Enhanced Nuclei Segmentation and Classification via Category Descriptors in the SAM Model.

Segmenting and classifying nuclei in H&E histopathology images is often limited by the long-tailed distribution of nuclei types. However, the strong generalization ability of image segmentation foundation models like the Segment Anything Model (SAM) can help improve the detection quality of rare types of nuclei. In this work, we introduce category descriptors to perform nuclei segmentation and classification by prompting the SAM model. We close the domain gap between histopathology and natural scene images by aligning features in low-level space while preserving the high-level representations of SAM. We performed extensive experiments on the Lizard dataset, validating the ability of our model to perform automatic nuclei segmentation and classification, especially for rare nuclei types, where achieved a significant detection improvement in the F1 score of up to 12%. Our model also maintains compatibility with manual point prompts for interactive refinement during inference without requiring any additional training.

Left psoas abscess due to duodenal fistula as a late complication of necrotizing pancreatitis treated by endoscopic approach.

Gastrointestinal fistulas can be a complication of severe acute pancreatitis, and their incidence is low and sporadically reported in the literature. The most frequently reported site is in the colon, followed by duodenal fistulas. Psoas abscess is a rare condition. Iliopsoas abscesses are classified as primary or secondary. Secondary abscesses develop by spreading infection from contiguous anatomical structures, such as the gastrointestinal tract. We present the case of a recurrent left psoas abscess secondary to a duodenal fistula as a late complication of necrotizing pancreatitis resolved by endoscopic treatment.

Attention guided multi-scale cluster refinement with extended field of view for amodal nuclei segmentation.

Nuclei segmentation plays a crucial role in disease understanding and diagnosis. In whole slide images, cell nuclei often appear overlapping and densely packed with ambiguous boundaries due to the underlying 3D structure of histopathology samples. Instance segmentation via deep neural networks with object clustering is able to detect individual segments in crowded nuclei but suffers from a limited field of view, and does not support amodal segmentation. In this work, we introduce a dense feature pyramid network with a feature mixing module to increase the field of view of the segmentation model while keeping pixel-level details. We also improve the model output quality by adding a multi-scale self-attention guided refinement module that sequentially adjusts predictions as resolution increases. Finally, we enable clusters to share pixels by separating the instance clustering objective function from other pixel-related tasks, and introduce supervision to occluded areas to guide the learning process. For evaluation of amodal nuclear segmentation, we also update prior metrics used in common modal segmentation to allow the evaluation of overlapping masks and mitigate over-penalization issues via a novel unique matching algorithm. Our experiments demonstrate consistent performance across multiple datasets with significantly improved segmentation quality.

Content preserving image translation with texture co-occurrence and spatial self-similarity for texture debiasing and domain adaptation.

Models trained on datasets with texture bias usually perform poorly on out-of-distribution samples since biased representations are embedded into the model. Recently, various image translation and debiasing methods have attempted to disentangle texture biased representations for downstream tasks, but accurately discarding biased features without altering other relevant information is still challenging. In this paper, we propose a novel framework that leverages image translation to generate additional training images using the content of a source image and the texture of a target image with a different bias property to explicitly mitigate texture bias when training a model on a target task. Our model ensures texture similarity between the target and generated images via a texture co-occurrence loss while preserving content details from source images with a spatial self-similarity loss. Both the generated and original training images are combined to train improved classification or segmentation models robust to inconsistent texture bias. Evaluation on five classification- and two segmentation-datasets with known texture biases demonstrates the utility of our method, and reports significant improvements over recent state-of-the-art methods in all cases.

Vitamin C for Photo-Stable Non-fullerene-acceptor-Based Organic Solar Cells.

The recent advent of the new class of organic molecules, the so-called non-fullerene acceptors, has resulted in skyrocketing power conversion efficiencies of organic solar cells. However, rapid degradation occurs under illumination, particularly when photocatalytic metal oxide electron transport layers are used in these devices. We introduced vitamin C (ascorbic acid) into the organic solar cells as a photostabilizer and systematically studied its photostabilizing effect on inverted PBDB-T:IT-4F devices. The presence of vitamin C as an antioxidant layer between the ZnO electron transport layer and the photoactive layer strongly suppressed the photocatalytic effect of ZnO that induces NFA photodegradation. Upon 96 h of exposure to AM 1.5G 1 Sun irradiation, the reference devices lost 64% of their initial efficiency, while those containing vitamin C lost only 38%. The UV-visible absorption, impedance spectroscopy, and light-dependent voltage and current measurements reveal that vitamin C reduces the photobleaching of NFA molecules and suppresses the charge recombination. This simple approach using a low-cost, naturally occurring antioxidant, provides an efficient strategy for improving photostability of organic semiconductor-based devices.

Treatment Approaches for Swallowing Disorders in Children.

A swallowing disorder or dysphagia is defined as a disorder in the sequence of swallowing, during the oral or pharyngeal phase, which compromises the safety and/or efficiency of transit of the food bolus to the esophagus. The evaluation of neurodevelopment, nutrition, and preventive medicine actions are as important as the clinical evaluation of dysphagia, so they must be included and systematized in all pediatric evaluations; This evaluation can be divided into different parts: bedside swallowing evaluation, instrumental swallowing evaluation, and additional studies. The management of swallowing disorders requires a multidisciplinary team approach, depending on the child's age, cognitive and physical abilities, and the specific swallowing and feeding disorder, ensuring adequate and safe nutrition and improving the patient's quality of life.

Epidemiological Characteristics of Deaths from COVID-19 in Peru during the Initial Pandemic Response.

BACKGROUND AND AIM: Peru is the country with the highest mortality rate from COVID-19 globally, so the analysis of the characteristics of deaths is of national and international interest. The aim was to determine the epidemiological characteristics of deaths from COVID-19 in Peru from 28 March to 21 May 2020. METHODS: Deaths from various sources were investigated, including the COVID-19 Epidemiological Surveillance and the National System of Deaths (SINADEF). In all, 3851 deaths that met the definition of a confirmed case and had a positive result of RT-PCR or rapid test IgM/IgG, were considered for the analysis. We obtained the epidemiological variables and carried out an analysis of time defined as the pre-hospital time from the onset of symptoms to hospitalization, and hospital time from the date of hospitalization to death. RESULTS: Deaths were more frequent in males (72.0%), seniors (68.8%) and residents of the region of Lima (42.7%). In 17.8% of cases, the death occurred out-of-hospital, and 31.4% had some comorbidity. The median of pre-hospital time was 7 days (IQR: 4.0-9.0) and for the hospital time was 5 days (IQR: 3.0-9.0). The multivariable analysis with Poisson regression with robust variance found that the age group, comorbidity diagnosis and the region of origin significantly influenced pre-hospital time; while sex, comorbidity diagnosis, healthcare provider and the region of origin significantly influenced hospital time. CONCLUSION: Deaths occurred mainly in males, seniors and on the coast, with considerable out-of-hospital deaths. Pre-hospital time was affected by age group, the diagnosis of comorbidities and the region of origin; while, hospital time was influenced by gender, the diagnosis of comorbidities, healthcare provider and the region of origin.

Dual attention multiple instance learning with unsupervised complementary loss for COVID-19 screening.

Chest computed tomography (CT) based analysis and diagnosis of the Coronavirus Disease 2019 (COVID-19) plays a key role in combating the outbreak of the pandemic that has rapidly spread worldwide. To date, the disease has infected more than 18 million people with over 690k deaths reported. Reverse transcription polymerase chain reaction (RT-PCR) is the current gold standard for clinical diagnosis but may produce false positives; thus, chest CT based diagnosis is considered more viable. However, accurate screening is challenging due to the difficulty in annotation of infected areas, curation of large datasets, and the slight discrepancies between COVID-19 and other viral pneumonia. In this study, we propose an attention-based end-to-end weakly supervised framework for the rapid diagnosis of COVID-19 and bacterial pneumonia based on multiple instance learning (MIL). We further incorporate unsupervised contrastive learning for improved accuracy with attention applied both in spatial and latent contexts, herein we propose Dual Attention Contrastive based MIL (DA-CMIL). DA-CMIL takes as input several patient CT slices (considered as bag of instances) and outputs a single label. Attention based pooling is applied to implicitly select key slices in the latent space, whereas spatial attention learns slice spatial context for interpretable diagnosis. A contrastive loss is applied at the instance level to encode similarity of features from the same patient against representative pooled patient features. Empirical results show that our algorithm achieves an overall accuracy of 98.6% and an AUC of 98.4%. Moreover, ablation studies show the benefit of contrastive learning with MIL.

Environmental Fe, Ti, Al, Cu, Hg, Bi, and Si Nanoparticles in the Atrioventricular Conduction Axis and the Associated Ultrastructural Damage in Young Urbanites: Cardiac Arrhythmias Caused by Anthropogenic, Industrial, E-Waste, and Indoor Nanoparticles.

Air pollution exposure is a risk factor for arrhythmia. The atrioventricular (AV) conduction axis is key for the passage of electrical signals to ventricles. We investigated whether environmental nanoparticles (NPs) reach the AV axis and whether they are associated with ultrastructural cell damage. Here, we demonstrate the detection of the shape, size, and composition of NPs by transmission electron microscopy (TEM) and energy-dispersive X-ray spectrometry (EDX) in 10 subjects from Metropolitan Mexico City (MMC) with a mean age of 25.3 ± 5.9 and a 71-year-old subject without cardiac pathology. We found that in every case, Fe, Ti, Al, Hg, Cu, Bi, and/or Si spherical or acicular NPs with a mean size of 36 ± 17 nm were present in the AV axis in situ, freely and as conglomerates, within the mitochondria, sarcomeres, lysosomes, lipofuscin, and/or intercalated disks and gap junctions of Purkinje and transitional cells, telocytes, macrophages, endothelium, and adjacent atrial and ventricular fibers. Erythrocytes were found to transfer NPs to the endothelium. Purkinje fibers with increased lysosomal activity and totally disordered myofilaments and fragmented Z-disks exhibited NP conglomerates in association with gap junctions and intercalated disks. AV conduction axis pathology caused by environmental NPs is a plausible and modifiable risk factor for understanding common arrhythmias and reentrant tachycardia. Anthropogenic, industrial, e-waste, and indoor NPs reach pacemaker regions, thereby increasing potential mechanisms that disrupt the electrical impulse pathways of the heart. The cardiotoxic, oxidative, and abnormal electric performance effects of NPs in pacemaker locations warrant extensive research. Cardiac arrhythmias associated with nanoparticle effects could be preventable.

Dose Escalation and Safety of Capsaicin for Cerebral Perfusion Augmentation: A Pilot Study.

Background and Purpose: Sphenopalatine ganglion (SPG) electrical stimulation has been studied in the setting of acute ischemic stroke to enhance collateral flow. Capsaicin poses an alternative to chemically stimulate the sphenopalatine ganglion. Therefore, the objective of this study was to determine the safety and effect of increasing doses of capsaicin upon serial transcranial Doppler markers of cerebral blood flow. Methods: We performed serial transcranial Doppler testing in 30 healthy volunteers divided into 5 equal groups. Capsaicin doses ranged from 33 to 165 µMol. We recorded peak systolic and end-diastolic velocities in the middle cerebral artery, arterial pressure, and perceived pungency in 5-minute intervals up to 20 minutes. We then calculated the mean velocity, the pulsatility index, and the cerebral blood flow index. Results: The participants' median age was 21 years (range, 5 years); all reported consumption of capsaicin in their diets. After and during the study, none reported side effects. Perceived pungency peaked at 5 minutes, and by the 20-minute mark, none perceived any pungency. All the tested doses produced the same pattern, consisting of augmentation of the middle cerebral artery mean velocity with the pulsatility index's diminution. The effects peaked between the 5- and the 10-minute measurements and then returned to basal levels except for the 66-µMol doses, which produced a sustained effect. We found no correlation between perceived pungency and dose, but the middle cerebral artery mean velocity was strongly correlated with the dose administered. Conclusions: This study provides evidence supporting the safety and tolerability of oral capsaicin in a population of healthy volunteers. Capsaicin appears to produce effects similar to those of sphenopalatine ganglion electrical stimulation. Registration: URL: https://www.clinicaltrials.gov; Unique identifier: NCT04545892.

Patients With Unexplained Dilated Pancreatic Duct Have High Risk of Biliopancreatic Malignancy Detected by EUS.

INTRODUCTION: Patients with unexplained dilated common bile duct (CBD) and/or dilated main pancreatic duct (MPD) on noninvasive abdominal imaging tests are often referred for endoscopic ultrasound (EUS) in order to rule out biliopancreatic cancer. The aim of the study was to evaluate the diagnostic yield of EUS in this patient group. METHODS: A prospective study was conducted. Patients with unexplained dilated CBD and/or MPD on abdominal imaging, who underwent EUS, were enrolled. RESULTS: Fifty-four patients underwent EUS (CBD dilation n=38, MPD dilation n=5 or both n=11). In 31/54 patients (57.4%), EUS revealed pathologic findings. Sixteen patients (29.6%) had EUS evidence of biliopancreatic cancer and 15 patients (27.7%) had benign pathology. Ten (62.5%) of the patients with biliopancreatic cancer had MPD dilation. MPD dilation was significantly associated with malignancy (P=0.017). CONCLUSION: Patients with unexplained dilated MPD on noninvasive image have a high risk of biliopancreatic malignancy detected by EUS.

Quantitative Assessment of Chest CT Patterns in COVID-19 and Bacterial Pneumonia Patients: a Deep Learning Perspective.

BACKGROUND: It is difficult to distinguish subtle differences shown in computed tomography (CT) images of coronavirus disease 2019 (COVID-19) and bacterial pneumonia patients, which often leads to an inaccurate diagnosis. It is desirable to design and evaluate interpretable feature extraction techniques to describe the patient's condition. METHODS: This is a retrospective cohort study of 170 confirmed patients with COVID-19 or bacterial pneumonia acquired at Yeungnam University Hospital in Daegu, Korea. The Lung and lesion regions were segmented to crop the lesion into 2D patches to train a classifier model that could differentiate between COVID-19 and bacterial pneumonia. The K-means algorithm was used to cluster deep features extracted by the trained model into 20 groups. Each lesion patch cluster was described by a characteristic imaging term for comparison. For each CT image containing multiple lesions, a histogram of lesion types was constructed using the cluster information. Finally, a Support Vector Machine classifier was trained with the histogram and radiomics features to distinguish diseases and severity. RESULTS: The 20 clusters constructed from 170 patients were reviewed based on common radiographic appearance types. Two clusters showed typical findings of COVID-19, with two other clusters showing typical findings related to bacterial pneumonia. Notably, there is one cluster that showed bilateral diffuse ground-glass opacities (GGOs) in the central and peripheral lungs and was considered to be a key factor for severity classification. The proposed method achieved an accuracy of 91.2% for classifying COVID-19 and bacterial pneumonia patients with 95% reported for severity classification. The CT quantitative parameters represented by the values of cluster 8 were correlated with existing laboratory data and clinical parameters. CONCLUSION: Deep chest CT analysis with constructed lesion clusters revealed well-known COVID-19 CT manifestations comparable to manual CT analysis. The constructed histogram features improved accuracy for both diseases and severity classification, and showed correlations with laboratory data and clinical parameters. The constructed histogram features can provide guidance for improved analysis and treatment of COVID-19.

Can topical epinephrine application to the papilla prevent pancreatitis after endoscopic retrograde cholangiopancreatography? Results from a double blind, multicentre, placebo controlled, randomised clinical trial.

BACKGROUND AND STUDY AIMS: Post-endoscopic retrograde cholangiopancreatography (ERCP) pancreatitis (PEP) is a complication associated with important morbidity, occasional mortality and high costs. Preventive strategies are suboptimal as PEP continues to affect 4% to 9% of patients. Spraying epinephrine on the papilla may decrease oedema and prevent PEP. This study aimed to compare rectal indomethacin plus epinephrine (EI) versus rectal indomethacin plus sterile water (WI) for the prevention of PEP. PATIENTS AND METHODS: This multicentre randomised controlled trial included patients aged >18 years with an indication for ERCP and naive major papilla. All patients received 100 mg of rectal indomethacin and 10 mL of sterile water or a 1:10 000 epinephrine dilution. Patients were asked about PEP symptoms via telephone 24 hours and 7 days after the procedure. The trial was stopped half way through after a new publication reported an increased incidence of PEP among patients receiving epinephrine. RESULTS: Of the 3602 patients deemed eligible, 3054 were excluded after screening. The remaining 548 patients were randomised to EI group (n=275) or WI group (n=273). The EI and WI groups had similar baseline characteristics. Patients in the EI group had a similar incidence of PEP to those in the WI group (3.6% (10/275) vs 5.12% (14/273), p=0.41). Pancreatic duct guidewire insertion was identified as a risk factor for PEP (OR 4.38, 95% CI (1.44 to 13.29), p=0.009). CONCLUSION: Spraying epinephrine on the papilla was no more effective than rectal indomethacin alone for the prevention of PEP. TRIAL REGISTRATION NUMBER: This study was registered with ClinicalTrials.gov (NCT02959112).

Utility of endoscopic ultrasound in idiopathic acute recurrent pancreatitis.

Idiopathic acute recurrent pancreatitis (IARP) is defined as at least two episodes of acute pancreatitis with the complete or near-complete resolution of symptoms and signs of pancreatitis between episodes, without an identified cause. There is a paucity of information about the usefulness of endoscopic ultrasound (EUS) in IARP. OBJECTIVES: To determine the diagnostic yield of EUS in IARP. DESIGN: A retrospective study was performed in patients with IARP evaluated by EUS between January 2009 and December 2016. Follow-up assessments of acute pancreatitis recurrence were carried out. RESULTS: Seventy-three patients with 102 EUS procedures were included. EUS was able to identify the cause of IARP in 55 patients (75.3%). The most common findings were chronic pancreatitis in 27 patients (49.1%), followed by lithiasic pathology in 24 patients (43.6%), and intraductal papillary mucinous neoplasm in four patients (7.3%). A directed treatment against EUS findings had a protective tendency associated with the final resolution of recurrence. There were no complications reported. CONCLUSION: EUS performed in patients with IARP helped to identify a possible cause in 2/3 of the cases. The majority of patients have a treatable disease.

EUS-guided biliary drainage in patients with distal malignant biliary obstruction requires fewer interventions and has a lower cost compared to ERCP biliary drainage.

INTRODUCTION: Endoscopic retrograde cholangiopancreatography (ERCP) biliary drainage is considered the reference standard in patients with biliary obstruction, but it is not free of complications. EUS-guided biliary drainage (EUS-BD) is considered an alternative in patients with failed ERCP; however, data are scarce as to whether EUS-BD could be considered a first option. OBJECTIVE: The aim of our study was to compare the need for reintervention and cost between ERCP biliary drainage vs. EUS-BD. MATERIAL AND METHODS: We conducted a retrospective and comparative study of patients with distal malignant biliary obstruction with biliary drainage with ERCP + plastic stent (ERCP-PS) vs. ERCP + metal stent (ERCP-MS) vs. EUS-BD. RESULTS: 124 patients were included, divided into three groups: ERCP-PS, 60 (48.3%) patients; ERCP-MS, 40 (32.2%) patients; and EUS-BD, 24 (19.3%) patients. The need for reinterventions (67 vs. 37 vs. 4%, respectively), the number of procedures [3 (1-10) vs. 2 (1-7) vs. 1 (1-2)], and the costs (4550 ± 3130 vs. 5555 ± 3210 vs. 2375 ± 1020 USD) were lower in the EUS-BD group. No differences in terms of complications were detected. CONCLUSION: EUS-BD requires fewer reinterventions and has a lower cost compared to drainage by ERCP with metal or plastic stents.

When Is Sentinel Node Biopsy Indicated in High-Risk Ductal Carcinoma in situ? Four Hundred Sixty-Eight Cases from Three Institutions.

INTRODUCTION: Sentinel lymph node biopsy (SLNB) in ductal carcinoma in situ (DCIS) is not indicated. However, in certain cases (size >3 cm, high grade, mass effect on mammography, or palpable mass), it may be possible to find incidental invasive carcinoma (IC) that requires an SLNB. We studied the correlation of the aforesaid factors with the probability of finding IC in the surgical specimen. METHODS: Data was collected from 3 different institutions between 2010 and 2016, recording characteristics such as, but not limited to: high grade, size >3 cm, mass effect on mammography, and palpable mass. RESULTS: On the whole, 468 "high-risk" DCIS cases were identified, 139 (29%) of which had IC. When the DCIS was high grade or the size was >3 cm, there was no significant difference in the probability of finding IC in the surgical specimen (OR = 1.13; 95% CI 0.84-1.51; OR = 1.2; 95% CI 0.85-1.40). Nevertheless, when a high grade and size (>3 cm) were combined, IC was more likely to exist (72.7 vs. 27.3%; p = 0.001). In addition, mass effect and palpation were independently associated with a significantly greater degree of IC (OR = 12.76; 95% CI 6.93-23.52). CONCLUSIONS: The results suggest that high-grade DCIS or DCIS with a size >3 cm, independently, does not require SLNB. Nonetheless, in the event that both factors are found in the same case, SLNB may be indicated. Additionally, SLNB is advisable for DCIS cases that are palpable or show a mass effect on mammography.

Cutaneous Manifestations of Zika in Peru.

This article aims to describe the cutaneous manifestations observed in the Zika epidemic in Peru during 2016 and 2017, as well as discuss the potential differential diagnoses. During the outbreak, the main reason for seeking medical advice was the development of a pruriginous maculopapular rash with a marked papular component, which started on the chest and later generalized to the rest of the body. Similar manifestations were noted in adults, children, and pregnant women. Other manifestations such as conjunctivitis, edema, or petechiae on the palate were rare. We suggest that in areas that are endemic for arboviral infections, in the differential diagnosis of a rash one must consider infections such as dengue, Zika, or chikungunya viruses. In nonendemic areas, the diagnosis is more difficult, as the rash may result from other viral infections not transmitted by arthropods and/or reactive or inflammatory diseases (urticaria, atopic dermatitis, systemic lupus erythematosus). We recommend that primary care health personnel are trained in the recognition of the mucocutaneous lesions caused by Zika virus infection, which could contribute to the identification of suspicious cases, particularly pregnant women.

Analysis of circulating blood and tissue biopsy PDX1 and MSX2 gene expression in patients with pancreatic cancer: A case-control experimental study.

Early diagnosis of pancreatic cancer (PC) is based on endoscopic ultrasound (EUS). However, EUS is invasive and requires a high level of technical skill. Recently, liquid biopsies have achieved the same sensitivity and specificity for the diagnosis of numerous pathologies, including cancer. Insulin-promoting factor 1 (PDX1) and Msh-homeobox 2 (MSX2), 2 homeotic genes, have been confirmed to be related to pancreatic oncogenesis.The aim of this study is to establish the diagnostic utility of circulating serum levels of MSX2 and PDX1 expression in patients with PC.A prospective study was conducted from January 2014 to February 2017. Patients with a suspected diagnosis of PC who underwent fine needle aspiration biopsy guided by EUS (EUS-FNA) were included in the study, in addition to non-PC control subjects. Both tissue and blood serum samples were submitted to histopathological analysis and measurement of PDX1 and MSX2 gene expression by means of qRT-PCR.Patients were divided into non-PC, malignant pathology (MP), or benign pathology (BP) groups. Significant differences in both MSX2 [2.05 (1.66-4.60) vs 0.83 (0.49-1.60), P = .006] and PDX1 [2.59 (1.28-10.12) vs 1.02 (0.81-1.17), P = .036] gene expression were found in blood samples of PC compared with non-PC subjects. We also observed a significant increase in MSX2 transcripts in tissue biopsy samples of patients diagnosed with MP compared with those with BP [1.98 (1.44-4.61) and 0.66 (0.45-1.54), respectively, P = .012]. The ROC curves indicate a sensitivity and specificity of 80% for PDX1 and 86% for MSX2.Gene expression of MSX2 in tissue samples obtained by EUS-FNA and serum expression of MSX2 and PDX1 were higher in patients with PC.

Endoscopic Ultrasound in Pediatric Patients With Pancreatobiliary Disease.

BACKGROUND: Endoscopic ultrasound (EUS) is one of the greatest advances of the last few decades for the diagnostic and therapeutic approach of gastrointestinal diseases in adults. However, there are limitations to the application of the procedure in the pediatric population. The aim of this study was to describe the diagnostic yield and therapeutic role of EUS in pediatric patients with pancreatobiliary disease. MATERIALS AND METHODS: A retrospective study was performed on a prospective database of pediatric patients who underwent diagnostic and therapeutic endosonographic procedures. All patients seen in a 12-year period were included. RESULTS: A total of 54 patients were included, including 32 (59.3%) female individuals, with an average age of 16 (9 to 17) years. EUS was abnormal in 46 (85%) patients. Of the abnormal procedures, 4 (7.4%) corresponded to therapeutic ones. The main indication of the study was recurrent acute pancreatitis in 29 (54%). The main endosonographic findings were microlithiasis in 14 (25.9%), chronic pancreatitis in 9 (16.7%), and pancreatic tumors in 6 (11.1%) patients. Follow-up was performed in 31 (57.4%) patients, 19/31 patients underwent surgery, and 4/31 patients had endoscopic retrograde cholangiopancreatography. The median follow-up was 910 (2 to 3916) days. In 100% of the patients with follow-up, the initial diagnosis of EUS was confirmed. CONCLUSION: EUS is a useful and safe tool in the pediatric population with pancreatobiliary diseases.