Current status and limitations of the newly developed endocytoscope GIF-Y0002 with reference to its diagnostic performance for common esophageal lesions

Endocytoscopic Observation of Esophageal Lesions: Our Own Experience and a Review of the Literature

This review outlines the process of the development of the endocytoscope (EC) with reference to previously reported studies including our own. The EC is an ultra-high-magnification endoscope capable of imaging at the cellular level. The esophagus is the most suitable site for EC observation because it is amenable to vital staining. The diagnosis of esophageal lesions using EC is based on nuclear density and nuclear abnormality, allowing biopsy histology to be omitted. The observation of nuclear abnormality requires a magnification of ×600 or higher using digital technology. Several staining methods have been proposed, but single staining with toluidine blue or methylene blue is most suitable because the contrast at the border of a cancerous area can be easily identified. A three-tier classification of esophageal lesions visualized by EC is proposed: Type 1 (non-cancerous), Type 2 (endocytoscopic borderline), and Type 3 (cancerous). Since characteristic EC images reflecting pathology can be obtained from non-cancerous esophageal lesions, a modified form of classification with four additional characteristic non-cancerous EC features has also been proposed. Recently, deep-learning AI for analysis of esophageal EC images has revealed that its diagnostic accuracy is comparable to that of expert pathologists.

AI analysis and modified type classification for endocytoscopic observation of esophageal lesions

Endocytoscopy (EC) facilitates real-time histological diagnosis of esophageal lesions in vivo. We developed a deep-learning artificial intelligence (AI) system for analysis of EC images and compared its diagnostic ability with that of an expert pathologist and nonexpert endoscopists. Our new AI was based on a vision transformer model (DeiT) and trained using 7983 EC images of the esophagus (2368 malignant and 5615 nonmalignant). The AI evaluated 114 randomly arranged EC pictures (33 ESCC and 81 nonmalignant lesions) from 38 consecutive cases. An expert pathologist and two nonexpert endoscopists also analyzed the same image set according to the modified type classification (adding four EC features of nonmalignant lesions to our previous classification). The area under the curve calculated from the receiver-operating characteristic curve for the AI analysis was 0.92. In per-image analysis, the overall accuracy of the AI, pathologist, and two endoscopists was 91.2%, 91.2%, 85.9%, and 83.3%, respectively. The kappa value between the pathologist and the AI, and between the two endoscopists and the AI showed moderate concordance; that between the pathologist and the two endoscopists showed poor concordance. In per-patient analysis, the overall accuracy of the AI, pathologist, and two endoscopists was 94.7%, 92.1%, 86.8%, and 89.5%, respectively. The modified type classification aided high overall diagnostic accuracy by the pathologist and nonexpert endoscopists. The diagnostic ability of the AI was equal or superior to that of the experienced pathologist. AI is expected to support endoscopists in diagnosing esophageal lesions based on EC images.

The development and clinical application of microscopic endoscopy for in vivo optical biopsies: Endocytoscopy and confocal laser endomicroscopy

Endoscopies are crucial for detecting and diagnosing diseases in gastroenterology, pulmonology, urology, and other fields. To accurately diagnose diseases, sample biopsies are indispensable and are currently considered the gold standard. However, random 4-quadrant biopsies have sampling errors and time delays. To provide intraoperative real-time microscopic images of suspicious lesions, microscopic endoscopy for in vivo optical biopsy has been developed, including endocytoscopy and confocal laser endomicroscopy. This article reviews recent advances in technology and clinical applications, as well as their shortcomings and future directions.

Clinical Efficacy of Endocytoscopy for Gastrointestinal Endoscopy

Endocytoscopy (EC) is a contact-type optical endoscope that allows in vivo cellular observation during gastrointestinal endoscopy and is now commercially available not only in Japan but also in Asian, European Union, and Middle Eastern countries. EC helps conduct a highly accurate pathological prediction without biopsy. Initially, EC was reported to be effective for esophageal diseases. Subsequently, its efficacy for stomach and colorectal diseases has been reported. In this narrative review, we searched for clinical studies that investigated the efficacy of EC. EC seems to accurately diagnose gastrointestinal diseases without biopsy. Most of the studies aimed to clarify the relationship between endocytoscopic findings of gastrointestinal neoplasia and pathological diagnosis. Some studies have investigated non-epithelial lesions or diseases, such as inflammatory bowel disease or infectious diseases. However, there are few high-level pieces of evidence, such as randomized trials; thus, further studies are needed.

Endocytoscopy: technology and clinical application in upper gastrointestinal tract

Over the past few years, the innovative field of magnifying endoscopy has been expanding with various cutting-edge technologies, one of which is endocytoscopy, to facilitate improvement in the detection and diagnosis of gastrointestinal lesions. Endocytoscopy is a novel ultra-high magnification endoscopic technique enabling high-quality in-vivo assessment of lesions found in the gastrointestinal tract with the use of intraprocedural stains. The main scope of this review article is to offer a closer look at the latest endocytoscopic technology and its clinical application in the upper gastrointestinal tract, especially in the esophagus and stomach, as well as to introduce readers to our simplified and up-to-date endocytoscopic classification, specifically developed for the esophagus and stomach, for the in-vivo assessment and diagnosis of esophageal and gastric lesions. Despite the good accuracy of endocytoscopy in the diagnosis of esophageal and gastric lesions in recent studies, some challenges still remain (e.g., staining method and standardized endocytoscopic classification). Through continuous evaluation and improvement of methods and skills, these challenges may be overcome thus establishing current techniques and classification, paving the way for further advances in the field of endocytoscopy and magnifying endoscopy. In all, endocytoscopy seems to aid in the in-vivo diagnosis of gastrointestinal tract lesions and may, in the future, revolutionize the field of in-vivo endoscopic diagnosis of gastrointestinal cancer, representing another step towards the so-called optical biopsy.

Dye solution optimizing staining conditions for in vivo endocytoscopy for normal villi and superficial epithelial tumors in the duodenum

Background

Vital staining is mandatory for endocytoscopy, which enables visualization of gastrointestinal mucosa at the cellular level. This study aimed to identify a dye solution that would optimize staining conditions for in vivo endocytoscopy in the duodenum, including normal villi and superficial non-ampullary duodenal epithelial tumors (SNADETs).

Methods

We performed endocytoscopy in 9 patients who had normal villi (27 sites) and 20 patients with SNADETs (20 sites). The normal sites were allocated to methylene blue (MB; 5/2.5/1%), toluidine blue (TB; 1/0.5/0.25%), and crystal violet (1/0.5/0.25%) staining. Based on the results of normal sites, we used 1% MB or 0.5% TB for staining SNADETs. Three reviewers, including endoscopists and pathologists, evaluated and scored the endocytoscopy images (1, poor; 2, moderate; 3, good) for general image quality and visibility of structure and nuclei. We calculated frequencies and compared the proportions of the highest score of 3 (good).

Results

The majority of scores of 3 for normal villi was given to 0.5% TB (81%), followed by 1% MB. For SNADETs, 1% MB showed significantly higher scores compared with 0.5% TB (P=0.035).

Conclusion

Among the dye solutions evaluated, 0.5% TB and 1% MB achieved the optimizing staining conditions for in vivo endocytoscopy for normal villi and SNADETs, respectively.

Diagnosis using deep-learning artificial intelligence based on the endocytoscopic observation of the esophagus

BACKGROUND AND AIMS

The endocytoscopic system (ECS) helps in virtual realization of histology and can aid in confirming histological diagnosis in vivo. We propose replacing biopsy-based histology for esophageal squamous cell carcinoma (ESCC) by using the ECS. We applied deep-learning artificial intelligence (AI) to analyse ECS images of the esophagus to determine whether AI can support endoscopists for the replacement of biopsy-based histology.

METHODS

A convolutional neural network-based AI was constructed based on GoogLeNet and trained using 4715 ECS images of the esophagus (1141 malignant and 3574 non-malignant images). To evaluate the diagnostic accuracy of the AI, an independent test set of 1520 ECS images, collected from 55 consecutive patients (27 ESCCs and 28 benign esophageal lesions) were examined.

RESULTS

On the basis of the receiver-operating characteristic curve analysis, the areas under the curve of the total images, higher magnification pictures, and lower magnification pictures were 0.85, 0.90, and 0.72, respectively. The AI correctly diagnosed 25 of the 27 ESCC cases, with an overall sensitivity of 92.6%. Twenty-five of the 28 non-cancerous lesions were diagnosed as non-malignant, with a specificity of 89.3% and an overall accuracy of 90.9%. Two cases of malignant lesions, misdiagnosed as non-malignant by the AI, were correctly diagnosed as malignant by the endoscopist. Among the 3 cases of non-cancerous lesions diagnosed as malignant by the AI, 2 were of radiation-related esophagitis and one was of gastroesophageal reflux disease.

CONCLUSION

AI is expected to support endoscopists in diagnosing ESCC based on ECS images without biopsy-based histological reference.

Advances toward fully automated in vivo assessment of oral epithelial dysplasia by nuclear endomicroscopy-A pilot study

BACKGROUND

Uncertainties in detection of oral epithelial dysplasia (OED) frequently result from sampling error especially in inflammatory oral lesions. Endomicroscopy allows non-invasive, "en face" imaging of upper oral epithelium, but parameters of OED are unknown.

METHODS

Mucosal nuclei were imaged in 34 toluidine blue-stained oral lesions with a commercial endomicroscopy. Histopathological diagnosis showed four biopsies in "dys-/neoplastic," 23 in "inflammatory," and seven in "others" disease groups. Strength of different assessment strategies of nuclear scoring, nuclear count, and automated nuclear analysis were measured by area under ROC curve (AUC) to identify histopathological "dys-/neoplastic" group. Nuclear objects from automated image analysis were visually corrected.

RESULTS

Best-performing parameters of nuclear-to-image ratios were the count of large nuclei (AUC=0.986) and 6-nearest neighborhood relation (AUC=0.896), and best parameters of nuclear polymorphism were the count of atypical nuclei (AUC=0.996) and compactness of nuclei (AUC=0.922). Excluding low-grade OED, nuclear scoring and count reached 100% sensitivity and 98% specificity for detection of dys-/neoplastic lesions. In automated analysis, combination of parameters enhanced diagnostic strength. Sensitivity of 100% and specificity of 87% were seen for distances of 6-nearest neighbors and aspect ratios even in uncorrected objects. Correction improved measures of nuclear polymorphism only. The hue of background color was stronger than nuclear density (AUC=0.779 vs 0.687) to detect dys-/neoplastic group indicating that macroscopic aspect is biased.

CONCLUSIONS

Nuclear-to-image ratios are applicable for automated optical in vivo diagnostics for oral potentially malignant disorders. Nuclear endomicroscopy may promote non-invasive, early detection of dys-/neoplastic lesions by reducing sampling error.

Advanced gastrointestinal endoscopic imaging for inflammatory bowel diseases

Gastrointestinal luminal endoscopy is of paramount importance for diagnosis, monitoring and dysplasia surveillance in patients with both, Crohn’s disease and ulcerative colitis. Moreover, with the recent recognition that mucosal healing is directly linked to the clinical outcome of patients with inflammatory bowel disorders, a growing demand exists for the precise, timely and detailed endoscopic assessment of superficial mucosal layer. Further, the novel field of molecular imaging has tremendously expanded the clinical utility and applications of modern endoscopy, now encompassing not only diagnosis, surveillance, and treatment but also the prediction of individual therapeutic responses. Within this review, we describe how novel endoscopic approaches and advanced endoscopic imaging methods such as high definition and high magnification endoscopy, dye-based and dye-less chromoendoscopy, confocal laser endomicroscopy, endocytoscopy and molecular imaging now allow for the precise and ultrastructural assessment of mucosal inflammation and describe the potential of these techniques for dysplasia detection.

From the surface to the single cell: Novel endoscopic approaches in inflammatory bowel disease

Inflammatory bowel diseases (IBD) comprise the two major entities Crohn’s disease and ulcerative colitis and endoscopic imaging of the gastrointestinal tract has always been an integral and central part in the management of IBD patients. Within the recent years, mucosal healing emerged as a key treatment goal in IBD that substantially decides about the clinical outcome of IBD patients, thereby demanding for a precise, timely and detailed endoscopic assessment of the mucosal inflammation associated with IBD. Further, molecular imaging has tremendously expanded the clinical utility and applications of modern endoscopy, now encompassing not only diagnosis, surveillance, and treatment but also the prediction of individual therapy response. Within this review we describe novel endoscopic approaches and advanced endoscopic imaging methods for the diagnosis, treatment and surveillance of IBD patients. We begin by providing an overview over novel and advanced imaging techniques such as magnification endoscopy and dye-based and dye-less chromoendoscopy, endomicroscopy and endocytoscopy. We then describe how these techniques can be utilized for the precise and ultrastructural assessment of mucosal inflammation and dysplasia development associated with IBD and outline how they have enabled the endoscopist to gain insight onto the cellular level in real-time. Finally, we provide an outlook on how molecular imaging has rapidly evolved in the recent past and can be used to make individual predictions about the therapeutic response towards biological treatment.

On endocytoscopy and posttherapy pathologic staging in esophageal cancers, and on evidence-based methodology

The following, from the 12th OESO World Conference: Cancers of the Esophagus, includes commentaries on the value of endocytoscopy to replace biopsy histology for squamous cell carcinoma and the clinical significance of posttherapy pathologic stage in patients with esophageal adenocarcinoma following preoperative chemoradiation; a short discussion of evidence-based methodology is also included.

Endocytoscopic observation of various esophageal lesions at ×600: can nuclear abnormality be recognized?

Endocytoscopy (ECS) is a novel endoscopic technique that allows detailed diagnostic examination of the gastrointestinal tract at the cellular level. We previously reported that use of ECS at ×380 magnification (GIF-Y0002) allowed a pathologist to diagnose esophageal squamous cell carcinoma (ESCC) with high sensitivity (94.9%) but considerably low specificity (46.7%) because this low magnification did not reveal information about nuclear abnormality. In the present study, we used the same magnifying endoscope to observe various esophageal lesions, but employed digital 1.6-fold magnification to achieve an effective magnification of ×600, and evaluated whether this improved the diagnostic accuracy in distinguishing neoplastic from non-neoplastic lesions.We examined the morphology of surface cells using vital staining with toluidine blue and compared the histological features of 40 cases, including 19 case of ESCC and 21 non-neoplastic esophageal lesions (18 cases of esophagitis, 1 case of glycogenic acanthosis, 1 case of leiomyoma, and 1 case of normal squamous epithelium). One endoscopist classified the lesions using the type classification, and we consulted one pathologist for judgment of the ECS images as 'neoplastic', 'borderline', or 'non-neoplastic'. At ×600 magnification, the pathologist confirmed that nuclear abnormality became evident, in addition to the information about nuclear density provided by observation at ×380. The overall sensitivity and specificity with which the endoscopist was able to predict neoplastic lesions using the type classification was 100% (19/19) and 90.5% (19/21), respectively, in comparison with values of 94.7% (18/19 cases) and 76.2% (16/21), respectively, for the pathologist using a magnification of ×600. The pathologist diagnosed two non-neoplastic lesions and one case of ESCC showing an apparent increase of nuclear density with weak nuclear abnormality as 'borderline'. Among the 21 non-cancerous lesions, two cases of esophagitis that were misdiagnosed by the endoscopist were also misinterpreted as 'neoplastic' by the pathologist. We have shown, by consultation with a pathologist, that an ECS magnification of ×600 (on a 19-inch monitor) is adequate for recognition of nuclear abnormality. We consider that it is feasible to diagnose esophageal neoplasms on the basis of ECS images, and that biopsy histology can be omitted if a combination of increased nuclear density and nuclear abnormality is observed.

Endoscopic diagnosis of early Barrett's neoplasia: perspectives for advanced endoscopic technology

Barrett's esophagus (BE) is a metaplastic condition that occurs secondary to gastroesophageal reflux disease. BE is also a precursor to esophageal adenocarcinoma, which, although still rare in Japan, is one of the most rapidly increasing cancers in Western countries. However, the prevalence of gastroesophageal reflux disease has increased significantly over the past few decades in Japan, possibly leading to an incremental rise in BE and the associated inherent risk of adenocarcinoma. Given the poor prognosis of advanced-stage Barrett's adenocarcinoma, endoscopic surveillance is recommended for subjects with BE to detect early neoplasias including dysplasia. However, endoscopic identification of dysplastic lesions is still not sufficiently reliable or subjective, making targeted therapy extremely difficult. Over the past few years, improvements in image resolution, image processing software, and optical filter technology have enabled identification of dysplasia and early cancer in BE patients. We retrieved as many studies on advanced endoscopic technologies in BE as possible from MEDLINE and PubMed. The present review focuses on the emergent clinically available technologies to provide an overview of the technologies, their practical applicability, current status, and future challenges.

Assessment of the diagnostic performance and interobserver variability of endocytoscopy in Barrett’s esophagus: A pilot ex-vivo study

AIM: To investigate a classification of endocytoscopy (ECS) images in Barrett’s esophagus (BE) and evaluate its diagnostic performance and interobserver variability.

METHODS: ECS was applied to surveillance endoscopic mucosal resection (EMR) specimens of BE ex-vivo. The mucosal surface of specimen was stained with 1% methylene blue and surveyed with a catheter-type endocytoscope. We selected still images that were most representative of the endoscopically suspect lesion and matched with the final histopathological diagnosis to accomplish accurate correlation. The diagnostic performance and inter-observer variability of the new classification scheme were assessed in a blinded fashion by physicians with expertise in both BE and ECS and inexperienced physicians with no prior exposure to ECS.

RESULTS: Three staff physicians and 22 gastroenterology fellows classified eight randomly assigned unknown still ECS pictures (two images per each classification) into one of four histopathologic categories as follows: (1) BEC1-squamous epithelium; (2) BEC2-BE without dysplasia; (3) BEC3-BE with dysplasia; and (4) BEC4-esophageal adenocarcinoma (EAC) in BE. Accuracy of diagnosis in staff physicians and clinical fellows were, respectively, 100% and 99.4% for BEC1, 95.8% and 83.0% for BEC2, 91.7% and 83.0% for BEC3, and 95.8% and 98.3% for BEC4. Interobserver agreement of the faculty physicians and fellows in classifying each category were 0.932 and 0.897, respectively.

CONCLUSION: This is the first study to investigate classification system of ECS in BE. This ex-vivo pilot study demonstrated acceptable diagnostic accuracy and excellent interobserver agreement.

Endocytoscopic visualization of squamous cell islands within Barrett’s epithelium

AIM: To study the endocytoscopic visualization of squamous cell islands within Barrett’s epithelium.

METHODS: Endocytoscopy (ECS) has been studied in the surveillance of Barrett’s esophagus, with controversial results. In initial studies, however, a soft catheter type endocytoscope was used, while only methylene blue dye was used for the staining of Barrett’s mucosa. Integrated type endocytoscopes (GIF-Q260 EC, Olympus Corp, Tokyo, Japan) have been recently developed, with the incorporation of a high-power magnifying endocytoscope into a standard endoscope together with narrow-band imaging (NBI). Moreover, double staining with a mixture of 0.05% crystal violet and 0.1% of methylene blue (CM) during ECS enables higher quality images comparable to conventional hematoxylin eosin histopathological images.

RESULTS: In vivo endocytoscopic visualization of papillary squamous cell islands within glandular Barrett’s epithelium in a patient with long-segment Barrett’s esophagus is reported. Conventional white light endoscopy showed typical long-segment Barrett’s esophagus, with small squamous cell islands within normal Barrett’s mucosa, which were better visualized by NBI endoscopy. ECS after double CM staining showed regular Barrett’s esophagus, while higher magnification (× 480) revealed the orifices of glandular structures better. Furthermore, typical squamous cell papillary protrusion, classified as endocytoscopic atypia classification (ECA) 2 according to ECA, was identified within regular glandular Barrett’s mucosa. Histological examination of biopsies taken from the same area showed squamous epithelium within glandular Barrett’s mucosa, corresponding well to endocytoscopic findings.

CONCLUSION: To our knowledge, this is the first report of in vivo visualization of esophageal papillary squamous cell islands surrounded by glandular Barrett’s epithelium.