adoption of HRME technology in resource-poor areas.

GASTROINTESTINAL ENDOSCOPY (2021)

Article Gastroenterology & Hepatology

Ulcer severity grading in video capsule images of patients with Crohn's disease: an ordinal neural network solution

Yiftach Barash et al.

Summary: The study developed a deep learning algorithm for automated grading of CD ulcers on capsule endoscopy images, achieving high accuracy in detecting severe ulcers. The algorithm has the potential to improve diagnosis and monitoring in patients with CD.

GASTROINTESTINAL ENDOSCOPY (2021)

Article Gastroenterology & Hepatology

Differential diagnosis for esophageal protruded lesions using a deep convolution neural network in endoscopic images

Min Zhang et al.

Summary: This study developed CNN-based models for distinguishing benign esophageal protruded lesions using endoscopic images, showing that CNN outperformed endoscopists in terms of accuracy. Combining CNN and endoscopist predictions significantly improved diagnostic accuracy, highlighting the potential of ensemble models in real endoscopic settings.

GASTROINTESTINAL ENDOSCOPY (2021)

Article Gastroenterology & Hepatology

Endoscopic prediction of submucosal invasion in Barrett's cancer with the use of artificial intelligence: a pilot study

Alanna Ebigbo et al.

Summary: This study demonstrates the multicenter application of an AI-based system in predicting submucosal invasion in endoscopic images of Barrett's cancer. The AI system performed equally to international experts in differentiating between T1a and T1b cancer lesions, but further improvements and application are needed.

ENDOSCOPY (2021)

Article Gastroenterology & Hepatology

Evaluation of the effects of an artificial intelligence system on endoscopy quality and preliminary testing of its performance in detecting early gastric cancer: a randomized controlled trial

Lianlian Wu et al.

Summary: The study demonstrated that the use of the ENDOANGEL system effectively improved the quality of esophagogastroduodenoscopy and showed potential for real-time detection of early gastric cancer. The ENDOANGEL group had fewer blind spots and longer inspection time compared to the control group, with a high accuracy, sensitivity, and specificity in detecting gastric cancer.

ENDOSCOPY (2021)

Article Gastroenterology & Hepatology

Optical diagnosis of colorectal polyp images using a newly developed computer-aided diagnosis system (CADx) compared with intuitive optical diagnosis

Quirine E. W. van der Zander et al.

Summary: A computer-aided diagnosis system (CADx) utilizing artificial neural networks achieved significantly higher diagnostic accuracy for optical diagnosis of colorectal polyps compared with expert and novice endoscopists. The system had a diagnostic accuracy of 88.3% using HDWL images and 86.7% using BLI images, which was improved to 95.0% when combining both modalities. However, the use of the BLI Adenoma Serrated International Classification (BASIC) did not increase the diagnostic accuracy of endoscopists compared to intuitive optical diagnosis.

ENDOSCOPY (2021)

Article Gastroenterology & Hepatology

Comparative study on artificial intelligence systems for detecting early esophageal squamous cell carcinoma between narrow-band and white-light imaging

Bing Li et al.

Summary: The CAD-NBI system for screening early ESCC has higher accuracy and specificity than CAD-WLI. Endoscopists can achieve the best diagnostic efficacy using both CAD-WLI and CAD-NBI.

WORLD JOURNAL OF GASTROENTEROLOGY (2021)

Article Multidisciplinary Sciences

A radiomics-based model for predicting prognosis of locally advanced gastric cancer in the preoperative setting

Jaeseung Shin et al.

Summary: The study evaluates the performance of a radiomics-based model for predicting recurrence-free survival of locally advanced gastric cancer on preoperative CT images. The radiomic model showed higher predictive value compared to the clinical model in both internal and external validations, improving risk stratification for LAGC patients.

SCIENTIFIC REPORTS (2021)

Article Oncology

Predicting aggressive histopathological features in esophageal cancer with positron emission tomography using a deep convolutional neural network

Joe Chao-Yuan Yeh et al.

Summary: Training a 3D-CNN with PET imaging data can predict the presence of LVI/PNI in esophageal cancer with acceptable accuracy.

ANNALS OF TRANSLATIONAL MEDICINE (2021)

Article Computer Science, Artificial Intelligence

A deep-learning-based unsupervised model on esophageal manometry using variational autoencoder

Wenjun Kou et al.

Summary: High-resolution manometry (HRM) is the primary method for diagnosing esophageal motility disorders, and a generative model using variational auto-encoder (VAE) approach was developed with over 32-thousand raw swallow data. The model provides a new possibility for automatic diagnosis and understanding of esophageal motility disorders.

ARTIFICIAL INTELLIGENCE IN MEDICINE (2021)

Article Gastroenterology & Hepatology

Use of a convolutional neural network for classifying microvessels of superficial esophageal squamous cell carcinomas

Ryotaro Uema et al.

Summary: A computer-aided diagnosis system based on convolutional neural network was constructed to classify microvessels on superficial esophageal squamous cell carcinomas. The system demonstrated a microvessel classification accuracy of 84.2% on a validation dataset of 747 images, outperforming the average of eight endoscopists (77.8%, P < 0.001).

JOURNAL OF GASTROENTEROLOGY AND HEPATOLOGY (2021)

Article Radiology, Nuclear Medicine & Medical Imaging

Machine Learning-based Differentiation of Benign and Premalignant Colorectal Polyps Detected with CT Colonography in an Asymptomatic Screening Population: A Proof-of-Concept Study

Sergio Grosu et al.

Summary: Machine learning-based image analysis showed promising results in differentiating benign and premalignant colorectal polyps detected with CT colonography, with high sensitivity and specificity demonstrated in an external test set. The most important image feature for decision making was quantifying first-order gray level histogram statistics.

RADIOLOGY (2021)

Article Gastroenterology & Hepatology

Performance of a deep learning-based identification system for esophageal cancer from CT images

Masashi Takeuchi et al.

Summary: By fine-tuning deep learning AI technology on CT images, a highly accurate diagnostic system for esophageal cancer was successfully established. Further training with larger datasets from multiple centers could enhance diagnostic accuracy and support better decision-making.

ESOPHAGUS (2021)

Review Gastroenterology & Hepatology

Accuracy of artificial intelligence-assisted detection of esophageal cancer and neoplasms on endoscopic images: A systematic review and meta-analysis

Si Min Zhang et al.

Summary: The study found that AI-assisted diagnostic models are more accurate in detecting esophageal neoplasms on endoscopic images compared to endoscopists, showing higher sensitivity and specificity. However, most of the included studies have a retrospective design, indicating a need for further validation through prospective trials.

JOURNAL OF DIGESTIVE DISEASES (2021)

Article Biochemistry & Molecular Biology

Triage-driven diagnosis of Barrett's esophagus for early detection of esophageal adenocarcinoma using deep learning

Marcel Gehrung et al.

Summary: Deep learning methods have been successfully integrated with expert knowledge and clinical decision pathways to automate the analysis of Cytosponge-TFF3 test samples for the early detection of Barrett's esophagus. By defining triage classes based on pathologists' decision patterns, the workload of pathologists can be reduced by 57% without compromising diagnostic performance. The clinician-in-the-loop deep learning system streamlines the workflow for Barrett's esophagus detection while maintaining the accuracy of manual review.

NATURE MEDICINE (2021)

Article Multidisciplinary Sciences

Ability of artificial intelligence to detect T1 esophageal squamous cell carcinoma from endoscopic videos and the effects of real-time assistance

Sho Shiroma et al.

Summary: The study demonstrated that using artificial intelligence with deep learning for diagnosis could be beneficial in endoscopic examinations. The AI system showed high accuracy in detecting superficial esophageal squamous cell carcinoma from esophagogastroduodenoscopy videos, and the sensitivity of endoscopists was improved with AI real-time support.

SCIENTIFIC REPORTS (2021)

Article Gastroenterology & Hepatology

Standalone performance of artificial intelligence for upper GI neoplasia: a meta-analysis

Julia Arribas et al.

Summary: Studies have evaluated the diagnostic performance of artificial intelligence in detecting and characterizing upper gastrointestinal lesions, showing a high overall accuracy for diagnosing any neoplastic lesion of the upper GI tract independently of the underlying condition.
Review Gastroenterology & Hepatology

Convolutional neural networks in the computer-aided diagnosis of Helicobacter pylori infection and non-causal comparison to physician endoscopists: a systematic review with meta-analysis

Babu P. Mohan et al.

Summary: The study found that AI based on deep learning performs similarly to physicians in the diagnosis of H. pylori infection, reaching an accuracy, sensitivity, and specificity of around 87%.

ANNALS OF GASTROENTEROLOGY (2021)

Article Gastroenterology & Hepatology

Artificial Intelligence-assisted System Improves Endoscopic Identification of Colorectal Neoplasms

Shin-ei Kudo et al.

CLINICAL GASTROENTEROLOGY AND HEPATOLOGY (2020)

News Item Gastroenterology & Hepatology

Deep-learning based detection of gastric precancerous conditions

Pedro Guimaraes et al.

Article Radiology, Nuclear Medicine & Medical Imaging

Prediction of the Depth of Tumor Invasion in Gastric Cancer: Potential Role of CT Radiomics

Yue Wang et al.

ACADEMIC RADIOLOGY (2020)

Article Gastroenterology & Hepatology

Prediction of Polyp Pathology Using Convolutional Neural Networks Achieves Resect and Discard Thresholds

Robin Zachariah et al.

AMERICAN JOURNAL OF GASTROENTEROLOGY (2020)

Article Gastroenterology & Hepatology

Potential of automatic diagnosis system with linked color imaging for diagnosis of Helicobacter pylori infection

Takeshi Yasuda et al.

DIGESTIVE ENDOSCOPY (2020)

Article Gastroenterology & Hepatology

A novel artificial intelligence system for the assessment of bowel preparation

Jie Zhou et al.

GASTROINTESTINAL ENDOSCOPY (2020)

Article Gastroenterology & Hepatology

Deep learning algorithms for automated detection of Crohn's disease ulcers by video capsule endoscopy

Eyal Klang et al.

GASTROINTESTINAL ENDOSCOPY (2020)

Article Surgery

Machine learning to predict early recurrence after oesophageal cancer surgery

S. A. Rahman et al.

BRITISH JOURNAL OF SURGERY (2020)

Article Gastroenterology & Hepatology

Diagnosing chronic atrophic gastritis by gastroscopy using artificial intelligence

Yaqiong Zhang et al.

DIGESTIVE AND LIVER DISEASE (2020)

Review Gastroenterology & Hepatology

Application of Artificial Intelligence to Gastroenterology and Hepatology

Catherine Le Berre et al.

GASTROENTEROLOGY (2020)

Review Gastroenterology & Hepatology

The impact of deep convolutional neural network-based artificial intelligence on colonoscopy outcomes: A systematic review with meta-analysis

Muhammad Aziz et al.

JOURNAL OF GASTROENTEROLOGY AND HEPATOLOGY (2020)

Review Gastroenterology & Hepatology

Accuracy of artificial intelligence-assisted detection of upper GI lesions: a systematic review and meta-analysis

Thomas K. L. Lui et al.

GASTROINTESTINAL ENDOSCOPY (2020)

Article Gastroenterology & Hepatology

Real-time assessment of video images for esophageal squamous cell carcinoma invasion depth using artificial intelligence

Yusaku Shimamoto et al.

JOURNAL OF GASTROENTEROLOGY (2020)

Article Radiology, Nuclear Medicine & Medical Imaging

Convolutional neural network-based dosimetry evaluation of esophageal radiation treatment planning

Dashan Jiang et al.

MEDICAL PHYSICS (2020)

Article Computer Science, Interdisciplinary Applications

Esophagus segmentation from planning CT images using an atlas-based deep learning approach

Joao Otavio Bandeira Diniz et al.

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE (2020)

Review Gastroenterology & Hepatology

Artificial Intelligence in Gastrointestinal Endoscopy

Alexander P. Abadir et al.

CLINICAL ENDOSCOPY (2020)

Article Gastroenterology & Hepatology

Novel computer-assisted diagnosis system for endoscopic disease activity in patients with ulcerative colitis

Tsuyoshi Ozawa et al.

GASTROINTESTINAL ENDOSCOPY (2019)

Article Gastroenterology & Hepatology

Application of convolutional neural networks for evaluating Helicobacter pylori infection status on the basis of endoscopic images

Satoki Shichijo et al.

SCANDINAVIAN JOURNAL OF GASTROENTEROLOGY (2019)

Editorial Material Gastroenterology & Hepatology

Endoscopic Surveillance of Barrett's Esophagus Using Volumetric Laser Endomicroscopy With Artificial Intelligence Image Enhancement

Arvind J. Trindade et al.

GASTROENTEROLOGY (2019)

Article Gastroenterology & Hepatology

High Accuracy of Convolutional Neural Network for Evaluation of Helicobacter pylori Infection Based on Endoscopic Images: Preliminary Experience

Wenfang Zheng et al.

CLINICAL AND TRANSLATIONAL GASTROENTEROLOGY (2019)

Article Gastroenterology & Hepatology

Accurate Classification of Diminutive Colorectal Polyps Using Computer-Aided Analysis

Peng-Jen Chen et al.

GASTROENTEROLOGY (2018)

Article Gastroenterology & Hepatology

Deep learning analyzes Helicobacter pylori infection by upper gastrointestinal endoscopy images

Takumi Itoh et al.

ENDOSCOPY INTERNATIONAL OPEN (2018)

Article Engineering, Biomedical

High-Performance CAD-CTC Scheme Using Shape Index, Multiscale Enhancement Filters, and Radiomic Features

Yacheng Ren et al.

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING (2017)

Review Gastroenterology & Hepatology

Performance measures for lower gastrointestinal endoscopy: a European Society of Gastrointestinal Endoscopy (ESGE) quality improvement initiative

Michal F. Kaminski et al.

UNITED EUROPEAN GASTROENTEROLOGY JOURNAL (2017)

Article Gastroenterology & Hepatology

Exploring the clinical potential of an automatic colonic polyp detection method based on the creation of energy maps

Gloria Fernandez-Esparrach et al.

ENDOSCOPY (2016)

Review Gastroenterology & Hepatology

Interval Colorectal Cancer After Colonoscopy: Exploring Explanations and Solutions

Jeffrey Adler et al.

AMERICAN JOURNAL OF GASTROENTEROLOGY (2015)

Article Computer Science, Interdisciplinary Applications

Polyp-Alert: Near real-time feedback during colonoscopy

Yi Wang et al.

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE (2015)

Article Gastroenterology & Hepatology

Adenoma detection rates decline with increasing procedural hours in an endoscopist's workload

Majid A. Almadi et al.

CANADIAN JOURNAL OF GASTROENTEROLOGY AND HEPATOLOGY (2015)

Article Gastroenterology & Hepatology

A Resect and Discard Strategy Would Improve Cost-Effectiveness of Colorectal Cancer Screening

Cesare Hassan et al.

CLINICAL GASTROENTEROLOGY AND HEPATOLOGY (2010)

Article Gastroenterology & Hepatology

Computer-aided classification of colorectal polyps based on vascular patterns: a pilot study

J. J. W. Tischendorf et al.

ENDOSCOPY (2010)

Article Gastroenterology & Hepatology

The Boston bowel preparation scale: a valid and reliable instrument for colonoscopy-oriented research

Edwin J. Lai et al.

GASTROINTESTINAL ENDOSCOPY (2009)

Article Computer Science, Information Systems

Helicobacter pylori -: Related gastric histology classification using support-vector-machine-based feature selection

Chun-Rong Huang et al.

IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE (2008)

Article Gastroenterology & Hepatology

Wide variation in adenoma detection rates at screening flexible sigmoidoscopy

W Atkin et al.

GASTROENTEROLOGY (2004)