The integrity of image acquisition is critical for biliopancreatic EUS reporting, significantly affecting the quality of EUS examinations and disease-related decision-making. However, the quality of EUS reports varies among endoscopists. To address this issue, we developed a deep learning-based EUS automatic image report system (EUS-AIRS), aiming to achieve automatic photodocumentation in real-time during EUS, including capturing standard stations, lesions, and puncture procedures.

Eight deep learning models trained and tested using 235,784 images were integrated to construct the EUS-AIRS. The performance of EUS-AIRS was tested through man-machine comparisons at 2 levels: a retrospective test (include internal and external testing) and a prospective test. From May 2023 to October 2023, a total of 114 patients undergoing EUS at Renmin Hospital of Wuhan University were consecutively recruited for prospective testing. The primary outcome was the completeness of the EUS-AIRS for capturing standard stations.

In terms of completeness in capturing biliopancreatic standard stations, EUS-AIRS exceeded the capabilities of endoscopists at all levels of expertise in retrospective internal testing (90.8% [95% confidence interval (CI), 88.7%-92.9%] vs 70.5% [95% CI, 67.2%-73.8%]; P < .001) and external testing (91.4% [95% CI, 88.4%-94.4%] vs 68.2% [95% CI, 63.3%-73.2%]; P < .001). EUS-AIRS exhibited high accuracy and completeness in capturing standard station images. The completeness of the EUS-AIRS significantly outperformed manual endoscopist reports (91.4% [95% CI, 89.4%-93.4%] vs 78.1% [95% CI, 75.1%-81.0%); P < .001).

EUS-AIRS exhibits exceptional capabilities in real-time, capturing high-quality and high-integrity biliopancreatic EUS images. This showcases the potential of applying an artificial intelligence image report system in the EUS field.

Endoscopic ultrasound (EUS) is widely used for the diagnosis of biliopancreatic and gastrointestinal tract diseases, but it is one of the most operator-dependent endoscopic techniques, requiring a long and complex learning curve. The role of artificial intelligence (AI) in EUS is growing as AI algorithms can assist in lesion detection and characterization by analyzing EUS images. Deep learning (DL) techniques, such as convolutional neural networks, have shown great potential for tumor identification; the application of AI models can increase the EUS diagnostic accuracy, provide faster diagnoses, and provide more information that can be helpful also for a training program.

Artificial Intelligence (AI) is transforming pancreaticobiliary endoscopy by enhancing diagnostic accuracy, procedural efficiency, and clinical outcomes. This narrative review explores AI's applications in endoscopic ultrasound (EUS) and endoscopic retrograde cholangiopancreatography (ERCP), emphasizing its potential to address diagnostic and therapeutic challenges in pancreaticobiliary diseases. In EUS, AI improves pancreatic mass differentiation, malignancy prediction, and landmark recognition, demonstrating high diagnostic accuracy and outperforming traditional guidelines. In ERCP, AI facilitates precise biliary stricture identification, optimizes procedural techniques, and supports decision-making through real-time data integration, improving ampulla recognition and predicting cannulation difficulty. Additionally, predictive analytics help mitigate complications like post-ERCP pancreatitis. The future of AI in pancreaticobiliary endoscopy lies in multimodal data fusion, integrating imaging, genomic, and molecular data to enable personalized medicine. However, challenges such as data quality, external validation, clinician training, and ethical concerns-like data privacy and algorithmic bias-must be addressed to ensure safe implementation. By overcoming these challenges, AI has the potential to redefine pancreaticobiliary healthcare, improving diagnostic accuracy, therapeutic outcomes, and personalized care.

This study aimed to develop and validate intratumoral, peritumoral, and combined radiomic models based on endoscopic ultrasonography (EUS) for retrospectively differentiating pancreatic neuroendocrine tumors (PNETs) from pancreatic cancer.

A total of 257 patients, including 151 with pancreatic cancer and 106 with PNETs, were retroactively enrolled after confirmation through pathological examination. These patients were randomized to either the training or test cohort in a ratio of 7:3. Radiomic features were extracted from the intratumoral and peritumoral regions from conventional EUS images. Following this, the radiomic features underwent dimensionality reduction through the utilization of the least absolute shrinkage and selection operator (LASSO) algorithm. Six machine learning algorithms were utilized to train prediction models employing features with nonzero coefficients. The optimum intratumoral radiomic model was identified and subsequently employed for further analysis. Furthermore, a combined radiomic model integrating both intratumoral and peritumoral radiomic features was established and assessed based on the same machine learning algorithm. Finally, a nomogram was constructed, integrating clinical signature and combined radiomics model.

107 radiomic features were extracted from EUS and only those with nonzero coefficients were kept. Among the six radiomic models, the support vector machine (SVM) model had the highest performance with AUCs of 0.853 in the training cohort and 0.755 in the test cohort. A peritumoral radiomic model was developed and assessed, achieving an AUC of 0.841 in the training and 0.785 in the test cohorts. The amalgamated model, incorporating intratumoral and peritumoral radiomic features, exhibited superior predictive accuracy in both the training (AUC=0.861) and test (AUC=0.822) cohorts. These findings were validated using the Delong test. The calibration and decision curve analyses (DCA) of the combined radiomic model displayed exceptional accuracy and provided the greatest net benefit for clinical decision-making when compared to other models. Finally, the nomogram also achieved an excellent performance.

An efficient and accurate EUS-based radiomic model incorporating intratumoral and peritumoral radiomic features was proposed and validated to accurately distinguish PNETs from pancreatic cancer. This research has the potential to offer novel perspectives on enhancing the clinical utility of EUS in the prediction of PNETs.

Artificial intelligence (AI) is defined as the theory and development of computer systems able to perform tasks normally associated with human intelligence. At present, AI has been widely used in a variety of ultrasound tasks, including in point-of-care ultrasound, echocardiography, and various diseases of different organs. However, the characteristics of ultrasound, compared to other imaging modalities, such as computed tomography (CT) and magnetic resonance imaging (MRI), poses significant additional challenges to AI. Application of AI can not only reduce variability during ultrasound image acquisition, but can standardize these interpretations and identify patterns that escape the human eye and brain. These advances have enabled greater innovations in ultrasound AI applications that can be applied to a variety of clinical settings and disease states. Therefore, The World Federation of Ultrasound in Medicine and Biology (WFUMB) is addressing the topic with a brief and practical overview of current and potential future AI applications in medical ultrasound, as well as discuss some current limitations and future challenges to AI implementation.

The rising incidence of pancreatic diseases, including acute and chronic pancreatitis and various pancreatic neoplasms, poses a significant global health challenge. Pancreatic ductal adenocarcinoma (PDAC) for example, has a high mortality rate due to late-stage diagnosis and its inaccessible location. Advances in imaging technologies, though improving diagnostic capabilities, still necessitate biopsy confirmation. Artificial intelligence, particularly machine learning and deep learning, has emerged as a revolutionary force in healthcare, enhancing diagnostic precision and personalizing treatment. This narrative review explores Artificial intelligence's role in pancreatic imaging, its technological advancements, clinical applications, and associated challenges. Following the PRISMA-DTA guidelines, a comprehensive search of databases including PubMed, Scopus, and Cochrane Library was conducted, focusing on Artificial intelligence, machine learning, deep learning, and radiomics in pancreatic imaging. Articles involving human subjects, written in English, and published up to March 31, 2024, were included. The review process involved title and abstract screening, followed by full-text review and refinement based on relevance and novelty. Recent Artificial intelligence advancements have shown promise in detecting and diagnosing pancreatic diseases. Deep learning techniques, particularly convolutional neural networks (CNNs), have been effective in detecting and segmenting pancreatic tissues as well as differentiating between benign and malignant lesions. Deep learning algorithms have also been used to predict survival time, recurrence risk, and therapy response in pancreatic cancer patients. Radiomics approaches, extracting quantitative features from imaging modalities such as CT, MRI, and endoscopic ultrasound, have enhanced the accuracy of these deep learning models. Despite the potential of Artificial intelligence in pancreatic imaging, challenges such as legal and ethical considerations, algorithm transparency, and data security remain. This review underscores the transformative potential of Artificial intelligence in enhancing the diagnosis and treatment of pancreatic diseases, ultimately aiming to improve patient outcomes and survival rates.

Endoscopic ultrasound (EUS) is the most sensitive method for evaluation of pancreatic lesions but is limited by significant operator dependency. Artificial intelligence (AI), in the form of computer-aided detection (CADe) systems, has shown potential in increasing accuracy and bridging operator dependency in several endoscopic domains. However, the complexity of integrating AI into EUS is far more challenging. This aims to develop and test the basis for a CADe system for real-time detection and segmentation of all pancreatic lesions.

In this single-center study EUS studies of pancreatic findings were included. Lesions were outlined by two expert (>5 years performing EUS) endoscopists, and the two leading types of models were benchmarked. The models' performance was evaluated through per-pixel intersection over union (IoU).

A total of 1497 EUS images from 165 patients were evaluated. The dataset included malignancies, neuroendocrine tumors, benign cysts, chronic and acute pancreatitis, normal fatty pancreas, and benign lesions. The best model demonstrated detection and segmentation on the test set with a mean IoU of 0.73, achieving a PPV, NPV, total accuracy, and ROC of 0.82, 0.96, 0.95, and 0.95, respectively. The algorithm is adaptable for real-time processing.

We developed and tested deep learning models for real-time detection and segmentation of pancreatic lesions during EUS with promising results. This constitutes the basis for a CADe system for EUS, which could be valuable in future detection and evaluation of pancreatic lesions. Further studies for validation and generalization are underway.

Pancreatic ductal adenocarcinoma continues to have a poor prognosis, although recent advances in neoadjuvant treatments (NATs) have provided some hope. Imaging assessment of suspected tumours can be challenging and requires a specific approach, with pancreas protocol CT being the primary imaging modality for staging with other modalities used as problem-solving tools to facilitate appropriate management. Imaging assessment post NAT can be particularly difficult due to a current lack of robust radiological criteria to predict response and differentiate treatment induced fibrosis/inflammation from residual tumour. This review aims to provide an update of pancreatic ductal adenocarcinoma with particular focus on three points: tumour staging pre- and post-NAT including vascular assessment, structured reporting with introduction of the PAncreatic Cancer reporting Template-UK (PACT-UK) radiology template, and the potential future role of artificial intelligence in the diagnosis and staging of pancreatic cancer.

The purpose of this study is to establish a deep learning automatic assistance diagnosis system for benign and malignant classification of mediastinal lesions in endobronchial ultrasound (EBUS) images. EBUS images are in the form of video and contain multiple imaging modes. Different imaging modes and different frames can reflect the different characteristics of lesions. Compared with previous studies, the proposed model can efficiently extract and integrate the spatiotemporal relationships between different modes and does not require manual selection of representative frames. In recent years, Vision Transformer has received much attention in the field of computer vision. Combined with convolutional neural networks, hybrid transformers can also perform well on small datasets. This study designed a novel deep learning architecture based on hybrid transformer called TransEBUS. By adding learnable parameters in the temporal dimension, TransEBUS was able to extract spatiotemporal features from insufficient data. In addition, we designed a two-stream module to integrate information from three different imaging modes of EBUS. Furthermore, we applied contrastive learning when training TransEBUS, enabling it to learn discriminative representation of benign and malignant mediastinal lesions. The results show that TransEBUS achieved a diagnostic accuracy of 82% and an area under the curve of 0.8812 in the test dataset, outperforming other methods. It also shows that several models can improve performance by incorporating two-stream module. Our proposed system has shown its potential to help physicians distinguishing benign and malignant mediastinal lesions, thereby ensuring the accuracy of EBUS examination.

Pancreatic cystic lesions (PCLs) represent a spectrum of non-neoplasms and neoplasms with varying malignant potential, posing significant challenges in diagnosis and management. While some PCLs are precursors to pancreatic cancer, others remain benign, necessitating accurate differentiation for optimal patient care. Conventional approaches to PCL management rely heavily on radiographic imaging, and endoscopic ultrasound (EUS) guided fine-needle aspiration (FNA), coupled with clinical and biochemical data. However, the observer-dependent nature of image interpretation and the complex morphology of PCLs can lead to diagnostic uncertainty and variability in patient management strategies. This review critically evaluates current PCL diagnosis and surveillance practices, showing features of the different lesions and highlighting the potential limitations of conventional methods. We then explore the potential of artificial intelligence (AI) to transform PCL management. AI-driven strategies, including deep learning algorithms for automated pancreas and lesion segmentation, and radiomics for analyzing heterogeneity, can improve diagnostic accuracy and risk stratification. These advanced techniques can provide more objective and reproducible assessments, aiding clinicians in decision-making regarding follow-up intervals and surgical interventions. Early results suggest that AI-driven methods can significantly improve patient outcomes by enabling earlier detection of high-risk lesions and reducing unnecessary procedures for benign cysts. Finally, this review emphasizes that AI-driven approaches could potentially reshape the landscape of PCL management, ultimately leading to improved pancreatic cancer prevention.

Endoscopic ultrasound (EUS) effectively diagnoses malignant and pre-malignant gastrointestinal lesions. In the past few years, artificial intelligence (AI) has shown promising results in enhancing EUS sensitivity and accuracy, particularly for subepithelial lesions (SELs) like gastrointestinal stromal tumors (GISTs). Furthermore, AI models have shown high accuracy in predicting malignancy in gastric GISTs and distinguishing between benign and malignant intraductal papillary mucinous neoplasms (IPMNs). The utility of AI has also been applied to existing and emerging technologies involved in the performance and evaluation of EUS-guided biopsies. These advancements may improve training in EUS, allowing trainees to focus on technical skills and image interpretation. This review evaluates the current state of AI in EUS, covering imaging diagnosis, EUS-guided biopsies, and training advancements. It discusses early feasibility studies and recent developments, while also addressing the limitations and challenges. This article aims to review AI applications to EUS and its applications in clinical practice while addressing pitfalls and challenges.

Bowel-preserving local resection of early rectal cancer is less successful if the tumor infiltrates the muscularis propria as opposed to submucosal infiltration only. Magnetic resonance imaging currently lacks the spatial resolution to provide a reliable estimation of the infiltration depth. Endoscopic ultrasound (EUS) has better resolution, but its interpretation is investigator dependent. We hypothesize that automated image segmentation of EUS could be a way to standardize EUS interpretation.

EUS media and outcome data were collected prospectively. Based on 373 expert manual segmentations, a convolutional neural network was developed to perform segmentation of the submucosa, muscularis propria, and tumors. The mean surface distance (MSD), maximal distance between segmentations (Hausdorff distance; HDD), and overlap (Dice similarity index; DSI) were calculated.

The median MSD and HDD values were 3.2 and 17.7 pixels for the tumor, 3.4 and 24.7 pixels for the submucosa, and 2.6 and 20.0 pixels for the muscularis propria, respectively. The median DSI values for the tumor, submucosa, and muscularis propria were 0.82, 0.57, and 0.59, respectively. These values reflect good agreement between manual and deep learning segmentation.

This study found encouraging results of using automated analysis of EUS images of early rectal cancer, supporting further exploration in clinical practice.

Recent advancements in artificial intelligence (AI) have significantly impacted the field of gastrointestinal (GI) endoscopy, with applications spanning a wide range of clinical indications. The central goals for AI in GI endoscopy are to improve endoscopic procedural performance and quality assessment, optimize patient outcomes, and reduce administrative burden. Despite early progress, such as Food and Drug Administration approval of the first computer-aided polyp detection system in 2021, there are numerous important challenges to be faced on the path toward broader adoption of AI algorithms in clinical endoscopic practice.

The development and implementation of artificial intelligence (AI), particularly deep learning (DL) models, has generated significant interest across various fields of gastroenterology. While research in luminal endoscopy has seen rapid translation to clinical practice with approved AI devices, its potential extends far beyond, offering promising benefits for biliopancreatic endoscopy like optical characterization of strictures during cholangioscopy or detection and classification of pancreatic lesions during diagnostic endoscopic ultrasound (EUS). This narrative review provides an up-to-date of the latest literature and available studies in this field. Serving as a comprehensive guide to the current landscape of AI in biliopancreatic endoscopy, emphasizing technological advancements, main applications, ethical considerations, and future directions for research and clinical implementation.

EUS-guided fine-needle biopsy is the procedure of choice for the diagnosis of pancreatic ductal adenocarcinoma (PDAC). Nevertheless, the samples obtained are small and require expertise in pathology, whereas the diagnosis is difficult in view of the scarcity of malignant cells and the important desmoplastic reaction of these tumors. With the help of artificial intelligence, the deep learning architectures produce a fast, accurate, and automated approach for PDAC image segmentation based on whole-slide imaging. Given the effectiveness of U-Net in semantic segmentation, numerous variants and improvements have emerged, specifically for whole-slide imaging segmentation.

In this study, a comparison of 7 U-Net architecture variants was performed on 2 different datasets of EUS-guided fine-needle biopsy samples from 2 medical centers (31 and 33 whole-slide images, respectively) with different parameters and acquisition tools. The U-Net architecture variants evaluated included some that had not been previously explored for PDAC whole-slide image segmentation. The evaluation of their performance involved calculating accuracy through the mean Dice coefficient and mean intersection over union (IoU).

The highest segmentation accuracies were obtained using Inception U-Net architecture for both datasets. PDAC tissue was segmented with the overall average Dice coefficient of 97.82% and IoU of 0.87 for Dataset 1, respectively, overall average Dice coefficient of 95.70%, and IoU of 0.79 for Dataset 2. Also, we considered the external testing of the trained segmentation models by performing the cross evaluations between the 2 datasets. The Inception U-Net model trained on Train Dataset 1 performed with the overall average Dice coefficient of 93.12% and IoU of 0.74 on Test Dataset 2. The Inception U-Net model trained on Train Dataset 2 performed with the overall average Dice coefficient of 92.09% and IoU of 0.81 on Test Dataset 1.

The findings of this study demonstrated the feasibility of utilizing artificial intelligence for assessing PDAC segmentation in whole-slide imaging, supported by promising scores.

The digitization of medicine will play an increasingly significant role in future years. In particular, telemedicine, Virtual Reality (VR) and innovative Artificial Intelligence (AI) systems offer tremendous potential in imaging diagnostics and are expected to shape ultrasound diagnostics and teaching significantly. However, it is crucial to consider the advantages and disadvantages of employing these new technologies and how best to teach and manage their use. This paper provides an overview of telemedicine, VR and AI in student ultrasound education, presenting current perspectives and controversies.

Pancreaticobiliary endoscopy is an essential tool for diagnosing and treating pancreaticobiliary diseases. However, it does not fully meet clinical needs, which presents challenges such as significant difficulty in operation and risks of missed diagnosis or misdiagnosis. In recent years, artificial intelligence (AI) has enhanced the diagnostic and treatment efficiency and quality of pancreaticobiliary endoscopy. Diagnosis and differential diagnosis based on endoscopic ultrasound (EUS) images, pathology of EUS-guided fine-needle aspiration or biopsy, need for endoscopic retrograde cholangiopancreatography (ERCP) and assessment of operational difficulty, postoperative complications and prediction of patient prognosis, and real-time procedure guidance. This review provides an overview of AI applications in pancreaticobiliary endoscopy and proposes future development directions in aspects such as data quality and algorithmic interpretability, aiming to provide new insights for the integration of AI technology with pancreaticobiliary endoscopy.

Pancreatic cancer does not show specific symptoms, which makes the diagnosis of early stages difficult with established image-based screening methods and therefore has the worst prognosis among all cancers. Although endoscopic ultrasonography (EUS) has a key role in diagnostic algorithms for pancreatic diseases, B-mode imaging of the pancreas can be affected by confounders such as chronic pancreatitis, which can make both pancreatic lesion segmentation and classification laborious and highly specialized. To address these challenges, this work proposes a semi-supervised multi-task network (SSM-Net) to leverage unlabeled and labeled EUS images for joint pancreatic lesion classification and segmentation. Specifically, we first devise a saliency-aware representation learning module (SRLM) on a large number of unlabeled images to train a feature extraction encoder network for labeled images by computing a contrastive loss with a semantic saliency map, which is obtained by our spectral residual module (SRM). Moreover, for labeled EUS images, we devise channel attention blocks (CABs) to refine the features extracted from the pre-trained encoder on unlabeled images for segmenting lesions, and then devise a merged global attention module (MGAM) and a feature similarity loss (FSL) for obtaining a lesion classification result. We collect a large-scale EUS-based pancreas image dataset (LS-EUSPI) consisting of 9,555 pathologically proven labeled EUS images (499 patients from four categories) and 15,500 unlabeled EUS images. Experimental results on the LS-EUSPI dataset and a public thyroid gland lesion dataset show that our SSM-Net clearly outperforms state-of-the-art methods.

Pancreatic cancer is a highly lethal disease with a poor prognosis. Its early diagnosis and accurate treatment mainly rely on medical imaging, so accurate medical image analysis is especially vital for pancreatic cancer patients. However, medical image analysis of pancreatic cancer is facing challenges due to ambiguous symptoms, high misdiagnosis rates, and significant financial costs. Artificial intelligence (AI) offers a promising solution by relieving medical personnel's workload, improving clinical decision-making, and reducing patient costs. This study focuses on AI applications such as segmentation, classification, object detection, and prognosis prediction across five types of medical imaging: CT, MRI, EUS, PET, and pathological images, as well as integrating these imaging modalities to boost diagnostic accuracy and treatment efficiency. In addition, this study discusses current hot topics and future directions aimed at overcoming the challenges in AI-enabled automated pancreatic cancer diagnosis algorithms.

The pancreas is a vital organ in digestive system which has significant health implications. It is imperative to evaluate and identify malignant pancreatic lesions promptly in light of the high mortality rate linked to such malignancies. Endoscopic Ultrasound (EUS) is a non-invasive precise technique to detect pancreas disorders, but it is highly operator dependent. Artificial intelligence (AI), including traditional machine learning (ML) and deep learning (DL) techniques can play a pivotal role to enhancing the performance of EUS regardless of operator. AI performs a critical function in the detection, classification, and segmentation of medical images. The utilization of AI-assisted systems has improved the accuracy and productivity of pancreatic analysis, including the detection of diverse pancreatic disorders (e.g., pancreatitis, masses, and cysts) as well as landmarks and parenchyma. This systematic review examines the rapidly developing domain of AI-assisted system in EUS of the pancreas. Its objective is to present a thorough study of the present research status and developments in this area. This paper explores the significant challenges of AI-assisted system in pancreas EUS imaging, highlights the potential of AI techniques in addressing these challenges, and suggests the scope for future research in domain of AI-assisted EUS systems.

To develop and validate various ultrasomics models based on endoscopic ultrasonography (EUS) for retrospective differentiating pancreatic neuroendocrine tumors (PNET) from pancreatic cancer.

A 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.

A 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.

A 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.

Pancreatic and biliary diseases encompass a range of conditions requiring accurate diagnosis for appropriate treatment strategies. This diagnosis relies heavily on imaging techniques like endoscopic ultrasonography and endoscopic retrograde cholangiopancreatography. Artificial intelligence (AI), including machine learning and deep learning, is becoming integral in medical imaging and diagnostics, such as the detection of colorectal polyps. AI shows great potential in diagnosing pancreatobiliary diseases. Unlike machine learning, which requires feature extraction and selection, deep learning can utilize images directly as input. Accurate evaluation of AI performance is a complex task due to varied terminologies, evaluation methods, and development stages. Essential aspects of AI evaluation involve defining the AI's purpose, choosing appropriate gold standards, deciding on the validation phase, and selecting reliable validation methods. AI, particularly deep learning, is increasingly employed in endoscopic ultrasonography and endoscopic retrograde cholangiopancreatography diagnostics, achieving high accuracy levels in detecting and classifying various pancreatobiliary diseases. The AI often performs better than doctors, even in tasks like differentiating benign from malignant pancreatic tumors, cysts, and subepithelial lesions, identifying gallbladder lesions, assessing endoscopic retrograde cholangiopancreatography difficulty, and evaluating the biliary strictures. The potential for AI in diagnosing pancreatobiliary diseases, especially where other modalities have limitations, is considerable. However, a crucial constraint is the need for extensive, high-quality annotated data for AI training. Future advances in AI, such as large language models, promise further applications in the medical field.

There are challenges for beginners to identify standard biliopancreatic system anatomical sites on endoscopic ultrasonography (EUS) images. Therefore, the authors aimed to develop a convolutional neural network (CNN)-based model to identify standard biliopancreatic system anatomical sites on EUS images.

The standard anatomical structures of the gastric and duodenal regions observed by EUS was divided into 14 sites. The authors used 6230 EUS images with standard anatomical sites selected from 1812 patients to train the CNN model, and then tested its diagnostic performance both in internal and external validations. Internal validation set tests were performed on 1569 EUS images of 47 patients from two centers. Externally validated datasets were retrospectively collected from 16 centers, and finally 131 patients with 85 322 EUS images were included. In the external validation, all EUS images were read by CNN model, beginners, and experts, respectively. The final decision made by the experts was considered as the gold standard, and the diagnostic performance between CNN model and beginners were compared.

In the internal test cohort, the accuracy of CNN model was 92.1-100.0% for 14 standard anatomical sites. In the external test cohort, the sensitivity and specificity of CNN model were 89.45-99.92% and 93.35-99.79%, respectively. Compared with beginners, CNN model had higher sensitivity and specificity for 11 sites, and was in good agreement with the experts (Kappa values 0.84-0.98).

The authors developed a CNN-based model to automatically identify standard anatomical sites on EUS images with excellent diagnostic performance, which may serve as a potentially powerful auxiliary tool in future clinical practice.

The European Society of Gastrointestinal Endoscopy (ESGE) has recognized the need to formalize and enhance training in diagnostic endoscopic ultrasound (EUS). This manuscript represents the outcome of a formal Delphi process resulting in an official Position Statement of the ESGE and provides a framework to develop and maintain skills in diagnostic EUS. This curriculum is set out in terms of the prerequisites prior to training; the recommended steps of training to a defined syllabus; the quality of training; and how competence should be defined and evidenced before independent practice. 1:  Trainees should have achieved competence in upper gastrointestinal endoscopy before training in diagnostic EUS. 2:  The development of diagnostic EUS skills by methods that do not involve patients is advisable, but not mandatory, prior to commencing formal training in diagnostic EUS. 3:  A trainee's principal trainer should be performing adequate volumes of diagnostic EUSs to demonstrate maintenance of their own competence. 4:  Training centers for diagnostic EUS should offer expertise, as well as a high volume of procedures per year, to ensure an optimal level of quality for training. Under these conditions, training centers should be able to provide trainees with a sufficient wealth of experience in diagnostic EUS for at least 12 months. 5:  Trainees should engage in formal training and supplement this with a range of learning resources for diagnostic EUS, including EUS-guided fine-needle aspiration and biopsy (FNA/FNB). 6:  EUS training should follow a structured syllabus to guide the learning program. 7:  A minimum procedure volume should be offered to trainees during diagnostic EUS training to ensure that they have the opportunity to achieve competence in the technique. To evaluate competence in diagnostic EUS, trainees should have completed a minimum of 250 supervised EUS procedures: 80 for luminal tumors, 20 for subepithelial lesions, and 150 for pancreaticobiliary lesions. At least 75 EUS-FNA/FNBs should be performed, including mostly pancreaticobiliary lesions. 8:  Competence assessment in diagnostic EUS should take into consideration not only technical skills, but also cognitive and integrative skills. A reliable valid assessment tool should be used regularly during diagnostic EUS training to track the acquisition of competence and to support trainee feedback. 9:  A period of supervised practice should follow the start of independent activity. Supervision can be delivered either on site if other colleagues are already practicing EUS or by maintaining contacts with the training center and/or other EUS experts. 10:  Key performance measures including the annual number of procedures, frequency of obtaining a diagnostic sample during EUS-FNA/FNB, and adverse events should be recorded within an electronic documentation system and evaluated.

EUS is a high-skill technique that requires numerous procedures to achieve competence. However, training facilities are limited worldwide. Convolutional neural network (CNN) models have been previously implemented for object detection. We developed 2 EUS-based CNN models for normal anatomic structure recognition during real-time linear- and radial-array EUS evaluations.

The study was performed from February 2020 to June 2022. Consecutive patient videos of linear- and radial-array EUS videos were recorded. Expert endosonographers identified and labeled 20 normal anatomic structures within the videos for training and validation of the CNN models. Initial CNN models (CNNv1) were developed from 45 videos and the improved models (CNNv2) from an additional 102 videos. CNN model performance was compared with that of 2 expert endosonographers.

CNNv1 used 45,034 linear-array EUS frames and 21,063 radial-array EUS frames. CNNv2 used 148,980 linear-array EUS frames and 128,871 radial-array EUS frames. Linear-array CNNv1 and radial-array CNNv1 achieved a 75.65% and 71.36% mean average precision (mAP) with a total loss of .19 and .18, respectively. Linear-array CNNv2 obtained an 88.7% mAP with a .06 total loss, whereas radial-array CNNv2 achieved an 83.5% mAP with a .07 total loss. CNNv2 accurately detected all studied normal anatomic structures with a >98% observed agreement during clinical validation.

The proposed CNN models accurately recognize the normal anatomic structures in prerecorded videos and real-time EUS. Prospective trials are needed to evaluate the impact of these models on the learning curves of EUS trainees.

Pancreatic cancer has the worst prognosis of all cancers. The clinical application of endoscopic ultrasound (EUS) for the assessment of pancreatic cancer risk and of deep learning for the classification of EUS images have been hindered by inter-grader variability and labeling capability. One of the key reasons for these difficulties is that EUS images are obtained from multiple sources with varying resolutions, effective regions, and interference signals, making the distribution of the data highly variable and negatively impacting the performance of deep learning models. Additionally, manual labeling of images is time-consuming and requires significant effort, leading to the desire to effectively utilize a large amount of unlabeled data for network training. To address these challenges, this study proposes the Dual Self-supervised Multi-Operator Transformation Network (DSMT-Net) for multi-source EUS diagnosis. The DSMT-Net includes a multi-operator transformation approach to standardize the extraction of regions of interest in EUS images and eliminate irrelevant pixels. Furthermore, a transformer-based dual self-supervised network is designed to integrate unlabeled EUS images for pre-training the representation model, which can be transferred to supervised tasks such as classification, detection, and segmentation. A large-scale EUS-based pancreas image dataset (LEPset) has been collected, including 3,500 pathologically proven labeled EUS images (from pancreatic and non-pancreatic cancers) and 8,000 unlabeled EUS images for model development. The self-supervised method has also been applied to breast cancer diagnosis and was compared to state-of-the-art deep learning models on both datasets. The results demonstrate that the DSMT-Net significantly improves the accuracy of pancreatic and breast cancer diagnosis.

Endoscopic ultrasonography (EUS) is a key procedure for the diagnosis of biliopancreatic diseases. However, the performance among EUS endoscopists varies greatly and leads to blind spots during the operation, which can impair the health outcomes of patients. We previously developed an artificial intelligence (AI) device that accurately identified EUS standard stations and significantly reduced the difficulty of ultrasonography image interpretation. In this study, we updated the device (named EUS-IREAD) and validated its performance in improving the quality of EUS procedures.

In this single-centre, randomised, controlled trial, we updated EUS-IREAD so it consisted of five learning models to identify eight EUS stations and 24 anatomical structures. The trial was done at the Renmin Hospital of Wuhan University (Wuhan, China) and included patients aged 18 years or older with suspected biliopancreatic (pancreas and biliopancreatic duct) lesions due to clinical symptoms, radiological findings, or laboratory findings, and with a high risk of pancreatic cancer. Patients were randomly assigned (1:1) by a dedicated research assistant using a computer-generated random number series (with a block size of four) to undergo the EUS procedure with or without the assistance of EUS-IREAD. Endoscopists in the EUS-IREAD-assisted group were required to observe all standard stations and anatomical structures according to the prompts by the AI device. Data collectors, the independent data anaylsis team, and patients were masked to group allocation. The primary outcome was the missed scanning rate of standard stations between the two groups, which was assessed in patients who underwent EUS procedure in accordance with the assigned intervention (per protocol). This trial is registered with ClinicalTrials.gov, NCT05457101.

Between July 9, 2022, and Feb 28, 2023, 290 patients (mean age 55·93 years [SD 14·06], 152 [52%] male, and 138 [48%] female) were randomly assigned and analysed, including 144 in the EUS-IREAD-assisted group and 146 in the control group. The EUS-IREAD-assisted group had a lower missed scanning rate of stations than the control group (4·5% [SD 0·8] vs 14·3% [1·0], -9·8% [95% CI -12·2 to -7·5]; odds ratio 3·6 [95% Cl 2·6 to 4·9]; p<0·0001). No significant adverse event was found during the study.

Our study confirms the capability of EUS-IREAD to monitor the blind spots and reduce the missed rate of stations and structures during EUS procedures. The EUS-IREAD has the potential to play an essential part in EUS quality control.

Innovation Team Project of Health Commission of Hubei Province and College-enterprise Deepening Reform Project of Wuhan University.

EUS is a crucial diagnostic and therapeutic method for many anatomical regions, especially in the evaluation of mediastinal diseases and related pathologies. Rapidly finding the standard stations is the key to achieving efficient and complete mediastinal EUS imaging. However, it requires substantial technical skills and extensive knowledge of mediastinal anatomy. We constructed a system, named EUS-MPS (EUS-mediastinal position system), for real-time mediastinal EUS station recognition.

The standard scanning of mediastinum EUS was divided into 7 stations. There were 33 010 images in mediastinum EUS examination collected to construct a station classification model. Then, we used 151 videos clips for video validation and used 1212 EUS images from 2 other hospitals for external validation. An independent data set containing 230 EUS images was applied for the man-machine contest. We conducted a crossover study to evaluate the effectiveness of this system in reducing the difficulty of mediastinal ultrasound image interpretation.

For station classification, the model achieved an accuracy of 90.49% in image validation and 83.80% in video validation. At external validation, the models achieved 89.85% accuracy. In the man-machine contest, the model achieved an accuracy of 84.78%, which was comparable to that of expert (83.91%). The accuracy of the trainees' station recognition was significantly improved in the crossover study, with an increase of 13.26% (95% confidence interval, 11.04%-15.48%; P < 0.05).

This deep learning-based system shows great performance in mediastinum station localization, having the potential to play an important role in shortening the learning curve and establishing standard mediastinal scanning in the future.

Endoscopic ultrasound (EUS) has emerged as a widely utilized tool in the diagnosis of digestive diseases. In recent years, the potential of artificial intelligence (AI) in healthcare has been gradually recognized, and its superiority in the field of EUS is becoming apparent. Machine learning (ML) and deep learning (DL) are the two main AI algorithms. This paper aims to outline the applications and prospects of artificial intelligence-assisted endoscopic ultrasound (EUS-AI) in digestive diseases over the past decade. The results demonstrated that EUS-AI has shown superiority or at least equivalence to traditional methods in the diagnosis, prognosis, and quality control of subepithelial lesions, early esophageal cancer, early gastric cancer, and pancreatic diseases including pancreatic cystic lesions, autoimmune pancreatitis, and pancreatic cancer. The implementation of EUS-AI has opened up new avenues for individualized precision medicine and has introduced novel diagnostic and treatment approaches for digestive diseases.

Endoscopic Ultrasound (EUS) is widely used for the diagnosis of bilio-pancreatic and gastrointestinal (GI) tract diseases, for the evaluation of subepithelial lesions, and for sampling of lymph nodes and solid masses located next to the GI tract. The role of Artificial Intelligence in healthcare in growing. This review aimed to provide an overview of the current state of AI in EUS from imaging to pathological diagnosis and training.

AI algorithms can assist in lesion detection and characterization in EUS by analyzing EUS images and identifying suspicious areas that may require further clinical evaluation or biopsy sampling. Deep learning techniques, such as convolutional neural networks (CNNs), have shown great potential for tumor identification and subepithelial lesion (SEL) evaluation by extracting important features from EUS images and using them to classify or segment the images.

AI models with new features can increase the accuracy of diagnoses, provide faster diagnoses, identify subtle differences in disease presentation that may be missed by human eyes, and provide more information and insights into disease pathology.

The integration of AI in EUS images and biopsies has the potential to improve the diagnostic accuracy, leading to better patient outcomes and to a reduction in repeated procedures in case of non-diagnostic biopsies.

Endoscopic ultrasound (EUS) plays a crucial role in the diagnosis of both solid and cystic pancreatic lesions and in the staging of patients with pancreatic cancer through its use for tissue and fluid sampling. Additionally, in cases of precancerous lesions, EUS-guided therapy can also be provided. This review aims to describe the most recent developments regarding the role of EUS in the diagnosis and staging of pancreatic lesions. Moreover, complementary EUS imaging modalities, the role of artificial intelligence, new devices, and modalities for tissue acquisition, and techniques for EUS-guided treatment are discussed.

Endoscopic ultrasonography (EUS) is one of the main examinations in pancreatic diseases. A series of the studies reported the application of deep learning (DL)-assisted EUS in the diagnosis of pancreatic diseases. This systematic review is to evaluate the role of DL algorithms in assisting EUS diagnosis of pancreatic diseases.

Literature search were conducted in PubMed and Semantic Scholar databases. Studies that developed DL models for pancreatic diseases based on EUS were eligible for inclusion. This review was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines and quality assessment of the included studies was performed according to the IJMEDI checklist.

A total of 23 studies were enrolled into this systematic review, which could be categorized into three groups according to computer vision tasks: classification, detection and segmentation. Seventeen studies focused on the classification task, among which five studies developed simple neural network (NN) models while twelve studies constructed convolutional NN (CNN) models. Three studies were concerned the detection task and five studies were the segmentation task, all based on CNN architectures. All models presented in the studies performed well based on EUS images, videos or voice. According to the IJMEDI checklist, six studies were recognized as high-grade quality, with scores beyond 35 points.

DL algorithms show great potential in EUS images/videos/voice for pancreatic diseases. However, there is room for improvement such as sample sizes, multi-center cooperation, data preprocessing, model interpretability, and code sharing.

BACKGROUND : There are several types of pancreatic mass, so it is important to distinguish between them before treatment. Artificial intelligence (AI) is a mathematical technique that automates learning and recognition of data patterns. This study aimed to investigate the efficacy of our AI model using endoscopic ultrasonography (EUS) images of multiple types of pancreatic mass (pancreatic ductal adenocarcinoma [PDAC], pancreatic adenosquamous carcinoma [PASC], acinar cell carcinoma [ACC], metastatic pancreatic tumor [MPT], neuroendocrine carcinoma [NEC], neuroendocrine tumor [NET], solid pseudopapillary neoplasm [SPN], chronic pancreatitis, and autoimmune pancreatitis [AIP]). METHODS : Patients who underwent EUS were included in this retrospective study. The included patients were divided into training, validation, and test cohorts. Using these cohorts, an AI model that can distinguish pancreatic carcinomas from noncarcinomatous pancreatic lesions was developed using a deep-learning architecture and the diagnostic performance of the AI model was evaluated. RESULTS : 22 000 images were generated from 933 patients. The area under the curve, sensitivity, specificity, and accuracy (95 %CI) of the AI model for the diagnosis of pancreatic carcinomas in the test cohort were 0.90 (0.84-0.97), 0.94 (0.88-0.98), 0.82 (0.68-0.92), and 0.91 (0.85-0.95), respectively. The per-category sensitivities (95 %CI) of each disease were PDAC 0.96 (0.90-0.99), PASC 1.00 (0.05-1.00), ACC 1.00 (0.22-1.00), MPT 0.33 (0.01-0.91), NEC 1.00 (0.22-1.00), NET 0.93 (0.66-1.00), SPN 1.00 (0.22-1.00), chronic pancreatitis 0.78 (0.52-0.94), and AIP 0.73 (0.39-0.94). CONCLUSIONS : Our developed AI model can distinguish pancreatic carcinomas from noncarcinomatous pancreatic lesions, but external validation is needed.

Pancreatic neuroendocrine tumor (PNET) behavior assessment is a daily challenge for physicians. Modern PNET management varies from a watch-and-wait strategy to surgery depending on tumor aggressiveness. Therefore, the aggressiveness definition plays a pivotal role in the PNET work-up. The aggressiveness of PNETs is mainly based on the dimensions and histological grading, with sometimes a lack of specificity and sensibility. In the last twenty years, EUS has become a cornerstone in the diagnostic phase of PNET management for its high diagnostic yield and the possibility of obtaining a histological specimen. The number of EUS applications in the PNET work-up has been rapidly increasing with new and powerful possibilities. The application of contrast has led to an important step in PNET detection; in recent years, it has been gaining interesting applications in aggressiveness assessment. In this review, we underline the latest experiences and opportunities in the behavior assessment of PNETs using contact-enhanced EUS and contested enhanced harmonic EUS with a particular focus on the future application and possibility that these techniques could provide.

Distinguishing pancreatic cancer from nonneoplastic masses is critical and remains a clinical challenge. The study aims to construct a deep learning-based artificial intelligence system to facilitate pancreatic mass diagnosis, and to guide EUS-guided fine-needle aspiration (EUS-FNA) in real time.

This is a prospective study. The CH-EUS MASTER system is composed of Model 1 (real-time capture and segmentation) and Model 2 (benign and malignant identification). It was developed using deep convolutional neural networks and Random Forest algorithm. Patients with pancreatic masses undergoing CH-EUS examinations followed by EUS-FNA were recruited. All patients underwent CH-EUS and were diagnosed both by endoscopists and CH-EUS MASTER. After diagnosis, they were randomly assigned to undergo EUS-FNA with or without CH-EUS MASTER guidance.

Compared with manual labeling by experts, the average overlap rate of Model 1 was 0.708. In the independent CH-EUS video testing set, Model 2 generated an accuracy of 88.9% in identifying malignant tumors. In clinical trial, the accuracy, sensitivity, and specificity for diagnosing pancreatic masses by CH-EUS MASTER were significantly better than that of endoscopists. The accuracy, sensitivity, specificity, positive predictive value, and negative predictive value were respectively 93.8%, 90.9%, 100%, 100%, and 83.3% by CH-EUS MASTER guided EUS-FNA, and were not significantly different compared to the control group. CH-EUS MASTER-guided EUS-FNA significantly improved the first-pass diagnostic yield.

CH-EUS MASTER is a promising artificial intelligence system diagnosing malignant and benign pancreatic masses and may guide FNA in real time.

NCT04607720.