Deep learning analysis for differential diagnosis and risk classification of gastrointestinal tumors.

OBJECTIVES: Recently, artificial intelligence (AI) has been applied to clinical diagnosis. Although AI has already been developed for gastrointestinal (GI) tract endoscopy, few studies have applied AI to endoscopic ultrasound (EUS) images. In this study, we used a computer-assisted diagnosis (CAD) system with deep learning analysis of EUS images (EUS-CAD) and assessed its ability to differentiate GI stromal tumors (GISTs) from other mesenchymal tumors and their risk classification performance. MATERIALS AND METHODS: A total of 101 pathologically confirmed cases of subepithelial lesions (SELs) arising from the muscularis propria layer, including 69 GISTs, 17 leiomyomas and 15 schwannomas, were examined. A total of 3283 EUS images were used for training and five-fold-cross-validation, and 827 images were independently tested for diagnosing GISTs. For the risk classification of 69 GISTs, including very-low-, low-, intermediate- and high-risk GISTs, 2,784 EUS images were used for training and three-fold-cross-validation. RESULTS: For the differential diagnostic performance of GIST among all SELs, the accuracy, sensitivity, specificity and area under the receiver operating characteristic (ROC) curve were 80.4%, 82.9%, 75.3% and 0.865, respectively, whereas those for intermediate- and high-risk GISTs were 71.8%, 70.2%, 72.0% and 0.771, respectively. CONCLUSIONS: The EUS-CAD system showed a good diagnostic yield in differentiating GISTs from other mesenchymal tumors and successfully demonstrated the GIST risk classification feasibility. This system can determine whether treatment is necessary based on EUS imaging alone without the need for additional invasive examinations.

Endoscopic resection in subepithelial lesions of the upper gastrointestinal tract: Experience at a tertiary referral hospital in The Netherlands.

Background and study aims Histological confirmation of subepithelial lesions (SELs) in the upper gastrointestinal tract remains challenging. Endoscopic resection of SELs is increasingly used for its excellent diagnostic yield and opportunity to do away with continued surveillance. In this study, we aimed to evaluate the indications, success rates and complications of different endoscopic resection techniques for SELs at a large, tertiary referral hospital in Rotterdam, The Netherlands. Patients and methods Data between October 2013 and December 2021 were retrospectively collected and analyzed. Main outcomes were R0-resection rate, en bloc resection rate, recurrence rate, and procedure-related adverse events (AEs) (Clavien-Dindo). Secondary outcomes were procedure time, need for surgical intervention, and clinical impact on patient management. Results A total of 58 patients were referred for endoscopic resection of upper gastrointestinal SELs. The median diameter of lesions was 20 mm (range 7-100 mm). Median follow-up time was 5 months (range 0.4-75.7). Forty-eight procedures (83%) were completed successfully leading to en bloc resection in 85% and R0-resection in 63%. Procedure-related AEs occurred in six patients (13%). Severe complications (CD grade 3a) were seen in three patients. The local recurrence rate for (pre)malignant diagnosis was 2%. Additional surgical intervention was needed in seven patients (15%). A total of 32 patients (67%) could be discharged from further surveillance after endoscopic resection. Conclusions Endoscopic resection is a safe and effective treatment for SELs and offers valuable information about undetermined SELs for which repeated sampling attempts have failed to provide adequate tissue for diagnosis.

Combining Endoscopic Submucosa Dissection and Endoscopic Full-Thickness Resection for Resection of a Gastric Schwannoma Mimicking Gastrointestinal Stroma Tumor.

Subepithelial gastric tumors are a diagnostic challenge. Endoscopic ultrasound allows differentiation. Lesions originating from the submucosal layer can be resected using endoscopic submucosal dissection (ESD). Surgery or endoscopic full-thickness resection (EFTR) techniques are alternatives. We present a patient with an 11 × 8 mm submucosal tumor in the gastric antrum suggestive of a gastrointestinal stromal tumor, originating from the muscularis propria. Eventually endoscopic resection was performed, combining ESD and EFTR (hybrid ESD-EFTR). Contrary to expectations, histology revealed a gastric schwannoma. This case illustrates an efficient and safe endoscopic hybrid technique for the removal of submucosal gastric lesions.

Clinical course of asymptomatic duodenal subepithelial lesions.

BACKGROUND/AIMS: There is limited knowledge regarding the management of duodenal subepithelial lesions (SELs) owing to a lack of understanding of their natural course. This study aimed to assess the natural course of asymptomatic duodenal SELs and provide management recommendations. METHODS: Patients diagnosed with duodenal SELs and followed up for a minimum of 6 months were retrospectively investigated. RESULTS: Among the 443,533 patients who underwent esophagogastroduodenoscopy between 2008 and 2020, duodenal SELs were identified in 0.39% (1,713 patients). Among them, 396 duodenal SELs were monitored for a median period of 72.5 months (interquartile range, 37.7-111.3 mo). Of them, 16 SELs (4.0%) showed substantial changes in size or morphology at a median follow-up of 35.1 months (interquartile range, 21.7-51.4 mo). Of these SELs with substantial changes, tissues of two SELs were acquired using endoscopic ultrasound-guided fine needle aspiration biopsy: one was a lipoma and the other was non-diagnostic. Three SELs were surgically or endoscopically removed; two were diagnosed as gastrointestinal stromal tumors, and one was a lipoma. An initial size of 20 mm or larger was associated with substantial changes during follow-up (p = 0.016). CONCLUSION: While the majority of duodenal SELs may not exhibit substantial interval changes, regular follow-up with endoscopy may be necessary for cases with an initial size of 20 mm or larger, considering a possibility of malignancy.

Efficacy of real-time artificial intelligence-aid endoscopic ultrasonography diagnostic system in discriminating gastrointestinal stromal tumors and leiomyomas: a multicenter diagnostic study.

Background: Gastrointestinal stromal tumors (GISTs) represent the most prevalent type of subepithelial lesions (SELs) with malignant potential. Current imaging tools struggle to differentiate GISTs from leiomyomas. This study aimed to create and assess a real-time artificial intelligence (AI) system using endoscopic ultrasonography (EUS) images to differentiate between GISTs and leiomyomas. Methods: The AI system underwent development and evaluation using EUS images from 5 endoscopic centers in China between January 2020 and August 2023. EUS images of 1101 participants with SELs were retrospectively collected for AI system development. A cohort of 241 participants with SELs was recruited for external AI system evaluation. Another cohort of 59 participants with SELs was prospectively enrolled to assess the real-time clinical application of the AI system. The AI system's performance was compared to that of endoscopists. This study is registered with Chictr.org.cn, Number ChiCT2000035787. Findings: The AI system displayed an area under the curve (AUC) of 0.948 (95% CI: 0.921-0.969) for discriminating GISTs and leiomyomas. The AI system's accuracy (ACC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) reached 91.7% (95% CI 87.5%-94.6%), 90.3% (95% CI 83.4%-94.5%), 93.0% (95% CI 87.2%-96.3%), 91.9% (95% CI 85.3%-95.7%), and 91.5% (95% CI 85.5%-95.2%), respectively. Moreover, the AI system exhibited excellent performance in diagnosing ≤20 mm SELs (ACC 93.5%, 95% CI 0.900-0.969). In a prospective real-time clinical application trial, the AI system achieved an AUC of 0.865 (95% CI 0.764-0.966) and 0.864 (95% CI 0.762-0.966) for GISTs and leiomyomas diagnosis, respectively, markedly surpassing endoscopists [AUC 0.698 (95% CI 0.562-0.834) for GISTs and AUC 0.695 (95% CI 0.546-0.825) for leiomyomas]. Interpretation: We successfully developed a real-time AI-assisted EUS diagnostic system. The incorporation of the real-time AI system during EUS examinations can assist endoscopists in rapidly and accurately differentiating various types of SELs in clinical practice, facilitating improved diagnostic and therapeutic decision-making. Funding: Science and Technology Commission Foundation of Shanghai Municipality, Science and Technology Commission Foundation of the Xuhui District, the Interdisciplinary Program of Shanghai Jiao Tong University and the Research Funds of Shanghai Sixth people's Hospital.

AGA Clinical Practice Update on Endoscopic Full-Thickness Resection for the Management of Gastrointestinal Subepithelial Lesions: Commentary.

DESCRIPTION: Subepithelial lesions of the gastrointestinal tract are not encountered uncommonly during routine endoscopy. There has been remarkable progress in the development of endoscopic options for the resection of subepithelial lesions, including full-thickness resection. The purpose of this American Gastroenterological Association (AGA) Clinical Practice Update (CPU) is to describe the various techniques for endoscopic full-thickness resection and to facilitate their appropriate application in the management of subepithelial lesions. METHODS: This CPU was commissioned and approved by the AGA Institute Clinical Practice Updates Committee (CPUC) and the AGA Governing Board to provide timely guidance on a topic of high clinical importance to the AGA membership and underwent internal peer review by the CPUC and external peer review through standard procedures of Gastroenterology.

Multiple GISTand pheochromocytoma -A rare associationin neurofibromatosis type 1 / GIST múltipley feocromocitoma -Una asociación raraen neurofibromatosis tipo 1

We describe a case of coexistence of multiple gastrointestinal stromal tumors (GIST) and pheochromocytoma in a 32-year-old patient with neurofibromatosis type 1. The coexistence of these two conditions in patients with this syndrome is extremely rare.(AU)

Effective submucosal tunneling endoscopic resection (STER) of a giant esophageal leiomyoma / Tunelización submucosa eficaz resección endoscópica (STER) de un esófago gigante leiomioma

We report the successful removal of a giant esophageal leiomyoma using submucosal tunneling endoscopic resection in a 37-year-old woman with significant dysphagia.(AU)

Gastric Schwannoma: A Rare Subepithelial Lesion of the Stomach.

Gastric schwannomas (GS) are rare, slow-growing, benign subepithelial (SE) lesions of the stomach. These are difficult to differentiate preoperatively from other types of SE lesions, as the gross appearance and clinical presentation are very similar especially the gastrointestinal stromal tumors (GISTs), which are the most common SE lesions of the stomach. We present the case of a 35-year-old Asian man with a one-month history of intermittent, right, upper quadrant pain and hematemesis. Preoperatively, intravenous contrast-enhanced computer tomography scan (CECT) showed a well-circumscribed lesion in the upper abdomen closer to the stomach's lesser curvature. Endoscopic ultrasound revealed an ulcerated subepithelial lesion and subsequent biopsy with a 22-gauge fine-needle biopsy (22G FNB) needle confirmed the diagnosis of GS. The patient underwent distal gastrectomy and a Bilroth 1 procedure. The postoperative biopsy was consistent with the initial one, therefore supporting the diagnosis of gastric schwannoma. Postoperatively, the recovery remained uneventful.

Endoscopic ultrasound artificial intelligence-assisted for prediction of gastrointestinal stromal tumors diagnosis: A systematic review and meta-analysis.

BACKGROUND: Subepithelial lesions (SELs) are gastrointestinal tumors with heterogeneous malignant potential. Endoscopic ultrasonography (EUS) is the leading method for evaluation, but without histopathological analysis, precise differentiation of SEL risk is limited. Artificial intelligence (AI) is a promising aid for the diagnosis of gastrointestinal lesions in the absence of histopathology. AIM: To determine the diagnostic accuracy of AI-assisted EUS in diagnosing SELs, especially lesions originating from the muscularis propria layer. METHODS: Electronic databases including PubMed, EMBASE, and Cochrane Library were searched. Patients of any sex and > 18 years, with SELs assessed by EUS AI-assisted, with previous histopathological diagnosis, and presented sufficient data values which were extracted to construct a 2 × 2 table. The reference standard was histopathology. The primary outcome was the accuracy of AI for gastrointestinal stromal tumor (GIST). Secondary outcomes were AI-assisted EUS diagnosis for GIST vs gastrointestinal leiomyoma (GIL), the diagnostic performance of experienced endoscopists for GIST, and GIST vs GIL. Pooled sensitivity, specificity, positive, and negative predictive values were calculated. The corresponding summary receiver operating characteristic curve and post-test probability were also analyzed. RESULTS: Eight retrospective studies with a total of 2355 patients and 44154 images were included in this meta-analysis. The AI-assisted EUS for GIST diagnosis showed a sensitivity of 92% [95% confidence interval (CI): 0.89-0.95; P < 0.01), specificity of 80% (95%CI: 0.75-0.85; P < 0.01), and area under the curve (AUC) of 0.949. For diagnosis of GIST vs GIL by AI-assisted EUS, specificity was 90% (95%CI: 0.88-0.95; P = 0.02) and AUC of 0.966. The experienced endoscopists' values were sensitivity of 72% (95%CI: 0.67-0.76; P < 0.01), specificity of 70% (95%CI: 0.64-0.76; P < 0.01), and AUC of 0.777 for GIST. Evaluating GIST vs GIL, the experts achieved a sensitivity of 73% (95%CI: 0.65-0.80; P < 0.01) and an AUC of 0.819. CONCLUSION: AI-assisted EUS has high diagnostic accuracy for fourth-layer SELs, especially for GIST, demonstrating superiority compared to experienced endoscopists' and improving their diagnostic performance in the absence of invasive procedures.

Prevalence, natural progression, and clinical practices of upper gastrointestinal subepithelial lesions in Korea: a multicenter study.

BACKGROUND/AIMS: This study aimed to evaluate the prevalence and natural progression of subepithelial lesions (SELs) in the upper gastrointestinal (UGI) tract. METHODS: The medical records of patients with UGI SELs who underwent endoscopic screening at eight university hospitals between January and December 2010 were retrospectively investigated. The follow-up evaluations were performed until December 2016. RESULTS: UGI SELs were found in 1,044 of the 65,233 participants screened (endoscopic prevalence, 1.60%; the total number of lesions, 1,062; mean age, 55.1±11.2 years; men, 53.6%). The median follow-up period was 48 (range, 8-74) months. SELs were most frequently found in the stomach (63.8%) and had a mean size of 9.9±6.1 mm. Endoscopic ultrasonography (EUS) was performed in 293 patients (28.1%). The most common lesions were leiomyomas, followed by gastrointestinal stromal tumors (GISTs), and ectopic pancreas. The proportions of SELs with malignant potential according to size were 3% (<1 cm), 22% (1-2 cm), 27% (2-3 cm), and 38% (≥3 cm). In gastric SELs larger than 1 cm, resections were performed in 20 patients because of an increase in size, of which 12 were found to be GISTs. CONCLUSION: The prevalence of UGI SELs was 1.60%. Further, 23% of gastric SELs ≥1 cm were precancerous lesions, most followed by EUS and clinical decisions without initial pathological confirmation.

Recent advances and current challenges in endoscopic resection with the full-thickness resection device.

Endoscopic full-thickness resection (EFTR) has emerged as a viable technique in the management of mucosal and subepithelial lesions of the gastrointestinal tract (GIT) not amenable to conventional therapeutic approaches. While various devices and techniques have been described for EFTR, a single, combined full-thickness resection and closure device (full-thickness resection device, FTRD system, Ovesco Endoscopy AG, Tuebingen, Germany) has become commercially available in recent years. Initially, the FTRD system was limited to use in the colorectum only. Recently, a modified version of the FTRD has been released for EFTR in the upper GIT as well. This review provides a broad summary of the FTRD, highlighting recent advances and current challenges.

Endoscopic ultrasound-guided fine-needle aspiration for gastrointestinal subepithelial lesions.

Endoscopic ultrasound-guided fine-needle aspiration (EUS-FNA) is the first-choice procedure for obtaining pathological tissue samples from gastrointestinal (GI) subepithelial lesions (SELs). However, its diagnostic accuracy is lower than that for pancreatic masses owing to puncture difficulty and the need for immunostaining for definitive diagnosis. The advent of fine-needle biopsy needles, which have become well known in recent years, improves the diagnostic accuracy of EUS-FNA for GI SELs. The forward-viewing echoendoscope and rapid on-site evaluation (ROSE) have also helped to improve diagnostic accuracy. Furthermore, in facilities where ROSE is not available, endosonographers perform a macroscopic on-site evaluation. With these procedural innovations, EUS-FNA is now performed aggressively even for SELs smaller than 20 mm. The incidence of procedure-related adverse events such as bleeding and infection is low, and thus, EUS-FNA can be safely performed to diagnose SELs.

EUS-Guided Diagnosis of Gastric Subepithelial Lesions, What Is New?

Gastric subepithelial lesions (SELs) are intramural lesions that arise underneath the gastric mucosa. SELs can be benign, but can also be malignant or have malignant potential. Therefore, correct diagnosis is crucial. Endosonography has been established as the diagnostic gold standard. Although the identification of some of these lesions can be carried out immediately, solely based on their echo characteristics, for certain lesions histological examination is necessary. Sometimes histology can be inconclusive, especially for smaller lesions. Therefore, new methods have been developed in recent years to assist decision making, such as contrast enhanced endosonography, EUS elastography, and artificial intelligence systems. In this narrative review we provide a complete overview of the gastric SELs and summarize the new data of the last ten years concerning the diagnostic advances of endosonography on this topic.

Comparison of endoscopic ultrasound-guided fine needle aspiration cytology versus endoscopic biopsy for the diagnosis of subepithelial lesions of the upper and lower gastrointestinal tract: A 10-year retrospective single institution analysis.

BACKGROUND: The aim of this study is to compare the diagnostic accuracy of endoscopic ultrasound-guided fine needle aspiration (EUS-FNA) versus endoscopic biopsy for the diagnosis of gastrointestinal (GI) subepithelial lesions (SELs) using surgical resection as the gold standard. METHODS: All patients who underwent EUS-FNA of upper and lower GI SELs over a 10-year period (2010 through 2019) were retrospectively reviewed. The medical records of all patients were reviewed and data extracted from the endoscopy, pathology, and surgical reports were analyzed. RESULTS: In total, 283 patients with ages ranging from 21 to 92 years underwent EUS-FNA for evaluation of GI SELs, 117 (41%) patients underwent endoscopic biopsy and 82 (29%) patients had concurrent surgical resection specimen. EUS-FNA was obtained from the stomach in 167 (59%) patients, duodenum in 51 (18%) patients, esophagus in 38 (13%) patients, and colorectum in 27 (10%) patients. It was found that the largest percentage of lesions originated in the muscularis propria (36%), followed by the submucosa (26%), deep mucosa (13%), and not specified in 21%. The concordance between EUS-FNA and endoscopic biopsy was good (correlation coefficient of 0.631, p < .001). EUS-FNA versus endoscopic biopsy in resected cases showed sensitivity and specificity of 78% versus 68% and 84% versus 100%, respectively. The EUS-FNA has an accuracy of 80% compared to 74% in biopsy. The diagnostic yield of EUS-FNA and endoscopic biopsy was 64% versus 55%. CONCLUSION: EUS-FNA is more sensitive and more accurate than endoscopic biopsy for diagnosing GI SELs with a good concordance between the two techniques.

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.

Efficacy and Safety of Laparoscopic Endoscopic Cooperative Surgery in Upper Gastrointestinal Lesions: A Systematic Review and Meta-Analysis.

Background and Aims: Laparoscopic and endoscopic cooperative surgery (LECS) combines advantages of endoscopy and laparoscopy in order to resect upper gastrointestinal lesions. Our aim was to evaluate the efficacy and safety of LECS in patients with EGJ (esophagogastric junction), gastric and duodenal lesions, as well as to compare LECS with pure endoscopic and pure laparoscopic procedures. Methods: PubMed, Scopus, and ISI Web of Knowledge were searched. Efficacy (R0, recurrence) and safety (conversion rate, procedure and hospitalization time, adverse events, mortality) outcomes were extracted and pooled (odds ratio or mean difference) using a random-effects model. Study quality was assessed with Newcastle-Ottawa Scale and heterogeneity by Cochran's Q test and I2 . Subgroup analysis according to location was performed. Results: This meta-analysis included 24 studies/1,336 patients (all retrospective cohorts). No significant differences were found between LECS and preexisting techniques (endoscopic submucosal dissection (ESD)/laparoscopy) regarding any outcomes. However, there was a trend to shorter hospitalization time, longer procedure duration, and fewer adverse events in LECS versus Laparoscopy and ESD. R0 tended to be higher in the LECS group. Hospitalization time was significantly shorter in gastric versus EGJ lesions (mean 7.3 vs. 13.7 days, 95% CI: 6.6-7.9 vs. 8.9-19.3). There were no significant differences in conversion rate, adverse events, or mean procedural time according to location. There was a trend to higher conversion rate and longer procedure durations in EGJ and higher rate of adverse events in duodenal lesions. Conclusion: LECS is a valid, safe, and effective treatment option in patients with EGJ, gastric, and duodenal lesions, although existing studies are retrospective and prone to selection bias. Prospective studies are needed to assess if LECS is superior to established techniques. Key Messages: LECS is safe and effective in the treatment of upper gastrointestinal lesions, but there is no evidence of superiority over established techniques.

Introdução e objetivos: A Cirurgia cooperativa laparoscópica e endoscópica (LECS) combina vantagens da endoscopia e laparoscopia na resseção de lesões gastrointestinais superiores. O nosso objetivo é avaliar a eficácia e segurança da LECS em pacientes com lesões na junção esofagogástrica (EGJ), estômago e duodeno, e comparar a LECS com procedimentos puramente endoscópicos e laparoscópicos. Métodos: PubMed, Scopus, ISI Web of Knowledge foram pesquisadas. Dados sobre eficácia (R0, recorrência) e segurança (taxa de conversão, duração do procedimento e hospitalização, recorrência, eventos adversos, mortalidade) foram colhidos e agrupados (odds ratio ou média das diferenças), usando modelo de efeitos randomizados. Qualidade dos estudos foi avaliada pela Escala Newcastle-Ottawa e heterogeneidade pelos testes Q da Cochran e I2. Foi realizada análise de subgrupos, consoante a localização. Resultados: Esta meta-análise incluiu 24 estudos/1336 pacientes (todos coortes retrospetivos). Não encontramos diferenças significativas entre LECS e as técnicas pré-existentes (Disseção endoscópica da submucosa (ESD)/Laparoscopia) em nenhum aspeto. Porém, encontramos uma tendência para hospitalização mais curta, procedimentos mais longos e menos efeitos adversos na LECS versus Laparoscopia e ESD. R0 tende a ser maior no grupo LECS. Hospitalização foi significativamente menor em lesões gástricas versus EGJ (média 7.3 vs. 13.7 dias, 95% CI: 6.6­7.9 vs. 8.9­19.3). Não encontramos diferenças significativas na taxa de conversão, eventos adversos nem tempo médio de procedimento. Porém encontramos uma tendência para taxas de conversão maiores e procedimentos mais longos na EGJ e maior taxa de eventos adversos no duodeno. Conclusão: LECS é um tratamento válido, seguro e eficaz em pacientes com lesões na EGJ, estômago e duodeno, apesar dos estudos retrospetivos existentes estarem propensos a viés de seleção. São necessários estudos prospetivos para avaliar a superioridade da LECS face às técnicas existentes. Mensagens-chave: LECS é um tratamento seguro e eficaz para lesões gastrointestinais superiores, mas sem evidência de superioridade face às técnicas existentes.

Artificial Intelligence in the Prediction of Gastrointestinal Stromal Tumors on Endoscopic Ultrasonography Images: Development, Validation and Comparison with Endosonographers.

Background/Aims: The accuracy of endosonographers in diagnosing gastric subepithelial lesions (SELs) using endoscopic ultrasonography (EUS) is influenced by experience and subjectivity. Artificial intelligence (AI) has achieved remarkable development in this field. This study aimed to develop an AI-based EUS diagnostic model for the diagnosis of SELs, and evaluated its efficacy with external validation. Methods: We developed the EUS-AI model with ResNeSt50 using EUS images from two hospitals to predict the histopathology of the gastric SELs originating from muscularis propria. The diagnostic performance of the model was also validated using EUS images obtained from four other hospitals. Results: A total of 2,057 images from 367 patients (375 SELs) were chosen to build the models, and 914 images from 106 patients (108 SELs) were chosen for external validation. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of the model for differentiating gastrointestinal stromal tumors (GISTs) and non-GISTs in the external validation sets by images were 82.01%, 68.22%, 86.77%, 59.86%, and 78.12%, respectively. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy in the external validation set by tumors were 83.75%, 71.43%, 89.33%, 60.61%, and 80.56%, respectively. The EUS-AI model showed better performance (especially specificity) than some endosonographers. The model helped improve the sensitivity, specificity, and accuracy of certain endosonographers. Conclusions: We developed an EUS-AI model to classify gastric SELs originating from muscularis propria into GISTs and non-GISTs with good accuracy. The model may help improve the diagnostic performance of endosonographers. Further work is required to develop a multi-modal EUS-AI system.

Management of gastrointestinal subepithelial lesions: an answer to the conflicting opinions.

Subepithelial lesions, formerly known as subepithelial tumors, are incidentally discovered protrusions throughout the gastrointestinal tract with normal overlying mucosa. Studies related to the diagnosis and therapy methods are limited due to the low incidence and malignant potential of these lesions. They commonly originating from the second, third, and fourth layers (muscularis mucosa, submucosa, and muscularis propria) of the gastrointestinal wall. They are reported to be more prevalent in the stomach and esophagus than small intestine and colon. Subepithelial lesions in the stomach and duodenum are more prone to malignancy than the lesions in the esophagus. Despite different strategies in the management of subepithelial lesions based on their size and location, there is still not a unique consensus on the issue. In this review, we have attempted to introduce the most practical approach to managing gastrointestinal subepithelial lesions based on current guidelines.

Comparison of 22G Fork-Tip and Franseen Needles and Usefulness of Contrast-Enhanced Endoscopic Ultrasound for Diagnosis of Upper Gastrointestinal Subepithelial Lesions.

Endoscopic ultrasound (EUS)-guided tissue acquisition (EUS-TA) is less accurate in obtaining samples from gastrointestinal subepithelial lesions (SELs) ≤2 cm than from pancreatic cancers. The present study compared the usefulness of 22G Fork-tip and Franseen needles for EUS-TA and assessed the ability of contrast-enhanced harmonic EUS (CH-EUS) to diagnose SELs ≤2 cm. Fifty-seven patients who underwent EUS-TA for SELs ≤2 cm were evaluated. The primary endpoint was to compare the rate of acquisition of sufficient samples by these two needles. Secondary endpoints included technical success rate, adverse events, numbers of needle passes, and diagnostic ability of CH-EUS for SELs. Of the 57 included patients, 23 and 34 underwent EUS-TA with Fork-tip and Franseen needles, respectively. Technical success rates were 100% with both needles and adverse events occurred in zero (0%) and one (2.9%) patient with Fork-tip and Franseen needles, respectively. The rate of adequate sample acquisition was significantly higher using Fork-tip than Franseen needles (96% vs. 74%; p = 0.038). The hyper- or iso-vascular pattern on CH-EUS correlated significantly with a diagnosis of gastrointestinal stromal tumor (p < 0.001). EUS-TA with Fork-tip needles were superior to EUS-TA with Franseen needles in acquiring sufficient samples and CH-EUS was also useful for the diagnosis of SELs ≤2 cm.