The future of endoscopy: Advances in endoscopic image innovations

Deep learning-based anatomical position recognition for gastroscopic examination

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.

Recent Advances and Future Challenges in the Field of Digestive Diseases

Digestive diseases are a rapidly evolving area of clinical and research [...].

Current status and future perspective of linked color imaging for gastric cancer screening: a literature review

Screening endoscopy has advanced to facilitate improvements in the detection and prognosis of gastric cancer. However, most early gastric cancers (EGCs) have subtle morphological or color features that are difficult to detect by white-light imaging (WLI); thus, even well-trained endoscopists can miss EGC when using this conventional endoscopic approach. This review summarizes the current and future status of linked color imaging (LCI), a new image-enhancing endoscopy (IEE) method, for gastric screening. LCI has been shown to produce bright images even at a distant view and provide excellent visibility of gastric cancer due to high color contrast relative to the surrounding tissue. LCI delineates EGC as orange-red and intestinal metaplasia as purple, regardless of a history of Helicobacter pylori (Hp) eradication, and contributes to the detection of superficial EGC. Moreover, LCI assists in the determination of Hp infection status, which is closely related to the risk of developing gastric cancer. Transnasal endoscopy (ultra-thin) using LCI is also useful for identifying gastric neoplastic lesions. Recently, several prospective studies have demonstrated that LCI has a higher detection ratio for gastric cancer than WLI. We believe that LCI should be used in routine upper gastrointestinal endoscopies.

Analysis of Texture and Color Enhancement Imaging for Improving the Visibility of Non-polypoid Colorectal Lesions

INTRODUCTION

An endoscopic system using 5-color light-emitting diodes (LEDs) (EVIS X1; Olympus Co., Tokyo, Japan), which includes texture and color enhancement imaging (TXI), has been released. In this study, we analyzed the effects of TXI on the visibility of non-polypoid colorectal lesions and its diagnostic accuracy.

METHODS

We reviewed 101 non-polypoid lesions from 26 patients observed with white light imaging (WLI), narrow band imaging (NBI), and TXI. One representative image of each mode was evaluated by 6 endoscopists using a polyp visibility score of 4 (excellent) to 1 (poor). We calculated the color difference (CD) values for each lesion in the three modes. For tumor characteristics, one representative image of TXI and NBI magnification was evaluated by 3 experts according to a NBI classification.

RESULTS

The least squares means [95% confidence interval] of polyp visibility score of TXI (3.42 [3.06-3.77]) was significantly higher than that of WLI (2.85 [2.49-3.20], p < 0.001) but not that of NBI (3.33 [2.98-3.69], p = 0.258). The CD value of TXI (13.3 ± 6.3) was higher than that of WLI (9.7 ± 6.0, p < 0.001) but not that of NBI (13.1 ± 6.8, p = 0.81). For sessile serrated lesions, the CD value of TXI (11.1 ± 4.4) tended to be lower than that of NBI (12.6 ± 6.0, p = 0.07). The diagnostic accuracy and confidence level of magnification for NBI were significantly better than those for TXI (87.1 vs. 80.5%, p = 0.027, 87.5 vs. 62.7%, p < 0.001, respectively).

CONCLUSION

TXI showed better visibility than WLI in terms of the endoscopist's score and CD value and may improve polyp detection.

Compact Smartphone-Based Laser Speckle Contrast Imaging Endoscope Device for Point-of-Care Blood Flow Monitoring

Laser speckle contrast imaging (LSCI) is a powerful visualization tool for quantifying blood flow in tissues, providing simplicity of configuration, ease of use, and intuitive results. With recent advancements, smartphone and camera technologies are suitable for the development of smartphone-based LSCI applications for point-of-care (POC) diagnosis. A smartphone-based portable LSCI endoscope system was validated for POC diagnosis of vascular disorders. The endoscope consisted of compact LED and laser illumination, imaging optics, and a flexible fiberscope assembled in a 3D-printed hand-held cartridge for access to body cavities and organs. A smartphone’s rear camera was mounted thereto, enabling endoscopy, LSCI image acquisition, and processing. Blood flow imaging was calibrated in a perfused tissue phantom consisting of a microparticle solution pumped at known rates through tissue-mimicking gel and validated in a live rat model of BBN-induced bladder cancer. Raw LSCI images successfully visualized phantom flow: speckle flow index showed linearity with the pump flow rate. In the rat model, healthy and cancerous bladders were distinguishable in structure and vasculature. The smartphone-based low-cost portable mobile endoscope for monitoring blood flow and perfusion shows promise for preclinical applications and may be suitable for primary diagnosis at home or as a cost-effective POC testing assay.

Emerging texture and color enhancement imaging in early gastric cancer

Screening endoscopy improves detection and prognosis of patients with gastric cancer. However, even expert endoscopists can miss early gastric cancer under standard white light imaging. Texture and color enhancement imaging (TXI) is an image-enhanced endoscopy that enhances brightness, surface irregularities such elevation or depression, and subtle color changes. A few image-oriented studies have compared the gastric color differences between neoplastic and peripheral areas under both white light imaging and TXI. The results not only suggested that the overall color differences to be more pronounced in TXI, but also that TXI mode 1 was superior to white light imaging in the visibility of early gastric cancer. Despite the promising results in these initial studies, it is unclear whether the superiority of the image-enhanced endoscopy will translate into an improvement in early gastric cancer detection in real practice. Therefore, large-scale prospective studies are necessary to investigate the efficacy of this new technology in the evaluation of patients undergoing screening endoscopy.

Development of artificial intelligence technology in diagnosis, treatment, and prognosis of colorectal cancer

Artificial intelligence (AI) technology has made leaps and bounds since its invention. AI technology can be subdivided into many technologies such as machine learning and deep learning. The application scope and prospect of different technologies are also totally different. Currently, AI technologies play a pivotal role in the highly complex and wide-ranging medical field, such as medical image recognition, biotechnology, auxiliary diagnosis, drug research and development, and nutrition. Colorectal cancer (CRC) is a common gastrointestinal cancer that has a high mortality, posing a serious threat to human health. Many CRCs are caused by the malignant transformation of colorectal polyps. Therefore, early diagnosis and treatment are crucial to CRC prognosis. The methods of diagnosing CRC are divided into imaging diagnosis, endoscopy, and pathology diagnosis. Treatment methods are divided into endoscopic treatment, surgical treatment, and drug treatment. AI technology is in the weak era and does not have communication capabilities. Therefore, the current AI technology is mainly used for image recognition and auxiliary analysis without in-depth communication with patients. This article reviews the application of AI in the diagnosis, treatment, and prognosis of CRC and provides the prospects for the broader application of AI in CRC.

Advances in optical gastrointestinal endoscopy: a technical review

Optical endoscopy is the primary diagnostic and therapeutic tool for management of gastrointestinal (GI) malignancies. Most GI neoplasms arise from precancerous lesions; thus, technical innovations to improve detection and diagnosis of precancerous lesions and early cancers play a pivotal role in improving outcomes. Over the last few decades, the field of GI endoscopy has witnessed enormous and focused efforts to develop and translate accurate, user-friendly, and minimally invasive optical imaging modalities. From a technical point of view, a wide range of novel optical techniques is now available to probe different aspects of light-tissue interaction at macroscopic and microscopic scales, complementing white light endoscopy. Most of these new modalities have been successfully validated and translated to routine clinical practice. Herein, we provide a technical review of the current status of existing and promising new optical endoscopic imaging technologies for GI cancer screening and surveillance. We summarize the underlying principles of light-tissue interaction, the imaging performance at different scales, and highlight what is known about clinical applicability and effectiveness. Furthermore, we discuss recent discovery and translation of novel molecular probes that have shown promise to augment endoscopists' ability to diagnose GI lesions with high specificity. We also review and discuss the role and potential clinical integration of artificial intelligence-based algorithms to provide decision support in real time. Finally, we provide perspectives on future technology development and its potential to transform endoscopic GI cancer detection and diagnosis.

Evaluation of novel LCI CAD EYE system for real time detection of colon polyps

Background

Linked color imaging (LCI) has been shown to be effective in multiple randomized controlled trials for enhanced colorectal polyp detection. Recently, artificial intelligence (AI) with deep learning through convolutional neural networks has dramatically improved and is increasingly recognized as a promising new technique for enhancing colorectal polyp detection.

Aim

This study aims to evaluate a newly developed computer-aided detection (CAD) system in combination with LCI for colorectal polyp detection.

Methods

First, a convolutional neural network was trained for colorectal polyp detection in combination with the LCI technique using a dataset of anonymized endoscopy videos. For validation, 240 polyps within fully recorded endoscopy videos in LCI mode, covering the entire spectrum of adenomatous histology, were used. Sensitivity (true-positive rate per lesion) and false-positive frames in a full procedure were assessed.

Results

The new CAD system used in LCI mode could process at least 60 frames per second, allowing for real-time video analysis. Sensitivity (true-positive rate per lesion) was 100%, with no lesion being missed. The calculated false-positive frame rate was 0.001%. Among the 240 polyps, 34 were sessile serrated lesions. The detection rate for sessile serrated lesions with the CAD system used in LCI mode was 100%.

Conclusions

The new CAD system used in LCI mode achieved a 100% sensitivity per lesion and a negligible false-positive frame rate. Note that the new CAD system used in LCI mode also specifically allowed for detection of serrated lesions in all cases. Accordingly, the AI algorithm introduced here for the first time has the potential to dramatically improve the quality of colonoscopy.

Use of Artificial Intelligence to Improve the Quality Control of Gastrointestinal Endoscopy

With the rapid development of science and technology, artificial intelligence (AI) systems are becoming ubiquitous, and their utility in gastroenteroscopy is beginning to be recognized. Digestive endoscopy is a conventional and reliable method of examining and diagnosing digestive tract diseases. However, with the increase in the number and types of endoscopy, problems such as a lack of skilled endoscopists and difference in the professional skill of doctors with different degrees of experience have become increasingly apparent. Most studies thus far have focused on using computers to detect and diagnose lesions, but improving the quality of endoscopic examination process itself is the basis for improving the detection rate and correctly diagnosing diseases. In the present study, we mainly reviewed the role of AI in monitoring systems, mainly through the endoscopic examination time, reducing the blind spot rate, improving the success rate for detecting high-risk lesions, evaluating intestinal preparation, increasing the detection rate of polyps, automatically collecting maps and writing reports. AI can even perform quality control evaluations for endoscopists, improve the detection rate of endoscopic lesions and reduce the burden on endoscopists.

Lifestyles, genetics, and future perspectives on gastric cancer in east Asian populations

The prevalence of gastric cancer (GC) differs among regions worldwide, with the highest occurrence in east Asia. Thus, its etiology, with respect to ethnic background, environmental factors, and lifestyles, is also thought to differ essentially. In addition, etiology of GC is speculated to be changing due to the recent decrease in the Helicobacter pylori (H. pylori) infection in Japan. State-of-the-art somatic/germline cancer genomics has clarified the etiologies of gastric carcinogenesis. In this review article, we summarize past and present milestones in our understanding of GC achieved through genomic approaches, including a recent report that revealed higher-than-expected frequencies of GCs attributed to east Asian-specific germline variants in ALDH2 or CDH1 in combination with lifestyles. Based on this updated knowledge, we also discuss the possible impact of and high-risk approaches for GCs in the upcoming "H. pylori-negative era."

Novel artificial intelligence-driven software significantly shortens the time required for annotation in computer vision projects

Background and study aims The contribution of artificial intelligence (AI) to endoscopy is rapidly expanding. Accurate labelling of source data (video frames) remains the rate-limiting step for such projects and is a painstaking, cost-inefficient, time-consuming process. A novel software platform, Cord Vision (CdV) allows automated annotation based on “embedded intelligence.” The user manually labels a representative proportion of frames in a section of video (typically 5 %), to create ‘micro-modelsʼ which allow accurate propagation of the label throughout the remaining video frames. This could drastically reduce the time required for annotation.

Methods We conducted a comparative study with an open-source labelling platform (CVAT) to determine speed and accuracy of labelling.

Results Across 5 users, CdV resulted in a significant increase in labelling performance (P < 0.001) compared to CVAT for bounding box placement.

Conclusions This advance represents a valuable first step in AI-image analysis projects.

Application of Artificial Intelligence in Gastrointestinal Endoscopy

Artificial intelligence (AI), also known as computer-aided diagnosis, is a technology that enables machines to process information and functions at or above human level and has great potential in gastrointestinal endoscopy applications. At present, the research on medical image recognition usually adopts the deep-learning algorithm based on the convolutional neural network. AI has been used in gastrointestinal endoscopy including esophagogastroduodenoscopy, capsule endoscopy, colonoscopy, etc. AI can help endoscopic physicians improve the diagnosis rate of various lesions, reduce the rate of missed diagnosis, improve the quality of endoscopy, assess the severity of the disease, and improve the efficiency of endoscopy. The diversity, susceptibility, and imaging specificity of gastrointestinal endoscopic images are all difficulties and challenges on the road to intelligence. We need more large-scale, high-quality, multicenter prospective studies to explore the clinical applicability of AI, and ethical issues need to be taken into account.

Artificial intelligence and its impact on quality improvement in upper and lower gastrointestinal endoscopy

Artificial intelligence (AI) and its application in medicine has grown large interest. Within gastrointestinal (GI) endoscopy, the field of colonoscopy and polyp detection is the most investigated, however, upper GI follows the lead. Since endoscopy is performed by humans, it is inherently an imperfect procedure. Computer-aided diagnosis may improve its quality by helping prevent missing lesions and supporting optical diagnosis for those detected. An entire evolution in AI systems has been established in the last decades, resulting in optimization of the diagnostic performance with lower variability and matching or even outperformance of expert endoscopists. This shows a great potential for future quality improvement of endoscopy, given the outstanding diagnostic features of AI. With this narrative review, we highlight the potential benefit of AI to improve overall quality in daily endoscopy and describe the most recent developments for characterization and diagnosis as well as the recent conditions for regulatory approval.

GIE Editorial Board top 10 topics: advances in GI endoscopy in 2019

The American Society for Gastrointestinal Endoscopy's GIE Editorial Board reviewed original endoscopy-related articles published during 2019 in Gastrointestinal Endoscopy and 10 other leading medical and gastroenterology journals. Votes from each individual member were tallied to identify a consensus list of 10 topic areas of major advances in GI endoscopy. Individual board members summarized important findings published in these 10 areas of disinfection, artificial intelligence, bariatric endoscopy, adenoma detection, polypectomy, novel imaging, Barrett's esophagus, third space endoscopy, interventional EUS, and training. This document summarizes these "top 10" endoscopic advances of 2019.

Comparison of endoscopic visibility and miss rate for early gastric cancers after Helicobacter pylori eradication with white-light imaging versus linked color imaging

BACKGROUND AND AIM

We aimed to investigate whether linked color imaging (LCI) improves endoscopic visibility of early gastric cancers (EGC) after Helicobacter pylori eradication, which are often difficult to detect, and reduces the miss rate when compared with white-light imaging (WLI).

METHODS

The visibility study used two images, one each with WLI and LCI, from 84 consecutive EGC after H. pylori eradication. Endoscopic visibility was evaluated using a visibility score and color difference (CD) value. To analyze miss rates, we studied a library of recorded videos using both WLI and LCI for 70 other consecutive patients after H. pylori eradication, among whom 19 had EGC. Endoscopic screening was done using the same protocol to map the entire stomach. Six endoscopists reviewed the videos in a randomized order. Miss rates of EGC were compared among the modalities.

RESULTS

Mean [(±standard deviation) visibility scores with LCI were significantly higher than those with WLI (3.19 ± 0.84 vs 2.52 ± 0.98, P < 0.001), as were mean CD values (26.3 ± 9.1 vs 13.6 ± 6.3, P < 0.001). Miss rates of the six endoscopists were significantly lower with LCI than with WLI (30.7% vs 64.9%, P < 0.001). Both expert and trainee endoscopists had significantly better results with LCI than with WLI.

CONCLUSIONS

Linked color imaging significantly improved the visibility of EGC after H. pylori eradication compared with WLI using both subjective and objective criteria. Furthermore, LCI significantly reduced miss rates of these lesions compared with WLI.

Standing-type magnetically guided capsule endoscopy versus gastroscopy for gastric examination: multicenter blinded comparative trial

AIM

To compare feasibility and safety after gastrointestinal checkup by standing-type magnetically controlled capsule endoscopy (SMCE) and conventional gastroscopy.

METHODS

This was a prospective multicenter, blinded study that compared SMCE with gastroscopy in patients from April 2018 to July 2018. All patients first underwent SMCE and then subsequently had gastroscopy with i.v. anesthesia. We calculated the compliance rates of gastric lesion detection by SMCE using gastroscopy as the standard. Capsule retention rate, incidence of adverse events, and patient satisfaction were documented throughout the study.

RESULTS

One hundred and sixty-one patients who completed SMCE and gastroscopy were included in the analysis. Positive compliance rate among SMCE and gastroscopy was 92.0% (95% CI: 80.77%-97.78%). Negative compliance rate was 95.5% (89.80%, 98.52%). Moreover, overall compliance rate was 94.41% (89.65%, 97.41%). Sixty-four pathological outcomes were identified. Of these 64 outcomes, 50 were detected by both procedures. The gastroscopy method neglected seven findings (such as five erosions, one polyp, and one ulcer). Furthermore, SMCE also overlooked seven lesions (i.e. one erosion, two polyps, one atrophy, and three submucosal tumors). Capsule retention or related adverse events were not reported.

CONCLUSION

Standing-type magnetically controlled capsule endoscopy provides equivalent agreement with gastroscopy and may be useful for screening of gastric illnesses without any anesthesia.

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.