Deep learning analyzes Helicobacter pylori infection by upper gastrointestinal endoscopy images

A systematic review of the role of non-magnified endoscopy for the assessment of H. pylori infection

Background and study aims  There is growing interest in the endoscopic recognition of Helicobacter pylori infection, and application to routine practice. We present a systematic review of the current literature regarding diagnosis of H. pylori during standard (non-magnified) endoscopy, including adjuncts such as image enhancement and computer-aided diagnosis. Method  The Medline and Cochrane databases were searched for studies investigating performance of non-magnified optical diagnosis for H. pylori , or those which characterized mucosal features associated with H. pylori infection. Studies were preferred with a validated reference test as the comparator, although they were included if at least one validated reference test was used. Results  Twenty suitable studies were identified and included for analysis. In total, 4,703 patients underwent investigation including white light endoscopy, narrow band imaging, i-scan, blue-laser imaging, and computer-aided diagnostic techniques. The endoscopic features of H. pylori infection observed using each modality are discussed and diagnostic accuracies reported. The regular arrangement of collecting venules (RAC) is an important predictor of the H. pylori -naïve stomach. "Mosaic" and "mottled" patterns have a positive association with H. pylori infection. The "cracked" pattern may be a predictor of an H. pylori- negative stomach following eradication. Conclusions  This review summarizes current progress made in endoscopic diagnosis of H. pylori infection. At present there is no single diagnostic approach that provides validated diagnostic accuracy. Further prospective studies are required, as is development of a validated classification system. Early studies in computer-aided diagnosis suggest potential for a high level of accuracy but real-time results are awaited.

Artificial intelligence in luminal endoscopy

Artificial intelligence is a strong focus of interest for global health development. Diagnostic endoscopy is an attractive substrate for artificial intelligence with a real potential to improve patient care through standardisation of endoscopic diagnosis and to serve as an adjunct to enhanced imaging diagnosis. The possibility to amass large data to refine algorithms makes adoption of artificial intelligence into global practice a potential reality. Initial studies in luminal endoscopy involve machine learning and are retrospective. Improvement in diagnostic performance is appreciable through the adoption of deep learning. Research foci in the upper gastrointestinal tract include the diagnosis of neoplasia, including Barrett's, squamous cell and gastric where prospective and real-time artificial intelligence studies have been completed demonstrating a benefit of artificial intelligence-augmented endoscopy. Deep learning applied to small bowel capsule endoscopy also appears to enhance pathology detection and reduce capsule reading time. Prospective evaluation including the first randomised trial has been performed in the colon, demonstrating improved polyp and adenoma detection rates; however, these appear to be relevant to small polyps. There are potential additional roles of artificial intelligence relevant to improving the quality of endoscopic examinations, training and triaging of referrals. Further large-scale, multicentre and cross-platform validation studies are required for the robust incorporation of artificial intelligence-augmented diagnostic luminal endoscopy into our routine clinical practice.

Can image-enhanced endoscopy improve the diagnosis of Kyoto classification of gastritis in the clinical setting?

Endoscopic diagnosis of Helicobacter pylori (H. pylori) infection, the most common cause of gastric cancer, is very important to clarify high-risk patients of gastric cancer for reducing morbidity and mortality of gastric cancer. Recently, the Kyoto classification of gastritis was developed based on the endoscopic characteristics of H. pylori infection-associated gastritis for clarifying H. pylori infection status and evaluating risk factors of gastric cancer. Recently, magnifying endoscopy with narrow-band imaging (NBI) has reported benefits of the accuracy and reproducibility of endoscopic diagnosis for H. pylori-related premalignant lesions. In addition to NBI, various types of image-enhanced endoscopies (IEEs) are available including autofluorescence imaging, blue laser imaging, and linked color imaging. This review focuses on understanding the clinical applications and the corresponding evidences shown to improve the diagnosis of gastritis based on Kyoto classification using currently available advanced technologies of IEEs.

Application of Artificial Intelligence to Gastroenterology and Hepatology

Since 2010, substantial progress has been made in artificial intelligence (AI) and its application to medicine. AI is explored in gastroenterology for endoscopic analysis of lesions, in detection of cancer, and to facilitate the analysis of inflammatory lesions or gastrointestinal bleeding during wireless capsule endoscopy. AI is also tested to assess liver fibrosis and to differentiate patients with pancreatic cancer from those with pancreatitis. AI might also be used to establish prognoses of patients or predict their response to treatments, based on multiple factors. We review the ways in which AI may help physicians make a diagnosis or establish a prognosis and discuss its limitations, knowing that further randomized controlled studies will be required before the approval of AI techniques by the health authorities.

Artificial Intelligence in Gastrointestinal Endoscopy in a Resource-constrained Setting: A Reality Check

Artificial intelligence (AI) is being increasingly explored in different domains of gastroenterology, particularly in endoscopic image analysis, cancer screening, and prognostication models. It is widely touted to become an integral part of routine endoscopies, considering the bulk of data handled by endoscopists and the complex nature of critical analyses performed. However, the application of AI in endoscopy in resource-constrained settings remains fraught with problems. We conducted an extensive literature review using the PubMed database on articles covering the application of AI in endoscopy and the difficulties encountered in resource-constrained settings. We have tried to summarize in the present review the potential problems that may hinder the application of AI in such settings. Hopefully, this review will enable endoscopists and health policymakers to ponder over these issues before trying to extrapolate the advancements of AI in technically advanced settings to those having constraints at multiple levels.

How to cite this article: Anirvan P, Meher D, Singh SP. Artificial Intelligence in Gastrointestinal Endoscopy in a Resource-constrained Setting: A Reality Check. Euroasian J Hepato-Gastroenterol 2020;10(2): 92–97.

Deep learning with convolutional neural networks for identification of liver masses and hepatocellular carcinoma: A systematic review

BACKGROUND

Artificial intelligence, such as convolutional neural networks (CNNs), has been used in the interpretation of images and the diagnosis of hepatocellular cancer (HCC) and liver masses. CNN, a machine-learning algorithm similar to deep learning, has demonstrated its capability to recognise specific features that can detect pathological lesions.

AIM

To assess the use of CNNs in examining HCC and liver masses images in the diagnosis of cancer and evaluating the accuracy level of CNNs and their performance.

METHODS

The databases PubMed, EMBASE, and the Web of Science and research books were systematically searched using related keywords. Studies analysing pathological anatomy, cellular, and radiological images on HCC or liver masses using CNNs were identified according to the study protocol to detect cancer, differentiating cancer from other lesions, or staging the lesion. The data were extracted as per a predefined extraction. The accuracy level and performance of the CNNs in detecting cancer or early stages of cancer were analysed. The primary outcomes of the study were analysing the type of cancer or liver mass and identifying the type of images that showed optimum accuracy in cancer detection.

RESULTS

A total of 11 studies that met the selection criteria and were consistent with the aims of the study were identified. The studies demonstrated the ability to differentiate liver masses or differentiate HCC from other lesions (n = 6), HCC from cirrhosis or development of new tumours (n = 3), and HCC nuclei grading or segmentation (n = 2). The CNNs showed satisfactory levels of accuracy. The studies aimed at detecting lesions (n = 4), classification (n = 5), and segmentation (n = 2). Several methods were used to assess the accuracy of CNN models used.

CONCLUSION

The role of CNNs in analysing images and as tools in early detection of HCC or liver masses has been demonstrated in these studies. While a few limitations have been identified in these studies, overall there was an optimal level of accuracy of the CNNs used in segmentation and classification of liver cancers images.

Challenge in the new era: Translational medicine in gastrointestinal endoscopy and early cancer

Translational medicine is a new medical model that has emerged over the past 20 years and is dedicated to bridging the gap between basic and clinical research. At the same time, the diagnosis and treatment of digestive diseases, especially gastrointestinal endoscopy, have been rapidly developed. The emergence of new techniques for gastrointestinal endoscopy has changed the therapeutic spectrum of some diseases and brought huge benefits to patients. Targeted therapy has positively affected the individualized and precise treatment of patients with advanced gastrointestinal cancer. The construction of a standardized biobank provides a strong guarantee for clinicians to conduct translational medical research. Translational medicine has brought good development opportunities, but it also faces challenges. The training of translational medicine researchers and the transformation of educational models require sufficient attention for further development.

Application of artificial intelligence in gastrointestinal endoscopy

With recent significant improvements in artificial intelligence (AI), especially in the field of deep learning, an increasing number of studies have evaluated the use of AI in endoscopy to detect and diagnose gastrointestinal (GI) lesions. The present review summarizes current publications on the use of AI in GI endoscopy and focuses on the challenges and future of AI-aided systems. We expect AI to provide an effective and practical method for endoscopists in lesion detection and characterization as well as in quality control in endoscopy. However, so far, most studies have remained at the preclinical stage. More attention should be paid in the future to the use of AI in real-life clinical applications.

A technical review of artificial intelligence as applied to gastrointestinal endoscopy: clarifying the terminology

Background and aim  The growing number of publications on the application of artificial intelligence (AI) in medicine underlines the enormous importance and potential of this emerging field of research. In gastrointestinal endoscopy, AI has been applied to all segments of the gastrointestinal tract most importantly in the detection and characterization of colorectal polyps. However, AI research has been published also in the stomach and esophagus for both neoplastic and non-neoplastic disorders. The various technical as well as medical aspects of AI, however, remain confusing especially for non-expert physicians. This physician-engineer co-authored review explains the basic technical aspects of AI and provides a comprehensive overview of recent publications on AI in gastrointestinal endoscopy. Finally, a basic insight is offered into understanding publications on AI in gastrointestinal endoscopy.

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

OBJECTIVES

Application of artificial intelligence in gastrointestinal endoscopy is increasing. The aim of the study was to examine the accuracy of convolutional neural network (CNN) using endoscopic images for evaluating Helicobacter pylori (H. pylori) infection.

METHODS

Patients who received upper endoscopy and gastric biopsies at Sir Run Run Shaw Hospital (January 2015-June 2015) were retrospectively searched. A novel Computer-Aided Decision Support System that incorporates CNN model (ResNet-50) based on endoscopic gastric images was developed to evaluate for H. pylori infection. Diagnostic accuracy was evaluated in an independent validation cohort. H. pylori infection was defined by the presence of H. pylori on immunohistochemistry testing on gastric biopsies and/or a positive 13C-urea breath test.

RESULTS

Of 1,959 patients, 1,507 (77%) including 847 (56%) with H. pylori infection (11,729 gastric images) were assigned to the derivation cohort, and 452 (23%) including 310 (69%) with H. pylori infection (3,755 images) were assigned to the validation cohort. The area under the curve for a single gastric image was 0.93 (95% confidence interval [CI] 0.92-0.94) with sensitivity, specificity, and accuracy of 81.4% (95% CI 79.8%-82.9%), 90.1% (95% CI 88.4%-91.7%), and 84.5% (95% CI 83.3%-85.7%), respectively, using an optimal cutoff value of 0.3. Area under the curve for multiple gastric images (8.3 ± 3.3) per patient was 0.97 (95% CI 0.96-0.99) with sensitivity, specificity, and accuracy of 91.6% (95% CI 88.0%-94.4%), 98.6% (95% CI 95.0%-99.8%), and 93.8% (95% CI 91.2%-95.8%), respectively, using an optimal cutoff value of 0.4.

DISCUSSION

In this pilot study, CNN using multiple archived gastric images achieved high diagnostic accuracy for the evaluation of H. pylori infection.

Prediction of future gastric cancer risk using a machine learning algorithm and comprehensive medical check-up data: A case-control study

A comprehensive screening method using machine learning and many factors (biological characteristics, Helicobacter pylori infection status, endoscopic findings and blood test results), accumulated daily as data in hospitals, could improve the accuracy of screening to classify patients at high or low risk of developing gastric cancer. We used XGBoost, a classification method known for achieving numerous winning solutions in data analysis competitions, to capture nonlinear relations among many input variables and outcomes using the boosting approach to machine learning. Longitudinal and comprehensive medical check-up data were collected from 25,942 participants who underwent multiple endoscopies from 2006 to 2017 at a single facility in Japan. The participants were classified into a case group (y = 1) or a control group (y = 0) if gastric cancer was or was not detected, respectively, during a 122-month period. Among 1,431 total participants (89 cases and 1,342 controls), 1,144 (80%) were randomly selected for use in training 10 classification models; the remaining 287 (20%) were used to evaluate the models. The results showed that XGBoost outperformed logistic regression and showed the highest area under the curve value (0.899). Accumulating more data in the facility and performing further analyses including other input variables may help expand the clinical utility.

Artificial intelligence and upper gastrointestinal endoscopy: Current status and future perspective

With recent breakthroughs in artificial intelligence, computer-aided diagnosis (CAD) for upper gastrointestinal endoscopy is gaining increasing attention. Main research focuses in this field include automated identification of dysplasia in Barrett's esophagus and detection of early gastric cancers. By helping endoscopists avoid missing and mischaracterizing neoplastic change in both the esophagus and the stomach, these technologies potentially contribute to solving current limitations of gastroscopy. Currently, optical diagnosis of early-stage dysplasia related to Barrett's esophagus can be precisely achieved only by endoscopists proficient in advanced endoscopic imaging, and the false-negative rate for detecting gastric cancer is approximately 10%. Ideally, these novel technologies should work during real-time gastroscopy to provide on-site decision support for endoscopists regardless of their skill; however, previous studies of these topics remain ex vivo and experimental in design. Therefore, the feasibility, effectiveness, and safety of CAD for upper gastrointestinal endoscopy in clinical practice remain unknown, although a considerable number of pilot studies have been conducted by both engineers and medical doctors with excellent results. This review summarizes current publications relating to CAD for upper gastrointestinal endoscopy from the perspective of endoscopists and aims to indicate what is required for future research and implementation in clinical practice.

Can endoscopists differentiate cytomegalovirus esophagitis from herpes simplex virus esophagitis based on gross endoscopic findings?

Differential diagnosis between herpes simplex virus (HSV) esophagitis and cytomegalovirus (CMV) esophagitis is challenging because there are many similarities and overlaps between their endoscopic features. The aims of this study were to investigate the implications of the endoscopic findings for the diagnosis of HSV and CMV esophagitis, and to develop a predictive model for differentiating CMV esophagitis from HSV esophagitis.Patients who underwent endoscopic examination and had pathologically-confirmed HSV or CMV esophagitis were eligible. Clinical characteristics and endoscopic features were retrospectively reviewed and categorized. A predictive model was developed based on parameters identified by logistic regression analysis.During the 8-year study period, HSV and CMV esophagitis were diagnosed in 85 and 63 patients, respectively. The endoscopic features of esophagitis were categorized and scored as follows: category 1 (-3 points): discrete ulcers or ulcers with vesicles, bullae, or pseudomembranes, category 2 (-2 points): coalescent or geographic ulcers, category 3 (1 points): ulcers with an uneven base, friability, or with a circumferential distribution, category 4 (2 points): punched-out, serpiginous, or healing ulcers with yellowish exudates. And previous history of transplantation (2 point) was included in the model as a discriminating clinical feature. The optimal cutoff point of the prediction model was 0 (area under receiver operating characteristic curve: 0.967), with positive scores favoring CMV esophagitis. Sensitivity, specificity, accuracy, positive predictive value, and negative predictive value were 96.8%, 89.4%, 92.6%, 87.3%, and 97.5%, respectively.The predictive model based on endoscopic and clinical findings appears to be accurate and useful in differentiating CMV esophagitis from HSV esophagitis.

Application of artificial intelligence in gastroenterology

Artificial intelligence (AI) using deep-learning (DL) has emerged as a breakthrough computer technology. By the era of big data, the accumulation of an enormous number of digital images and medical records drove the need for the utilization of AI to efficiently deal with these data, which have become fundamental resources for a machine to learn by itself. Among several DL models, the convolutional neural network showed outstanding performance in image analysis. In the field of gastroenterology, physicians handle large amounts of clinical data and various kinds of image devices such as endoscopy and ultrasound. AI has been applied in gastroenterology in terms of diagnosis, prognosis, and image analysis. However, potential inherent selection bias cannot be excluded in the form of retrospective study. Because overfitting and spectrum bias (class imbalance) have the possibility of overestimating the accuracy, external validation using unused datasets for model development, collected in a way that minimizes the spectrum bias, is mandatory. For robust verification, prospective studies with adequate inclusion/exclusion criteria, which represent the target populations, are needed. DL has its own lack of interpretability. Because interpretability is important in that it can provide safety measures, help to detect bias, and create social acceptance, further investigations should be performed.

Artificial intelligence in gastrointestinal endoscopy: The future is almost here

Artificial intelligence (AI) enables machines to provide unparalleled value in a myriad of industries and applications. In recent years, researchers have harnessed artificial intelligence to analyze large-volume, unstructured medical data and perform clinical tasks, such as the identification of diabetic retinopathy or the diagnosis of cutaneous malignancies. Applications of artificial intelligence techniques, specifically machine learning and more recently deep learning, are beginning to emerge in gastrointestinal endoscopy. The most promising of these efforts have been in computer-aided detection and computer-aided diagnosis of colorectal polyps, with recent systems demonstrating high sensitivity and accuracy even when compared to expert human endoscopists. AI has also been utilized to identify gastrointestinal bleeding, to detect areas of inflammation, and even to diagnose certain gastrointestinal infections. Future work in the field should concentrate on creating seamless integration of AI systems with current endoscopy platforms and electronic medical records, developing training modules to teach clinicians how to use AI tools, and determining the best means for regulation and approval of new AI technology.

Diagnosis of Helicobacter pylori infection

The progress this year in Helicobacter pylori diagnosis concerned essentially endoscopy and molecular techniques. New endoscopy techniques such as blue laser imaging and magnifying narrow band imaging allow the visualization of mucosal aspects representing H. pylori infection, intestinal metaplasia, and even ambiguous early gastric cancer. Several real-time PCRs have also been used either to quantify H. pylori or to detect mutations associated with clarithromycin resistance in gastric biopsies or applied on gastric juice, stool specimens, or the oral cavity. The presence of H. pylori in free-living amebae purified from wastewater and drinking water was also determined by PCR and sequencing, as well as culture from a few wastewater samples. Among the noninvasive methods, the urea breath test was used in different conditions, including with a new test meal, which is claimed to avoid the proton-pump inhibitor washout period before testing. Several articles concerning antibody detection and stool antigen test were also published.

Artificial intelligence diagnosis of Helicobacter pylori infection using blue laser imaging-bright and linked color imaging: a single-center prospective study

Background

Deep learning is a type of artificial intelligence (AI) that imitates the neural network in the brain. We generated an AI to diagnose Helicobacter pylori (H. pylori) infection using blue laser imaging (BLI)-bright and linked color imaging (LCI). The aim of this pilot study was to establish an AI diagnosing system that predicts H. pylori infection status using endoscopic images to improve the accuracy and productivity of endoscopic examination.

Methods

A total of 222 enrolled subjects (105 H. pylori-positive) underwent esophagogastroduodenoscopy and a serum test for H. pylori IgG antibodies. During esophagogastroduodenoscopy, an endoscopist sequentially took 3 still images of the lesser curvature of the stomach using white light imaging (WLI), BLI-bright, and LCI. EG-L580NW endoscopic equipment (FUJIFILM Co., Japan) was used for the study. The specifications of the AI were as follows: operating system, Linux; neural network, GoogLeNet; framework, Caffe; graphic processor unit, Geforce GTX TITAN X (NVIDIA Co., USA).

Results

The area under the curve (AUC) on receiver operating characteristics analysis was 0.66 for WLI. In contrast, the AUCs of BLI-bright and LCI were 0.96 and 0.95, respectively. The AUCs obtained for BLI-bright and LCI were significantly larger than those for WLI (P<0.01).

Conclusions

The results demonstrate that the developed AI has an excellent ability to diagnose H. pylori infection using BLI-bright and LCI. AI technology with image-enhanced endoscopy is likely to become a useful image diagnostic tool.