Is endoscopic ultrasound a promising technique in the diagnosis and treatment of liver diseases?

Percutaneous ultrasound has been a longstanding method in the diagnostics and interventional procedures of liver diseases. In some countries, its use is restricted to radiologists, limiting access for other clinicians, such as gastroenterologists. Endoscopic ultrasound, as a novel technique, plays a crucial role in diagnosis and treatment of digestive diseases. However, its use is sometimes recommended for conditions where no clear advantage over percutaneous ultrasound exists, leaving the impression that clinicians sometimes resort to an endoscopic approach due to the unavailability of percutaneous options.

Endoscopic ultrasonography-based intratumoral and peritumoral machine learning radiomics analyses for distinguishing insulinomas from non-functional pancreatic neuroendocrine tumors.

Objectives: To develop and validate radiomics models utilizing endoscopic ultrasonography (EUS) images to distinguish insulinomas from non-functional pancreatic neuroendocrine tumors (NF-PNETs). Methods: A total of 106 patients, comprising 61 with insulinomas and 45 with NF-PNETs, were included in this study. The patients were randomly assigned to either the training or test cohort. Radiomics features were extracted from both the intratumoral and peritumoral regions, respectively. Six machine learning algorithms were utilized to train intratumoral prediction models, using only the nonzero coefficient features. The researchers identified the most effective intratumoral radiomics model and subsequently employed it to develop peritumoral and combined radiomics models. Finally, a predictive nomogram for insulinomas was constructed and assessed. Results: A total of 107 radiomics features were extracted based on EUS, and only features with nonzero coefficients were retained. Among the six intratumoral radiomics models, the light gradient boosting machine (LightGBM) model demonstrated superior performance. Furthermore, a peritumoral radiomics model was established and evaluated. The combined model, integrating both the intratumoral and peritumoral radiomics features, exhibited a comparable performance in the training cohort (AUC=0.876) and achieved the highest accuracy in predicting outcomes in the test cohorts (AUC=0.835). The Delong test, calibration curves, and decision curve analysis (DCA) were employed to validate these findings. Insulinomas exhibited a significantly smaller diameter compared to NF-PNETs. Finally, the nomogram, incorporating diameter and radiomics signature, was constructed and assessed, which owned superior performance in both the training (AUC=0.929) and test (AUC=0.913) cohorts. Conclusion: A novel and impactful radiomics model and nomogram were developed and validated for the accurate differentiation of NF-PNETs and insulinomas utilizing EUS images.

[Endoscopic ultrasound-guided liver biopsy: current status and prospects].

Liver biopsy is an important means of clinical diagnosis and treatment of liver diseases, but it is not easily accepted by patients because of its invasiveness. The most commonly employed liver biopsy approaches are percutaneous or transjugular. Endoscopic ultrasound-guided liver biopsy (EUS-LB), a newly emerging transjugular technique, has been widely studied and applied in recent years, but its application in China is less common. The EUS-LB has the advantages of high safety and comfort, simultaneous sampling of both liver lobes, and adequate sampling volume; however, it also has the disadvantages of high requirements for hardware, operators, and cost. This article reviews the clinical application of EUS-LB in accordance with pertinent research findings from recent years and discusses its advantages, disadvantages, and implementation feasibility.

3D airway geometry analysis of factors in airway navigation failure for lung nodules.

BACKGROUND: This study aimed to quantitatively reveal contributing factors to airway navigation failure during radial probe endobronchial ultrasound (R-EBUS) by using geometric analysis in a three-dimensional (3D) space and to investigate the clinical feasibility of prediction models for airway navigation failure. METHODS: We retrospectively reviewed patients who underwent R-EBUS between January 2017 and December 2018. Geometric quantification was analyzed using in-house software built with open-source python libraries including the Vascular Modeling Toolkit ( http://www.vmtk.org ), simple insight toolkit ( https://sitk.org ), and sci-kit image ( https://scikit-image.org ). We used a machine learning-based approach to explore the utility of these significant factors. RESULTS: Of the 491 patients who were eligible for analysis (mean age, 65 years +/- 11 [standard deviation]; 274 men), the target lesion was reached in 434 and was not reached in 57. Twenty-seven patients in the failure group were matched with 27 patients in the success group based on propensity scores. Bifurcation angle at the target branch, the least diameter of the last section, and the curvature of the last section are the most significant and stable factors for airway navigation failure. The support vector machine can predict airway navigation failure with an average area under the curve of 0.803. CONCLUSIONS: Geometric analysis in 3D space revealed that a large bifurcation angle and a narrow and tortuous structure of the closest bronchus from the lesion are associated with airway navigation failure during R-EBUS. The models developed using quantitative computer tomography scan imaging show the potential to predict airway navigation failure.

EUS-FNA Biopsy for Pancreatic Mass.

OBJECTIVE: To assess both solid and cystic pancreatic lesions using endoscopic ultrasound (EUS), and the effect of endoscopic ultrasound-guided fine-needle aspiration (EUS-FNA) in patient management. STUDY DESIGN: Descriptive study. Place and Duration of the Study: Department of Gastroenterology, Division of Internal Diseases, Sivas Cumhuriyet University Hospital, Sivas, Turkiye, from January 2018 to 2022. METHODOLOGY: Patients with pancreatic mass, who underwent EUS-FNA were inducted in the study. EUS-FNA was performed using a 22-gauge needle via both transgastric and transduodenal routes. The size of the pancreatic lesion, its location, and whether there was SMA or CA invasion were evaluated on CT and EUS scans. Biopsy results of 64 patients who received EUS-FNA due to pancreatic lesions were considered. The results were divided into malignancy or benign pathology. RESULTS: A total of 64 cases were compared. Crosstable Chi-square analysis showed a statistically significant difference between CT and EUS (p <0.001). EUS-FNA results revealed that out of the 64 patients with pancreatic mass detected in EUS, 46 had adenocarcinoma, 7 were negative for malignancy, 4 had intraductal papillary mucinous neoplasia (IPMN), 3 had neuroendocrine tumour (NET), 2 had lymphoma, and 2 had solid pseudopapillary neoplasia (SPN). In the 2-year follow-up of the seven patients who were negative for malignancy in EUS-FNA, there were no clinical, laboratory or imaging findings indicating pancreatic malignancy or distant metastasis. CONCLUSION: Tissue sampling through EUS-FNA has minimal side effects and remains useful in managing preoperative patients with resectable or suspicious pancreatic masses. KEY WORDS: Pancreatic cancer, Abdominal CT, Endoscopic ultrasound (EUS), Ultrasound-guided fine-needle aspiration (EUS-FNA).

Diagnosing Solid Lesions in the Pancreas With Multimodal Artificial Intelligence: A Randomized Crossover Trial.

Importance: Diagnosing solid lesions in the pancreas via endoscopic ultrasonographic (EUS) images is challenging. Artificial intelligence (AI) has the potential to help with such diagnosis, but existing AI models focus solely on a single modality. Objective: To advance the clinical diagnosis of solid lesions in the pancreas through developing a multimodal AI model integrating both clinical information and EUS images. Design, Setting, and Participants: In this randomized crossover trial conducted from January 1 to June 30, 2023, from 4 centers across China, 12 endoscopists of varying levels of expertise were randomly assigned to diagnose solid lesions in the pancreas with or without AI assistance. Endoscopic ultrasonographic images and clinical information of 439 patients from 1 institution who had solid lesions in the pancreas between January 1, 2014, and December 31, 2022, were collected to train and validate the joint-AI model, while 189 patients from 3 external institutions were used to evaluate the robustness and generalizability of the model. Intervention: Conventional or AI-assisted diagnosis of solid lesions in the pancreas. Main Outcomes and Measures: In the retrospective dataset, the performance of the joint-AI model was evaluated internally and externally. In the prospective dataset, diagnostic performance of the endoscopists with or without the AI assistance was compared. Results: The retrospective dataset included 628 patients (400 men [63.7%]; mean [SD] age, 57.7 [27.4] years) who underwent EUS procedures. A total of 130 patients (81 men [62.3%]; mean [SD] age, 58.4 [11.7] years) were prospectively recruited for the crossover trial. The area under the curve of the joint-AI model ranged from 0.996 (95% CI, 0.993-0.998) in the internal test dataset to 0.955 (95% CI, 0.940-0.968), 0.924 (95% CI, 0.888-0.955), and 0.976 (95% CI, 0.942-0.995) in the 3 external test datasets, respectively. The diagnostic accuracy of novice endoscopists was significantly enhanced with AI assistance (0.69 [95% CI, 0.61-0.76] vs 0.90 [95% CI, 0.83-0.94]; P < .001), and the supplementary interpretability information alleviated the skepticism of the experienced endoscopists. Conclusions and Relevance: In this randomized crossover trial of diagnosing solid lesions in the pancreas with or without AI assistance, the joint-AI model demonstrated positive human-AI interaction, which suggested its potential to facilitate a clinical diagnosis. Nevertheless, future randomized clinical trials are warranted. Trial Registration: ClinicalTrials.gov Identifier: NCT05476978.

Incremental Application of Positive End-Expiratory Pressure for the Evaluation of Atelectasis During RP-EBUS and Bronchoscopy (I-APPEAR).

BACKGROUND: CT-to-body divergence-described as the difference between preprocedural CT scans and intraprocedural lung architecture-is a significant barrier to improving diagnostic yield during navigational bronchoscopy. A major proposed contributor to CT-to-body divergence is the development of atelectasis, which can confound visualization of peripheral lung lesions via radial probe endobronchial ultrasound (RP-EBUS). High positive end-expiratory pressure (PEEP) ventilatory strategies have been used to decrease atelectasis, allowing the lesion to re-APPEAR on intraprocedure imaging. However, standardized PEEP levels may not be appropriate for all patients due to hemodynamic and ventilatory impacts. METHODS: We performed a multicenter, prospective observational study in which patients were imaged with RP-EBUS under general anesthesia to determine if subsegmental atelectasis would resolve as incremental increases in PEEP were applied. Resolution of atelectasis was based on the transition from a non-aerated pattern to an aerated appearance on RP-EBUS. RP-EBUS images were reviewed by 3 experienced operators to determine correlation. RESULTS: Forty-three patients underwent RP-EBUS examination following navigational bronchoscopy. Thirty-seven patients underwent incremental PEEP application and subsequent RP-EBUS imaging. Atelectasis was determined to have resolved in 33 patients (88.2%) following increased PEEP. The intraclass correlation coefficient between reviewers was 0.76. A recruitment maneuver was performed in 7 (16.3%) patients after atelectasis persisted at maximal PEEP. Atelectasis was not identified in the examined subsegments in 6 (10.8%) patients despite zero PEEP. CONCLUSION: RP-EBUS is an effective tool to monitor what pressure atelectasis within a lung segment has resolved with increasing levels of PEEP.

Optimization of Endoscopic Ultrasound Characteristics in the Diagnosis of Malignant Intraductal Papillary Mucinous Neoplasm.

OBJECTIVES: Endoscopic ultrasound (EUS) is an excellent diagnostic tool that provides high-resolution images of pancreatic cystic lesions. However, its role in the diagnosis of malignant intraductal papillary mucinous neoplasm (IPMN) remains limited and unclear. We aimed to determine the usefulness of this modality for such diagnosis. METHODS: Overall, 246 patients who underwent EUS for IPMN after computed tomography (CT)/magnetic resonance imaging (MRI) from April 2018 to June 2021 were followed up until March 2022. We assessed the added value of performing EUS after CT or MRI for diagnosing malignant IPMN, using receiver operating characteristic curve analysis. Walls as thick as 2 mm were considered thickened in this study if they were highly uneven. RESULTS: EUS clearly enhanced accuracy in identifying enhancing nodules and thickened walls. The areas under the receiver operating characteristic curve and corresponding 95% confidence intervals were 0.655 (0.549-0.760) and 0.566 (0.478-0.654) upon CT/MRI but 0.853 (0.763-0.942) and 0.725 (0.634-0.817) when observed using EUS. The combination of nodule size, thickened wall, and main duct size yielded the highest area under the receiver operating characteristic curve (0.944 [0.915-0.973]). CONCLUSIONS: EUS more accurately detects malignant IPMN, as uneven wall thickening and certain nodules cannot be identified with CT/MRI.

Diagnostics and Imaging for Pancreatic Neuroendocrine Tumors.

Pancreatic neuroendocrine tumors originate from hormone-producing islet cells and have a propensity to metastasize to the liver once they reach 2 cm in size. Their diagnosis relies upon a combination of computed tomography, MRI, DOTATATE PET, and endoscopic ultrasound with or without tissue biopsy. Biochemical work-up is driven by patient symptoms of hormone excess.

Endoscopic band ligation or endoscopic tissue adhesive injection in the treatment of gastric varices: Which is better?

The combination of endoscopic ultrasound with endoscopic treatment of type 1 gastric variceal hemorrhage may improve the robustness and generalizability of the findings in future studies. Moreover, the esophageal varices should also be included in the evaluation of treatment efficacy in subsequent studies to reach a more convincing conclusion.

Using quality indicators to assess performance of endobronchial ultrasound in the staging and diagnosis of lung cancer: a pre/post study at a New Zealand centre.

AIM: There are no data on the performance of endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) in the staging and diagnosis of lung cancer in New Zealand. We aimed to assess the performance of EBUS-TBNA for lung cancer staging and diagnosis at our institution before and after the commencement of regular performance monitoring with comparison to published EBUS quality indicators. METHODS: The performance of EBUS-TBNA in the staging and diagnosis of lung cancer was assessed in two phases. Phase 1 consisted of a retrospective review of all lung cancer EBUS performed over a 2-year period. Published quality indicators were determined from the literature with relevant indicators being extracted and used to determine EBUS performance. Local reporting and education were undertaken and prospective data collection was commenced. Phase 2 consisted of prospective assessment of all lung cancer EBUS over the subsequent year. Performance of EBUS was then compared between phases 1 and 2 in order to determine the effect of performance monitoring and identify areas for service improvement. RESULTS: A total of 115 staging EBUS and 117 diagnostic EBUS were performed during the study period. Staging EBUS demonstrated good performance across phases 1 and 2 with high sensitivity and negative predictive values (NPV) for the detection of N2/3 disease, meeting published quality standards. During phase 2 there was evidence of a transition towards more guideline-concordant practice evidenced by more detailed nodal sampling during staging EBUS; however, this did not affect overall sensitivity or NPV. Diagnostic EBUS resulted in high rates of pathological confirmation meeting published quality standards across both phases. Pathway times were similar between phases 1 and 2, with reporting of molecular profiling being the predominant factor in delayed pathway times. CONCLUSION: Monitoring and reporting of local performance allows critical assessment of practice and can identify areas for quality improvement. This review demonstrated good overall performance but prompted a move towards more guideline-concordant practice with increased mediastinal nodal sampling during staging procedures. Consideration should be given to the adoption of routine EBUS performance monitoring within local and/or regional networks, which could be incorporated alongside the newly proposed Lung Cancer Clinical Quality Registry.