Conventional Endoscopic Ultrasonography Research Articles

Construction and validation of an endoscopic ultrasonography-based ultrasomics nomogram for differentiating pancreatic neuroendocrine tumors from pancreatic cancer

ObjectivesTo develop and validate various ultrasomics models based on endoscopic ultrasonography (EUS) for retrospective differentiating pancreatic neuroendocrine tumors (PNET) from pancreatic cancer.MethodsA total of 231 patients, comprising 127 with pancreatic cancer and 104 with PNET, were retrospectively enrolled. These patients were randomly divided into either a training or test cohort at a ratio of 7:3. Ultrasomics features were extracted from conventional EUS images, focusing on delineating the region of interest (ROI) for pancreatic lesions. Subsequently, dimensionality reduction of the ultrasomics features was performed by applying the Mann-Whitney test and least absolute shrinkage and selection operator (LASSO) algorithm. Eight machine learning algorithms, namely logistic regression (LR), light gradient boosting machine (LightGBM), multilayer perceptron (MLP), random forest (RF), extra trees, k nearest neighbors (KNN), support vector machine (SVM), and extreme gradient boosting (XGBoost), were employed to train prediction models using nonzero coefficient features. The optimal ultrasomics model was determined using a ROC curve and utilized for subsequent analysis. Clinical-ultrasonic features were assessed using both univariate and multivariate logistic regression. An ultrasomics nomogram model, integrating both ultrasomics and clinical-ultrasonic features, was developed.ResultsA total of 107 EUS-based ultrasomics features were extracted, and 6 features with nonzero coefficients were ultimately retained. Among the eight ultrasomics models based on machine learning algorithms, the RF model exhibited superior performance with an AUC= 0.999 (95% CI 0.9977 - 1.0000) in the training cohort and an AUC= 0.649 (95% CI 0.5215 - 0.7760) in the test cohort. A clinical-ultrasonic model was established and evaluated, yielding an AUC of 0.999 (95% CI 0.9961 - 1.0000) in the training cohort and 0.847 (95% CI 0.7543 - 0.9391) in the test cohort. Subsequently, the ultrasomics nomogram demonstrated a significant improvement in prediction accuracy in the test cohort, as evidenced by an AUC of 0.884 (95% CI 0.8047 - 0.9635) and confirmed by the Delong test. The calibration curve and decision curve analysis (DCA) depicted this ultrasomics nomogram demonstrated superior accuracy. They also yielded the highest net benefit for clinical decision-making compared to alternative models.ConclusionsA novel ultrasomics nomogram was proposed and validated, that integrated clinical-ultrasonic and ultrasomics features obtained through EUS, aiming to accurately and efficiently identify pancreatic cancer and PNET.

Contrast-enhanced endoscopic ultrasound likely does not improve diagnostic adequacy during endoscopic ultrasound guided tissue acquisition: A systematic review and meta-analysis

Background and aimsSolid pancreatic masses are sampled through tissue acquisition by endoscopic ultrasound (EUS). Inadequate samples may significantly delay diagnosis, increasing costs and carrying risks to the patients. Aim: assess the diagnostic adequacy of tissue acquisition using contrast-enhanced harmonic endoscopic ultrasound (CEH-EUS) compared to conventional EUS. MethodsFive databases (PubMed, Embase, CENTRAL, Scopus and Web of Science) were searched in November 2023. Studies comparing diagnostic adequacy, accuracy and safety using CEH-EUS versus conventional EUS for tissue acquisition of solid pancreatic masses were included. Risk of bias was assessed using the Risk of Bias tool for randomized controlled trials (RoB2) and the Risk Of Bias In Non-Randomized Studies - of Interventions (ROBINS-I) tool for non-randomized studies, level of evidence using the GRADE approach, Odds Ratios (RR) with 95 % Confidence Intervals (CI) calculated and pooled using a random-effects model. I2 quantified heterogeneity. ResultsThe search identified 3858 records; nine studies (1160 patients) were included. OR for achieving an adequate sample was 1.467 (CI: 0.850–2.533), for randomized trials 0.902 (CI: 0.541–1.505), for non-randomized 2.396 (CI: 0.916–6.264), with significant subgroup difference. OR for diagnostic accuracy was 1.326 (CI: 0.890–1977), for randomized trials 0.997 (CI: 0.593–1.977) and for non-randomized studies 1.928 (CI: 1.096–3.393), significant subgroup difference (p = 0.0467). No differences were observed for technical failures or adverse events. Heterogeneity was low, risk of bias “low” to “some concerns” for most outcomes, mostly moderate for non-randomized studies. ConclusionNon-randomized studies indicated differences in favor of contrast-enhanced EUS, randomized studies showed no difference in diagnostic adequacy, accuracy or sensitivity when using CEH-EUS.

Artificial intelligence assisted endoscopic ultrasound for detection of pancreatic space-occupying lesion: a systematic review and meta-analysis.

Diagnosing pancreatic lesions, including chronic pancreatitis, autoimmune pancreatitis, and pancreatic cancer, poses a challenge and, as a result, is time-consuming. To tackle this issue, artificial intelligence (AI) has been increasingly utilized over the years. AI can analyze large data sets with heightened accuracy, reduce interobserver variability, and can standardize the interpretation of radiologic and histopathologic lesions. Therefore, this study aims to review the use of AI in the detection and differentiation of pancreatic space-occupying lesions and to compare AI-assisted endoscopic ultrasound (EUS) with conventional EUS in terms of their detection capabilities. Literature searches were conducted through PubMed/Medline, SCOPUS, and Embase to identify studies eligible for inclusion. Original articles, including observational studies, randomized control trials, systematic reviews, meta-analyses, and case series specifically focused on AI-assisted EUS in adults, were included. Data were extracted and pooled, and a meta-analysis was conducted using Meta-xl. For results exhibiting significant heterogeneity, a random-effects model was employed; otherwise, a fixed-effects model was utilized. A total of 21 studies were included in the review with four studies pooled for a meta-analysis. A pooled accuracy of 93.6% (CI 90.4-96.8%) was found using the random-effects model on four studies that showed significant heterogeneity ( P <0.05) in the Cochrane's Q test. Further, a pooled sensitivity of 93.9% (CI 92.4-95.3%) was found using a fixed-effects model on seven studies that showed no significant heterogeneity in the Cochrane's Q test. When it came to pooled specificity, a fixed-effects model was utilized in six studies that showed no significant heterogeneity in the Cochrane's Q test and determined as 93.1% (CI 90.7-95.4%). The pooled positive predictive value which was done using the random-effects model on six studies that showed significant heterogeneity was 91.6% (CI 87.3-95.8%). The pooled negative predictive value which was done using the random-effects model on six studies that showed significant heterogeneity was 93.6% (CI 90.4-96.8%). AI-assisted EUS shows a high degree of accuracy in the detection and differentiation of pancreatic space-occupying lesions over conventional EUS. Its application may promote prompt and accurate diagnosis of pancreatic pathologies.

Diagnostic value of conventional endoscopic ultrasound for lymph node metastasis in upper gastrointestinal neoplasia: A meta-analysis.

Upper gastrointestinal neoplasia mainly includes esophageal cancer and gastric cancer, both of which have high morbidity and mortality. Lymph node metastasis (LNM), as the most common metastasis mode of both diseases, is an important factor affecting tumor stage, treatment strategy and clinical prognosis. As a new fusion technology, endoscopic ultrasound (EUS) is becoming increasingly used in the diagnosis and treatment of digestive system diseases, but its use in detecting LNM in clinical practice remains limited. To evaluate the diagnostic value of conventional EUS for LNM in upper gastrointestinal neoplasia. Using the search mode of "MeSH + Entry Terms" and according to the predetermined inclusion and exclusion criteria, we conducted a comprehensive search and screening of the PubMed, EMBASE and Cochrane Library databases from January 1, 2000 to October 1, 2022. Study data were extracted according to the predetermined data extraction form. The quality of the included studies was assessed using the Quality Assessment of Diagnostic Accuracy Studies tool, and the results of the quality assessment were presented using Review Manager 5.3.5 software. Finally, Stata14.0 software was used for a series of statistical analyses. A total of 22 studies were included in our study, including 2986 patients. The pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, diagnostic score and diagnostic odds ratio of conventional EUS in the diagnosis of upper gastrointestinal neoplasia LNM were 0.62 [95% confidence interval (CI): 0.50-0.73], 0.80 (95%CI: 0.73-0.86), 3.15 (95%CI: 2.46-4.03), 0.47 (95%CI: 0.36-0.61), 1.90 (95%CI: 1.51-2.29) and 6.67 (95%CI: 4.52-9.84), respectively. The area under the summary receiver operating characteristic curve was 0.80 (95%CI: 0.76-0.83). Sensitivity analysis indicated that the results of the meta-analysis were stable. There was considerable heterogeneity among the included studies, and the threshold effect was an important source of heterogeneity. Univariable meta-regression and subgroup analysis showed that tumor type, sample size and EUS diagnostic criteria were significant sources of heterogeneity in specificity (P < 0.05). No significant publication bias was found. Conventional EUS has certain clinical value and can assist in the detection of LNM in upper gastrointestinal neoplasia, but it cannot be used as a confirmatory or exclusionary test.

Endoscopic Ultrasound in the Diagnosis of Extrahepatic Cholangiocarcinoma: What Do We Know in 2023?

Extrahepatic cholangiocarcinoma (CCA) is a rare and aggressive type of cancer, presenting as a mass or as a biliary stricture. This review summarizes the utility of endoscopic ultrasound (EUS) in the detection, staging, and determination of the differential diagnosis, especially when no cause of bile duct dilatation is revealed by cross-sectional imaging. The EUS detection rate for distal CCAs is higher than that for the proximal CCAs. The accuracy of T staging varies between 60 and 80%, and vascular involvement is correctly assessed by conventional EUS. EUS-tissue acquisition from the primary tumors is reserved for unresectable or metastatic CCA, especially in distal strictures or mass CCAs. For proximal lesions, EUS could be performed as an adjunctive to ERCP sampling when the latter is inconclusive. EUS is not appropriate for assessing the malignant features of lymph nodes in CCAs. Lymph node EUS-tissue acquisition should be performed only if it changes the surgical decision. Perhaps the development of EUS-fine needle biopsy and the detection of molecular genetic alteration will increase the diagnostic yield in CCAs.

Endoscopic Ultrasound Advanced Techniques for Diagnosis of Gastrointestinal Stromal Tumours

Gastrointestinal Stromal Tumors (GISTs) are subepithelial lesions (SELs) that commonly develop in the gastrointestinal tract. GISTs, unlike other SELs, can exhibit malignant behavior, so differential diagnosis is critical to the decision-making process. Endoscopic ultrasound (EUS) is considered the most accurate imaging method for diagnosing and differentiating SELs in the gastrointestinal tract by assessing the lesions precisely and evaluating their malignant risk. Due to their overlapping imaging characteristics, endosonographers may have difficulty distinguishing GISTs from other SELs using conventional EUS alone, and the collection of tissue samples from these lesions may be technically challenging. Even though it appears to be less effective in the case of smaller lesions, histology is now the gold standard for achieving a final diagnosis and avoiding unnecessary and invasive treatment for benign SELs. The use of enhanced EUS modalities and elastography has improved the diagnostic ability of EUS. Furthermore, recent advancements in artificial intelligence systems that use EUS images have allowed them to distinguish GISTs from other SELs, thereby improving their diagnostic accuracy.

Study of preoperative diagnostic modalities in Chinese patients with superficial esophageal squamous cell carcinoma.

BACKGROUNDEndoscopic ultrasonography (EUS) and magnifying endoscopy (ME) reliably determine indications for endoscopic resection in patients with superficial esophageal squamous cell carcinoma (SESCC). ME is widely accepted for predicting the invasion depth of superficial esophageal cancer with satisfying accuracy. However, the addition of EUS is controversial.AIMTo evaluate the diagnostic efficiency of ME vs EUS for invasion depth prediction and investigate the influencing factors in patients with SESCC to determine the best diagnostic model in China.METHODSWe retrospectively analyzed patients with suspected SESCC who completed both ME and EUS and then underwent endoscopic or surgical resection at Sun Yat-Sen University Cancer Center between January 2018 and December 2021. We evaluated and compared the diagnostic efficiency of EUS and ME according to histological results, and investigated the influencing factors.RESULTSWe included 152 lesions from 144 patients in this study. The diagnostic accuracies of ME and EUS in differentiating invasion depth were not significantly different (73.0% and 66.4%, P = 0.24); both demonstrated moderate consistency with the pathological results (ME: kappa = 0.58, 95% confidence interval [CI]: 0.48-0.68, P < 0.01; EUS: kappa = 0.46, 95%CI: 0.34-0.57, P < 0.01). ME was significantly more accurate in the diagnosis of high-grade intraepithelial (HGIN) or carcinoma in situ (odds ratio [OR] = 3.62, 95%CI: 1.43-9.16, P = 0.007) subgroups. Using a miniature probe rather than conventional EUS can improve the accuracy of lesion depth determination (82.3% vs 49.3%, P < 0.01). Less than a quarter of circumferential occupation and application of a miniature probe were independent risk factors for the accuracy of tumor invasion depth as assessed by EUS (< 1/4 circumferential occupation: OR = 3.07, 95%CI: 1.04-9.10; application of a miniature probe: OR = 5.28, 95%CI: 2.41-11.59, P < 0.01). Of the 41 lesions (41/152, 27.0%) that were misdiagnosed by ME, 24 were corrected by EUS (24/41, 58.5%). CONCLUSIONPreoperative diagnosis of SESCC should be conducted endoscopically using white light and magnification. In China, EUS can be added after obtaining patient consent. Use of a high-frequency miniature probe or miniature probe combined with conventional EUS is preferable.

The expanding role of endoscopic ultrasound elastography.

Endoscopic ultrasound (EUS) is an invaluable tool for assessing various GI diseases. However, using just the conventional B-mode EUS imaging may not be sufficient to accurately delineate the lesion's character. Using the principle of stress-induced tissue strain, EUS elastography (EUS-E) can help in the real-time sonographic assessment of the level of tissue stiffness or hardness of any organ of interest during a routine EUS procedure. Thus, EUS-E can better characterize the lesion's nature and highlight the more suspicious areas within an individual lesion. The most commonly studied lesions with EUS-E are the pancreatic lesions, namely, chronic pancreatitis, pancreatic cancer, and lymph nodes. However, EUS-E is gradually expanding its use for lesion characterization of the liver, bile duct, adrenals, gastrointestinal tract, and even therapy response. Moreover, the use of EUS-E along with other image enhancement techniques such as harmonic EUS and contrast-enhanced EUS can improve the accuracy of the diagnosis. However, several technical aspects need to be standardized before EUS-E can be truly used as a tool for "virtual biopsy". This review focuses on the various technical aspects of the use of EUS-E, it is established and expanding indications and an extensive outline of the various studies on EUS-E. We also discuss the current pitfalls and future trends in EUS-E.

Contrast enhanced endoscopic ultrasound in the diagnosis of pancreatic metastases.

Less than 5% of pancreatic masses represent metastases and differentiation from primitive tumors using endo-scopic ultrasound (EUS) is difficult. The aim of our work was to assess the diagnostic value of contrast-enhanced harmonic endoscopic ultrasound (CH-EUS) for pancreatic metastases. We retrospectively analyzed patients with pancreatic metastasis identified during a 8 year period in a tertiary medical center. We included in the study 20 patients evaluated with EUS and CH-EUS. The primary tumor was localized in the kidney (6 cases), lung (5 cases), colon (3 cases), skin (2 patients) and stomach, breast, ovary and liver (1 patient each). Only 11 patients (55%) (kidney, lung, liver, ovary or skin metastases), presented hypervascularity at EUS and arterial hyperenhancement on CH-EUS, with similar diag-nostic value. All renal metastases were hyperenhanced (the negative predictive value 100%) and the stomach, colon and ovary metastases were hypoenhanced. The fast wash-out of contrast substance was encountered in all cases or renal, pulmonary and digestive metastases, but with 53.3-64.3% specificity for the different origin of pancreatic metastases. The vascularity assessments on conventional EUS or CH-EUS are similar for pancreatic metastases of different origin. EUS tissue acquisition remains mandatory for the diagnosis.

Current role of endoscopic ultrasound in the diagnosis and management of pancreatic cancer.

Endoscopic ultrasound (EUS) has emerged as an invaluable tool for the diagnosis, staging and treatment of pancreatic ductal adenocarcinoma (PDAC). EUS is currently the most sensitive imaging tool for the detection of solid pancreatic tumors. Conventional EUS has evolved, and new imaging techniques, such as contrast-enhanced harmonics and elastography, have been developed to improve diagnostic accuracy during the evaluation of focal pancreatic lesions. More recently, evaluation with artificial intelligence has shown promising results to overcome operator-related flaws during EUS imaging evaluation. Currently, an appropriate diagnosis is based on a proper histological assessment, and EUS-guided tissue acquisition is the standard procedure for pancreatic sampling. Newly developed cutting needles with core tissue procurement provide the possibility of molecular evaluation for personalized oncological treatment. Interventional EUS has modified the therapeutic approach, primarily for advanced pancreatic cancer. EUS-guided fiducial placement for local targeted radiotherapy treatment or EUS-guided radiofrequency ablation has been developed for local treatment, especially for patients with pancreatic cancer not suitable for surgical resection. Additionally, EUS-guided therapeutic procedures, such as celiac plexus neurolysis for pain control and EUS-guided biliary drainage for biliary obstruction, have dramatically improved in recent years toward a more effective and less invasive procedure to palliate complications related to PDAC. All the current benefits of EUS in the diagnosis and management of PDAC will be thoroughly discussed.

Differentiation Between Solid Pseudopapillary Neoplasm of the Pancreas and Nonfunctional Pancreatic Neuroendocrine Neoplasm Using Endoscopic Ultrasound.

We investigated the utility of endoscopic ultrasound (EUS) for differentiating between solid pseudopapillary neoplasm of the pancreas (SPN) and pancreatic neuroendocrine neoplasm (PanNEN). A retrospective analysis was performed on 29 and 77 consecutive patients with pathologically proven SPN and nonfunctional PanNEN. In patients who underwent contrast-enhanced harmonic EUS (CH-EUS), lesions were classified into 3 vascular patterns (hypoechoic/isoechoic/hyperechoic), and the presence of "the alveolus nest sign," which we previously reported as a characteristic feature of SPN on CH-EUS, was also assessed. Conventional EUS findings showed that calcification echoes were significantly more frequent in SPN lesions than in PanNEN lesions (19/29 [66%] vs 21/77 [27%], P = 0.001) as was internal isoechogenicity or hyperechogenicity (10/29 [34%] vs 11/77 [14%], P = 0.029). Contrast-enhanced harmonic EUS findings showed that SPN lesions more frequently had the isoechoic or hypoechoic vascular pattern, and significantly more frequently had the alveolus nest sign (18/25 [72%] vs 4/60 [7%], P < 0.001). In a multivariate analysis, the presence of the alveolus nest sign contributed the most to the SPN diagnosis (odds ratio, 70; 95% confidence interval, 6.2-786). Endoscopic ultrasound, particularly the presence of the alveolus nest sign on CH-EUS, is useful for differentiating SPN from PanNEN.

Differentiating Gastrointestinal Stromal Tumors from Leiomyomas Using a Neural Network Trained on Endoscopic Ultrasonography Images

Background: Endoscopic ultrasonography (EUS) is crucial to diagnose and evaluate gastrointestinal mesenchymal tumors (GIMTs). However, EUS-guided biopsy does not always differentiate gastrointestinal stromal tumors (GISTs) from leiomyomas. We evaluated the ability of a convolutional neural network (CNN) to differentiate GISTs from leiomyomas using EUS images. The conventional EUS features of GISTs were also compared with leiomyomas. Patients and Methods: Patients who underwent EUS for evaluation of upper GIMTs between 2010 and 2020 were retrospectively reviewed, and 145 patients (73 women and 72 men; mean age 54.8 ± 13.5 years) with GISTs (n = 109) or leiomyomas (n = 36), confirmed by immunohistochemistry, were included. A total of 978 images collected from 100 patients were used to train and test the CNN system, and 384 images from 45 patients were used for validation. EUS images were also evaluated by an EUS expert for comparison with the CNN system. Results: The sensitivity, specificity, and accuracy of the CNN system for diagnosis of GIST were 92.0%, 64.3%, and 86.98% for the validation dataset, respectively. In contrast, the sensitivity, specificity, and accuracy of the EUS expert interpretations were 60.5%, 74.3%, and 63.0%, respectively. Concerning EUS features, only higher echogenicity was an independent and significant factor for differentiating GISTs from leiomyomas (p < 0.05). Conclusions: The CNN system could diagnose GIMTs with higher accuracy than an EUS expert and could be helpful in differentiating GISTs from leiomyomas. A higher echogenicity may also aid in differentiation.

Imaging diagnosis of autoimmune pancreatitis using endoscopic ultrasonography.

The diagnosis of autoimmune pancreatitis (AIP) is challenging and should be achieved through the comprehensive evaluation of clinical, radiological, serological, and pathological evidence, as there is currently no single reliable diagnostic modality. Endoscopic ultrasonography (EUS) can reveal pancreatic parenchymal and ductal features in much more detail than any other existing imaging modality. In this article, we focused on three applications of EUS, i.e., conventional EUS imaging, EUS elastography (EUS-EG), and contrast-enhanced harmonic EUS (CEH-EUS), for the diagnosis of AIP. Diffuse hypoechoic areas, diffuse enlargement, bile duct wall thickening, and peripancreatic hypoechoic margins on conventional EUS are characteristic features of AIP, and the frequencies of these findings are significantly higher in AIP than in pancreatic cancer (PC). EUS-EG of the pancreatic parenchyma in AIP showed homogenous stiffness and that the elasticity of the pancreas may change after steroid therapy. CEH-EUS revealed focal or diffuse iso-enhancement in most AIP cases and hypo-enhancement in most PC cases. However, some AIP cases show a contrast enhancement pattern similar to that of PC. It should be noted that EUS findings of AIP may differ depending on its stage or disease activity. Differentiation from PC has become an increasingly important issue in the process of diagnosing AIP, and EUS, including elastography and contrast enhancement, could be a promising imaging modality for this purpose.

Role of endoscopic ultrasound elastography in differential diagnosis of pancreatic solid masses

Introduction: Endoscopic ultrasound (EUS) elastography is another technique that measures the stiffness of tissue and adds more diagnostic value to EUS.Objective: This study aimed to assess the ability of qualitative and quantitative EUS elastography in differentiating malignant from benign solid pancreatic masses.Methods: This 2-year cross-sectional study enrolled 80 patients with solid pancreatic masses in the department of endoscopy in Alassad University Hospital who underwent conventional and elastography-assisted EUS and then followed for pathology through EUS-guided or CT-guided biopsy or surgery.Results: Qualitative elastography using a 5-point scoring system was able to recognize malignant pathology (obtained by EUS-guided biopsy, CT-guided biopsy, or surgery) with a sensitivity, specificity, and accuracy rates of 100%, 28.6%, and 81.3%, respectively. A quantitative method using hue histogram had a sensitivity of 71.2%–86.4% and specificity of 71.4%–81% with the best accuracy for histogram mean ratio (area under the curve, 0.867).Conclusion: EUS elastography is a simple and good alternative method in differentiating malignant from benign pancreatic solid masses.

Examination of Endoscopic Ultrasonographic Diagnosis for the Depth of Early Gastric Cancer

BackgroundEndoscopic ultrasonography (EUS) is one of the helpful tools to diagnose depth of early gastric cancer (EGC). In this study, we examined efficiencies of EUS for EGC such as overall accuracy, risk factors of over/under-staging, and accuracies of each invasive distance.MethodsA total of 403 EGC lesions that could be investigated by EUS during pre-operation and histological diagnosis after endoscopic submucosal dissection (ESD) or surgery were enrolled in this study. For the 403 cases, we analyzed the accuracies of depth by conventional endoscopy (CE) and EUS retrospectively. We evaluated the clinical survey items of CE and EUS which will be described later to compare the differences between “accuracy group” and “over-staging group”, and between “accuracy group” and “under-staging group”, retrospectively. Additionally, 78 EGC lesions which were confined to the submucosa and for which it was possible to measure accurate invasive distance from the muscularis mucosae were examined for the relationship between preoperative diagnosis of depth by CE and EUS and invasive distance retrospectively.ResultsThe overall accuracies of both CE and EUS in predicting EGC invasion depth were 87.3%. For CE staging, histological classification was the factor which influenced over-staging. Gastric regions and tumor area were the factors which influenced under-staging of CE. For EUS staging, tumor area was the factor which influenced over-staging, and gastric regions were the factors which influenced under-staging. Both CE and EUS were not sufficient for predicting the lesions confined to < 500 µm from the muscularis mucosae because the accuracies of both in predicting depth were less than 50%. However, EUS has a higher accuracy than CE for the lesions confined to 500 - 2,000 µm.ConclusionsThe overall accuracies of both CE and EUS in predicting EGC invasion depth were equal, but the contributing factors for over/under-staging were different. Both CE and EUS are not sufficient at present to predict the lesions confined to < 500 µm from the muscularis mucosae. However, the accuracy of EUS in predicting them may increase if high-performance EUS systems are developed in the future.

Use of Artificial Intelligence in the Prediction of Malignant Potential of Gastric Gastrointestinal Stromal Tumors.

This study aimed to investigate whether AI via a deep learning algorithm using endoscopic ultrasonography (EUS) images could predict the malignant potential of gastric gastrointestinal stromal tumors (GISTs). A series of patients who underwent EUS before surgical resection for gastric GISTs were included. A total of 685 images of GISTs from 55 retrospectively included patients were used as the training data set for the AI system. Convolutional neural networks were constructed to build a deep learning model. After applying the synthetic minority oversampling technique, 70% of the generated images were used for AI training and 30% were used to test AI diagnoses. Next, validation was performed using 153 EUS images of 15 patients with GISTs. In addition, conventional EUS features of 55 patients in the training cohort were evaluated to predict the malignant potential of GISTs and mitotic index. The overall sensitivity, specificity, and accuracy of the AI system for predicting malignancy risk were 83%, 94%, and 82% in the training dataset, and 75%, 73%, and 66% in the validation cohort, respectively. When patients were divided into low-risk and high-risk groups, sensitivity, specificity, and accuracy increased to 99% in the training dataset and 99.7%, 99.7%, and 99.6%, respectively, in the validation cohort. No conventional EUS features were found to be associated with either malignant potential or mitotic index (P > 0.05). AI via a deep learning algorithm using EUS images could predict the malignant potential of gastric GISTs with high accuracy.

Diagnostic yield of conventional endoscopy with endoscopic ultrasonography for submucosal invasion of superficial esophageal squamous cell carcinoma: a post hoc analysis of multicenter prospective confirmatory study (JCOG0508).

Endoscopic ultrasonography (EUS) is reportedly the reliable modality to predict the depth of esophageal squamous cell carcinoma (ESCC), however, most previous studies are retrospective or single-centered. We aimed to evaluate the diagnostic ability of conventional endoscopy and EUS using the data from a multicenter prospective study of endoscopic resection (ER) followed by chemoradiotherapy for cSM1-2N0M0 ESCC (JCOG0508). All lesions were evaluated as cSM cancer with both conventional endoscopy and EUS before enrollment and judged as cSM1 or cSM2 in real time. We compared the clinical and pathological diagnoses for tumor depth and assessed the positive predictive value (PPV) for pSM (pSM/cSM) as the primary endpoint. We also investigated the clinical factors affecting the pathological depth of SM. 175 lesions were examined, and clinical diagnosis was SM1 in 114 and SM2 in 61 lesions. The pathological diagnoses of the epithelium, lamina propria mucosa, muscularis mucosae, SM1, and SM2 were 3, 31, 55, 17, and 69. The PPV for pSM was 49.1% (86/175) in all lesions, 34.2% (39/114) in cSM1 lesions, and 77.0% (47/61) in cSM2 lesions. Multivariable analysis demonstrated that cSM2 (vs. cSM1, OR 6.79) was an independent clinical factor associated with pSM. While the accurate depth diagnosis in cSM ESCC was difficult to make, the clinical diagnosis of SM2 with both conventional endoscopy and EUS was significantly associated with pSM. Furthermore, diagnostic ER could be recommended to confirm the pathological diagnosis especially in cSM1 lesions with both conventional endoscopy and EUS.

Efficacy of Endoscopic Ultrasound Elastography in Differential Diagnosis of Gastrointestinal Stromal Tumor Versus Gastrointestinal Leiomyoma.

BackgroundThe diagnostic efficacy of endoscopic ultrasound (EUS) elastography for alimentary tract diseases remains uncertain. The aim of this study was to evaluate the utility of EUS elastography in differential diagnosis between the 2 most common subepithelium tumors of the digestive tract – gastrointestinal stromal tumors (GISTs) and gastrointestinal leiomyomas (GILs) – which cannot be differentiated by conventional EUS imaging.Material/MethodsElectronic records were retrospectively reviewed from Jan 2015 to Jul 2019. Patients accepting EUS elastography with histopathological diagnosis of GISTs or GILs were included. The images of EUS elastography were analyzed by hue histogram in Photoshop. Hue values of RGB, R, G, and B channels of each group were acquired. We used the t test, ROC curve analysis, and binary logistic regression analysis for data post-processing.ResultsWe included 47 patients with GISTs and 14 with GILs. The mean±standard deviations (SD) of hue values were 20.25±0.72, −0.79±0.78, 20.79±1.68, 39.72±1.30 for GISTs and 20.80±0.46, 1.80±1.05, 28.39±2.15, and 31.95±2.60 for GILs of RGB, R, G, and B channels, respectively. The t test showed statistically significant differences in mean hue values between GISTs and GILs in B and G channels, but not in RGB and R channels. The area under the ROC curve combining B and G values was 0.723. Binary logistic regression analysis suggested no statistically significant difference in ability to differentiate between GISTs and GILs with B and G values (P>0.05).ConclusionsThere was insufficient evidence to support the application of quantitative EUS elastography for differential diagnosis of GISTs and GILs in this study.

Role of Endoscopic Ultrasound in Selecting Superficial Esophageal Cancers for Endoscopic Resection

Endoscopic submucosal dissection (ESD) is a curative treatment option for superficial esophageal cancer with a minimal risk for lymph node metastasis. Before ESD, accurate clinical staging is important to select the appropriate candidate. We aimed to estimate the practicality of endoscopic ultrasound (EUS) to select pTis and pT1a. We included patients with squamous esophageal cancers who underwent surgical resection or ESD between 2005 and 2018. Pathologic reports were reviewed retrospectively, and pathologic T staging was compared with clinical stage evaluated by EUS. Among 532 patients, 321 had superficial esophageal cancer (pTis: 42; pT1a: 115; and pT1b: 164). Accuracy rates, sensitivity, specificity, positive predicted value, and negative predicted value for selecting cT1a by EUS were 82.3%, 60.5%, 91.5%, 74.8%, and 84.7%, respectively. The rate of overstaged pTis-T1a was 39.5%. Upon multivariable analysis, tumor size (>2 cm), poor differentiation, protruding gross type, and use of conventional EUS (versus miniprobe) were associated factors for overstaging of pTis-T1a. The accuracy of prediction of EUS for selecting mucosal esophageal cancer that can be treated with ESD was favorable. Target lesions with a large size (>2 cm), poor differentiation, and protruding morphology were related to T overstaging; precaution should be taken when evaluating the clinical stage for cancers with those conditions. Furthermore, miniprobe EUS provides higher accuracy for squamous esophageal cancers confined to mucosa.

EUS in the diagnosis of pathologically undiagnosed esophageal tuberculosis

BackgroundEsophageal tuberculosis (ET) is relatively rare, and the diagnosis is challenging. The aim of this study was to evaluate the clinical features of ET and highlight the role of endoscopic ultrasonography (EUS) in the diagnosis of pathologically undiagnosed ET.MethodsWe retrospectively analysed the clinical features, radiological performances, conventional endoscopic appearances, EUS features, treatment and outcomes of pathologically undiagnosed ET between January 2011 and December 2018. All 9 patients failed to be diagnosed by at least two repeated biopsies (such as routine biopsy, multipoint or deep biopsy, and even or EUS-guided fine-needle aspiration (EUS-FNA)).ResultsNine patients (66.7% female) with a mean age of 45 years (range 29–59) complained of retrosternal pain or discomfort, or (and) dysphagia. Esophagoscopy demonstrated protruding lesions in the mucosa with central ulcers or erosion in five patients, submucosal bulges with smooth surfaces in one patient, submucosal bulges with diverticula in one patient, ulcers with suspicious fistula formation in one patient, and multiple ulcers in one patient. None of the patients received confirmed histopathological or bacteriological diagnoses by repeated biopsies. However, they were first suspected to have ET based on EUS examination. Because EUS found some characteristic ultrasonographic changes, which were very helpful for the diagnosis of ET when combined with clinical manifestations, the patients subsequently received diagnostic antituberculosis therapy. Finally, the patients recovered or improved with follow-up times ranging from 3 to 10 months.ConclusionsEUS could help in the diagnosis of ET on basis of EUS features like poorly defined esophageal wall structure, enlarged paraesophageal or mediastinal lymph nodes, hypoechoic lesions of esophageal wall that are linked to the enlarged paraesophageal lymph nodes. However all attempts should be made to obtain histological or microbiological diagnosis.