Endoscopic Ultrasound Imaging Research Articles

The impact of the novel EUS scope and ultrasonographic system for diagnosis and therapy in patients with pancreatobiliary diseases (videos).

We evaluated the diagnostic and therapeutic capabilities of endoscopic ultrasonography (EUS) in pancreaticobiliary diseases. We aimed to validate the efficiency of detective flow imaging (DFI), shear wave elastography (SWE), and other advanced imaging techniques. We used new EUS scopes (EG-740 UT and G-580UR) and the latest ultrasound equipment (ARIETTA 850) (Fujifilm Healthcare, Kanagawa, Japan). Diagnostic procedures were performed in 16 cases, including pancreatic cancer and intraductal papillary mucinous neoplasms, and therapeutic procedures in eight cases, involving complex biliary and pancreatic interventions. The utility of SWE in assessing tissue stiffness was quantified by measuring the shear wave velocity (SWV) in pancreatic cancer and autoimmune pancreatitis. We found no significant difference in SWVs among different pancreatic conditions; however, significant variations were observed in the net percentage of effective SWV. Interventional EUS had a 100% technical and clinical success rate, demonstrating the efficacy of new imaging techniques and equipment in enhancing procedural safety and diagnostic accuracy. The integration of advanced EUS imaging technologies, particularly DFI, contrast-enhanced EUS, and SWE, significantly enhances the diagnosis and treatment of pancreaticobiliary diseases.

An artificial intelligence model utilizing endoscopic ultrasonography for differentiating small and micro gastric stromal tumors from gastric leiomyomas

BackgroundGastric stromal tumors (GSTs) and gastric leiomyomas (GLs) represent the primary subtypes of gastric submucosal tumors (SMTs) characterized by distinct biological characteristics and treatment modalities. The accurate differentiation between GSTs and GLs poses a significant clinical challenge. Recent advancements in artificial intelligence (AI) leveraging endoscopic ultrasonography (EUS) have demonstrated promising results in the categorization of larger-diameter SMTs (> 2.0 cm). However, the diagnostic capacity of AI models for micro-diameter SMTs (< 1.0 cm) remains uncertain due to limited imaging features. This study seeks to develop a specialized diagnostic model utilizing EUS images to differentiate small and micro GSTs from GLs effectively.MethodsIn this study, a dataset comprising 358 EUS images of GSTs or GLs was utilized for training the EUS-AI model. Subsequently, 216 EUS images were allocated for validation purposes, with 159 images in validation set 1 (micro SMTs: tumor diameter < 1.0 cm) and 216 images in validation set 2 (small SMTs: tumor diameter < 2.0 cm). The diagnostic performance of the EUS-AI model for individual tumors was assessed by consolidating the diagnostic outcomes of the corresponding images. Comparative analyses were conducted between the diagnostic outcomes of endoscopists, clinical signatures, and those of the EUS-AI models.ResultsThe EUS-AI models were developed using DenseNet201, ResNet50, and VGG19 architectures. Among the three models, the ResNet50 model demonstrated superior performance on EUS images, achieving area under the curve (AUC) values of 0.938, 0.832, and 0.841 in the training set, validation set 1, and validation set 2, respectively. By combining predictions from multiple images for each tumor, the diagnostic efficacy of ResNet50 was further enhanced, resulting in AUCs of 0.994, 0.911, and 0.915 in the aforementioned sets. In comparison, both clinical signatures and endoscopists exhibited notably lower AUC values than those obtained with the EUS-AI model.ConclusionsThe EUS-AI model utilizing ResNet50 architecture effectively discriminates between micro GSTs and GLs from both image-centric and tumor-centric perspectives. Demonstrating superior diagnostic efficiency compared to clinical models and assessments by endoscopists, the EUS-AI model serves as a valuable tool for clinicians in precisely distinguishing small and micro GSTs from GLs before surgery.Graphical abstract

Interobserver variability in lymph node evaluation with endoscopic ultrasonography in cholangiocarcinoma

Background: Accurate preoperative lymph node (LN) assessment is crucial for patients with intrahepatic cholangiocarcinoma (iCCA) and perihilar cholangiocarcinoma (pCCA), as the presence of LN metastases significantly reduces survival rates and can contraindicate surgical resection. Endoscopic ultrasound (EUS) provides a reliable method for LN assessment with the advantage of enabling tissue acquisition for pathological confirmation. This study aimed to assess the interobserver agreement among endosonographers in evaluating LN characteristics in patients with iCCA and pCCA. Materials and methods: A cross-sectional survey study was conducted among 24 endosonographers. Participants reviewed 42 EUS images from iCCA and pCCA patients, classifying LNs based on six characteristics (demarcation, shape, echogenicity, homogeneity, suspiciousness, and need to retrieve tissue). Interobserver agreement was determined using Light’s kappa statistics. Accuracy, sensitivity, and specificity in identifying malignant LNs were calculated. Results: The overall kappa values indicated moderate to fair agreement on LN characteristics, with Kappa values of 0.24 for demarcation, 0.45 for shape, 0.38 for echogenicity, 0.52 for homogeneity, and 0.36 for suspiciousness. The overall accuracy of endosonographers in correctly identifying malignant LNs was 62% with individual accuracy ranging from 44 to 75%. Sensitivity was 60% (range: 29-90%) and specificity was 64% (range: 28-89%). Conclusions: The endosonographic assessment of LN morphology and characterization demonstrates considerable variability among endosonographers. Thus, there is a clear need for standardization in preoperative LN evaluation, including establishing consensus on when to perform tissue acquisition, based on objective criteria such as short-axis diameter. Further research is required to refine and optimize these guidelines.

A Lightweight Machine Learning Model for High Precision Gastrointestinal Stromal Tumors Identification

Gastrointestinal stromal tumors (GISTs), which usually develop with a significant malignant potential, are a serious challenge in stromal health. With Endoscopic ultrasound (EUS), GISTs can appear similar to other tumors. This study introduces a lightweight convolutional neural network model optimized for the classification of GISTs and leiomyomas using EUS images only. Models are constructed based on a dataset that comprises 13277 augmented grayscale images derived from 703 patients, ensuring a balanced representation between GIST and leiomyoma cases. The optimized model architecture includes seven convolutional units followed by fully connected layers. After being trained and evaluated with a 5-fold cross-validation, the optimized model achieves an average validation accuracy of 96.2%. The model achieved a sensitivity, specificity, positive predictive value, and negative predictive value of 97.7%, 94.7%, 94.6%, and 97.7%, respectively, and significantly outperformed endoscopists’ assessments. The study highlights the model’s robustness and consistency. Our results suggest that instead of using developed deep models with fine-tuning, lightweight models with their simpler designs may grasp the essence and drop speckle noise. A lightweight model as a hypothesis with fewer model parameters is preferable to a deeper model with 10 times the model parameters according to Occam’s razor statement.

Diagnosis of invasive pancreatic cancer in endoscopic ultrasound images leveraging translation models

Diagnosis of invasive pancreatic cancer in endoscopic ultrasound images leveraging translation models

Preoperative prediction of pancreatic neuroendocrine tumors grade based on computed tomography, magnetic resonance imaging and endoscopic ultrasonography.

To establish a preoperative prediction model for pathological grade of PanNETs based on computed tomography (CT), magnetic resonance imaging (MRI) and endoscopic ultrasonography (EUS). Clinical data of 58 patients with pathologically confirmed PanNETs were included in this retrospectively study and they were divided into grade 1 and grade 2/3. CT, MRI and EUS images were collected within one week before surgery. A clinical predictive model based on the independent clinical risk factors and significant radiological features was established. The area under receiver operating characteristic curve (AUC) was performed to assess the model. Gender, pancreatic duct dilatation (PDD) and portal enhancement ratio (PER) were the independent predictors for PanNETs grading (P < 0.05). PanNETs grade 1 and grade 2/3 had statistical difference in elastography score (P = 0.001). The combination of gender, PDD and PER had better predictive efficiency than each of these three predictors alone, with a high AUC of 0.925. The elastography score also achieved an AUC of 0.838. We proposed a comprehensive model based on preoperative CT, MRI and EUS to predict grade 1 and grade 2/3 of PanNETs and better informs clinicians on individualized diagnosis and treatment of patients with PanNETs.

EUS-based intratumoral and peritumoral machine learning radiomics analysis for distinguishing pancreatic neuroendocrine tumors from pancreatic cancer.

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.

Current status and future perspective of artificial intelligence analysis for the diagnosis of pancreatobiliary diseases using endoscopic ultrasonography images

Current status and future perspective of artificial intelligence analysis for the diagnosis of pancreatobiliary diseases using endoscopic ultrasonography images

Clinical value of the nomogram model based on endoscopic ultrasonography radiomics and clinical indicators in identifying benign and malignant lesions of the pancreas.

Based on endoscopic ultrasonography (EUS) radiomics and clinical data, we constructed a radiomics model and a nomogram model for identifying benign and malignant pancreatic lesions, and explored the diagnostic performance of these two prediction models. Images and clinical data of 151 patients with pancreatic lesions detected by EUS from January 2018 to September 2023 were retrospectively collected. The patients were randomly divided into a training set and a validation set at a ratio of 7:3. Through feature extraction and feature screening of EUS images, we calculated the radiomics score (rad-score) to realize the construction of the radiomics model. Collecting the clinical data, laboratory test results, and rad-scores from patients, univariate and multivariate logistic regression analyses were used to screen statistically significant influencing factors that could help identify benign and malignant lesions of the pancreas, and a nomogram model was constructed. The diagnostic performance and clinical utility of the two prediction models were evaluated using the receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). Through feature extraction and screening, eight non-zero coefficient features were finally selected to calculate the rad-score. Multivariate logistic regression analysis showed that rad-score, age, and CA199 were the influencing factors in predicting benign and malignant pancreatic lesions. A nomogram model was constructed based on the three factors. In the validation set, the nomogram model exhibited superior performance with an AUC = 0.865 (95% CI 0.761-0.968) compared to the radiomics prediction model. The calibration curve and DCA depicted that the nomogram model demonstrated superior accuracy and yielded a higher net benefit for clinical decision-making compared to the radiomics prediction model. Based on EUS radiomics and clinical indicators, we constructed a promising nomogram model to accurately identify benign and malignant pancreatic lesions.

Diagnostic value of the standardised uptake value (SUV) ratio of mediastinal lymph node to primary tumour in lung cancer.

This study aimed to determine whether the mediastinal lymph node/tumour ratio (NTR) of the standardised uptake value (SUV) predicts N2 involvement more accurately than node SUV in patients with non-small cell lung cancer (NSCLC). We retrospectively analysed consecutive patients with lung cancer at clinical stages I-IVA. All patients underwent positron emission tomography-computed tomography (PET-CT), followed by mediastinal staging using endobronchial ultrasound and endoscopic ultrasound imaging, and curative-intent lung resection with systematic lymph node dissection. Pathological examination of the surgical specimen was performed for confirmation. The data from 774 patients were analysed. There was a significant correlation between the risk of false-negative PET results for N2 disease and both the SUV of the mediastinal nodes (p = 0.012) and NTR (p = 0.030). The NTR outperformed node SUV in predictive ability; the Akaike information criterion was 307.268 for NTR compared to 308.498 for node SUV. Three factors were significantly associated with the positive predictive value of PET: patient age (p = 0.021), female sex (p = 0.012), and adenocarcinoma histology (p = 0.036). There were no significant correlations between PET sensitivity, specificity, and negative predictive value (NPV), and age, sex, body mass index (BMI), tumour grade, lobar location, or histological type. The NTR may be a useful tool for excluding N2 disease in NSCLC. PET sensitivity and NPV for detecting N2 disease are not influenced by age, sex, BMI, tumour grade, lobar location, or histological type.

Endoscopic ultrasound-based radiomics for predicting pathologic upgrade in esophageal low-grade intraepithelial neoplasia.

There is no consensus on managing patients with endoscopic suspicion of early esophageal squamous cell carcinoma (ESCC) but biopsy-confirmed low-grade intraepithelial neoplasia (LGIN). The aim of this study is to evaluate the utility of an endoscopic ultrasound (EUS)-based radiomics nomogram for predicting esophageal LGIN pathological progression before diagnostic endoscopic submucosal dissection (ESD). In the development phase, EUS images of535 patients who had biopsy-confirmed LGIN and were undergoing ESDwere retrospectively included. Concurrently, 251 patients were prospectively included for independent model validation. A radiomics signature (RS) was constructed using Pearson test and the least absolute shrinkage and selection operator (LASSO) algorithm. A radiomics nomogram was then developed with multivariatelogistic regression to predict pathologic upgrade before ESD. Model performance was assessed with receiver operating characteristic (ROC) analysis, calibration curves, and decision curve analysis (DCA). Following stepwise multivariate logistic regression analysis, statistically significant clinical features were incorporated into the clinical predictive model. From EUS images, 105 radiomic features were extracted, with 11 key features selected for RS development. The RS showed strong predictive performance in identifying pathologic upgrade (AUC = 0.786). Moreover, when integrated with the clinical model (AUC = 0.648), the RS performance remarkably improved (AUC = 0.818). These results were subsequently validated in the prospective test cohort (RS: AUC = 0.792; Clinical model: AUC = 0.669; Combined model: AUC = 0.821). The combined model presented as a nomogram also excelled in calibration tests and DCA, underlining its potential for clinical application. The EUS-based radiomics nomogram showed potential for predicting pathologic upgrade in esophageal LGIN, which helps to distinguish high-risk from low-risk cases and assists clinicians in assessing the necessity of diagnostic ESD.

A systematic review of the impact of artificial intelligence in pancreatic cancer detection.

685 Background: Pancreatic cancer is the fourth leading cause of cancer deaths in the United States, and early detection remains a significant challenge. Screening the general population is not feasible, but the rise of artificial intelligence (AI) has introduced new possibilities for improving early diagnosis and patient outcomes. Methods: A systematic literature search was conducted using PubMed, Google Scholar, and MEDLINE using MeSH terms Artificial intelligence or AI, and diagnosis and pancreatic carcinoma or pancreatic adenocarcinoma. Prisma guidelines were adhered to, and a total of 19 studies resulted, 6 of them were retrospective studies, 4 of them were literature reviews, and 4 of them were randomized trials. The rest were duplicates. The inclusion criteria for this study is AI being used in the diagnosis, only in pancreatic cancer, within the last 5 years, only in English, and only retrospective studies were included. Results: One study used Digital Imaging Processing (DIP) for analyzing Endoscopic ultrasound (EUS) images from 153 pancreatic cancer patients, yielding a sensitivity of 97.98% and a specificity of 94.32%. Two studies explored Computer Aided Diagnosis (CAD) models applied to PET/CT and EUS images, achieving a sensitivity of 95.23% and specificity of 97.51% in PET/CT scans and 83.3% and 93.3% in EUS images, respectively. Another study used a Faster R-CNN model to analyze CT images from 338 pancreatic cancer patients showed high diagnostic accuracy in much less time. Additionally, two studies utilized Natural Language Processing (NLP) for identifying family histories of pancreatic cancer and detecting pancreatic cysts, with the latter achieving sensitivity and specificity rates of 99.9% and 98.8%. Conclusions: The current strategies for early diagnosis of pancreatic cancer focus on serum biomarkers and EUS-guided Fine Needle Aspiration (EUS-FNA) and sensitivity varies but depends on the physician's expertise. AI is showing promise in improving pancreatic cancer diagnosis by enhancing early detection and accuracy. Techniques like deep learning, NLP-based models, Faster R-CNN, and CAD systems analyze medical data and images more effectively than manual methods. AI holds the potential to shape the future of pancreatic cancer diagnosis and improve patient outcomes.

IPNet: An Interpretable Network With Progressive Loss for Whole-Stage Colorectal Disease Diagnosis.

Colorectal cancer plays a dominant role in cancer-related deaths, primarily due to the absence of obvious early-stage symptoms. Whole-stage colorectal disease diagnosis is crucial for assessing lesion evolution and determining treatment plans. However, locality difference and disease progression lead to intra-class disparities and inter-class similarities for colorectal lesion representation. In addition, interpretable algorithms explaining the lesion progression are still lacking, making the prediction process a "black box". In this paper, we propose IPNet, a dual-branch interpretable network with progressive loss for whole-stage colorectal disease diagnosis. The dual-branch architecture captures unbiased features representing diverse localities to suppress intra-class variation. The progressive loss function considers inter-class relationship, using prior knowledge of disease evolution to guide classification. Furthermore, a novel Grain-CAM is designed to interpret IPNet by visualizing pixel-wise attention maps from shallow to deep layers, providing regions semantically related to IPNet's progressive classification. We conducted whole-stage diagnosis on two image modalities, i.e., colorectal lesion classification on 129,893 endoscopic optical images and rectal tumor T-staging on 11,072 endoscopic ultrasound images. IPNet is shown to surpass other state-of-the-art algorithms, accordingly achieving an accuracy of 93.15% and 89.62%. Especially, it establishes effective decision boundaries for challenges like polyp vs. adenoma and T2 vs. T3. The results demonstrate an explainable attempt for colorectal lesion classification at a whole-stage level, and rectal tumor T-staging by endoscopic ultrasound is also unprecedentedly explored. IPNet is expected to be further applied, assisting physicians in whole-stage disease diagnosis and enhancing diagnostic interpretability.

Informatics strategies for early detection and risk mitigation in pancreatic cancer patients.

Informatics strategies for early detection and risk mitigation in pancreatic cancer patients.

An endoscopic ultrasound-based interpretable deep learning model and nomogram for distinguishing pancreatic neuroendocrine tumors from pancreatic cancer

To retrospectively develop and validate an interpretable deep learning model and nomogram utilizing endoscopic ultrasound (EUS) images to predict pancreatic neuroendocrine tumors (PNETs). Following confirmation via pathological examination, a retrospective analysis was performed on a cohort of 266 patients, comprising 115 individuals diagnosed with PNETs and 151 with pancreatic cancer. These patients were randomly assigned to the training or test group in a 7:3 ratio. The least absolute shrinkage and selection operator algorithm was employed to reduce the dimensionality of deep learning (DL) features extracted from pre-standardized EUS images. The retained nonzero coefficient features were subsequently applied to develop predictive eight DL models based on distinct machine learning algorithms. The optimal DL model was identified and used to establish a clinical signature, which subsequently informed the construction and evaluation of a nomogram. Gradient-weighted Class Activation Mapping (Grad-CAM) and Shapley Additive Explanations (SHAP) were implemented to interpret and visualize the model outputs. A total of 2048 DL features were initially extracted, from which only 27 features with coefficients greater than zero were retained. The support vector machine (SVM) DL model demonstrated exceptional performance, achieving area under the curve (AUC) values of 0.948 and 0.795 in the training and test groups, respectively. Additionally, a nomogram was developed, incorporating both DL and clinical signatures, and was visually represented for practical application. Finally, the calibration curves, decision curve analysis (DCA) plots, and clinical impact curves (CIC) exhibited by the DL model and nomogram indicated high accuracy. The application of Grad-CAM and SHAP enhanced the interpretability of these models. These methodologies contributed substantial net benefits to clinical decision-making processes. A novel interpretable DL model and nomogram were developed and validated using EUS images, cooperating with machine learning algorithms. This approach demonstrates significant potential for enhancing the clinical applicability of EUS in predicting PNETs from pancreatic cancer, thereby offering valuable insights for future research and implementation.

Endoscopic ultrasonography-based intratumoral and peritumoral machine learning ultrasomics model for predicting the pathological grading of pancreatic neuroendocrine tumors

ObjectivesThe objective is to develop and validate intratumoral and peritumoral ultrasomics models utilizing endoscopic ultrasonography (EUS) to predict pathological grading in pancreatic neuroendocrine tumors (PNETs).MethodsEighty-one patients, including 51 with grade 1 PNETs and 30 with grade 2/3 PNETs, were included in this retrospective study after confirmation through pathological examination. The patients were randomly allocated to the training or test group in a 6:4 ratio. Univariate and multivariate logistic regression were used for screening clinical and ultrasonic characteristics. Ultrasomics is ultrasound-based radiomics. Ultrasomics features were extracted from both the intratumoral and peritumoral regions of conventional EUS images. Subsequently, the dimensionality of these radiomics features was reduced using the least absolute shrinkage and selection operator (LASSO) algorithm. A machine learning algorithm, namely multilayer perception (MLP), was employed to construct prediction models using only the nonzero coefficient features and retained clinical features, respectively.ResultsOne hundred seven ultrasomics features based on EUS were extracted, and only features with nonzero coefficients were ultimately retained. Among all the models, the combined ultrasomics model achieved the greatest performance, with an AUC of 0.858 (95% CI, 0.7512 - 0.9642) in the training group and 0.842 (95% CI, 0.7061 - 0.9785) in the test group. A calibration curve and a decision curve analysis (DCA) also demonstrated its accuracy and utility.ConclusionsThe integrated model using EUS ultrasomics features from intratumoral and peritumoral tumors accurately predicts PNETs' pathological grades pre-surgery, aiding personalized treatment planning.Trial registrationChiCTR2400091906.

Diagnostic Accuracy of Detective Flow Imaging Endoscopic Ultrasonography for Evaluating Blood Flow Within Mural Nodules of Intraductal Papillary Mucinous Neoplasms.

Background/Objectives: Detective flow imaging (DFI) endoscopic ultrasonography (EUS) can identify the microvascular flow imaging of a mural nodule (MN) in an intraductal papillary mucinous neoplasm (IPMN) without the use of contrast agents. This retrospective study evaluated the diagnostic accuracy of DFI-EUS and its ability to evaluate the blood flow of MNs in IPMNs. Methods: Between April 2021 and September 2023, 68 patients with MNs in IPMNs observed on EUS images were retrospectively analyzed. Both DFI-EUS and contrast-enhanced EUS (CE-EUS) were performed during the same session. Three expert endosonographers blinded to the patients' clinical data assessed the MN images obtained with CE-EUS and DFI-EUS. First, DFI-EUS images were evaluated using a predefined scoring system; thereafter, CE-EUS images were evaluated. The diagnostic capability of DFI-EUS to detect MN blood flow was assessed with CE-EUS as the gold standard. Secondary outcomes included inter-reader agreement, the correlation between MN size and detection rates, and the association between DFI blood flow signal patterns and malignancy of MNs in surgically resected cases. Results: CE-EUS showed a contrast effect in the MN in 24 cases. Among these, DFI-EUS detected blood flow signals in 20 cases; false-positive results were not observed. DFI-EUS demonstrated a sensitivity of 83%, specificity of 100%, and accuracy of 93% for detecting MN blood flow. Inter-reader agreement was substantial (kappa values, 0.6-0.8). The subgroup analysis revealed that all MNs ≥ 10 mm had detectable blood flow on DFI-EUS, whereas MNs < 10 mm had reduced detection rates (75%; 12/16 cases). No significant correlation between the DFI blood flow signal patterns and MN malignancy of resected cases was observed. Conclusions: DFI-EUS demonstrated high diagnostic accuracy for detecting MN blood flow. Because of its simplicity and cost-effectiveness, DFI-EUS could be an alternative to CE-EUS for patients with MNs inside IPMNs.

A Two-Dimensional Circular Array Transducer for Endoscopic Ultrasound Imaging of Tube.

The concept of endoscopic ultrasound (EUS) has been introduced to non-destructive testing for the inspection of tubular structure. However, the fixed normal focusing beam of the present EUS transducers obstructs imaging flexibility and limits the robustness of the inspection, particularly for planar reflectors. To address this challenge, a two-dimensional circular array (2-D CA) designed for three-dimensional focusing is developed in this paper. A prototype 2-D CA transducer is fabricated and validated, which is demonstrated has a central frequency of 10.10 MHz and an average pulse duration of no more than 344 ns. An independent-dual-focusing beamforming scheme is further proposed, providing delay laws in two orthogonal directions. The acoustic field simulation results confirm that the 2-D CA is capable of achieving focusing in any direction, thereby enhancing the flexibility of EUS imaging. The imaging performance of the 2-D CA is evaluated through the immersion EUS inspection of a stainless-steel tube specimen. All the quasi-planar reflectors, including ring grooves with narrow-width, small-diameter flat bottom holes, and longitudinal grooves, are successfully detected in the 2-D CA imaging results. These reflectors could hardly be recognized by the conventional CA with a fixed-normal beam, affirming the superior detection robustness of the 2-D CA. The detection signal-to-noise ratio and error of quantitative characterization of the 2-D CA are 26.12 dB higher and 40.37 % lower than those of conventional CA, respectively. The proposed 2-D CA enables novel and advanced EUS imaging modalities, which have potential applications in both medical imaging and non-destructive testing domains.

Artificial intelligence in pancreaticobiliary endoscopy: Current applications and future directions.

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.

Deep learning for segmentation of colorectal carcinomas on endoscopic ultrasound.

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.