Due to its irregular shape and varying contour, pancreas segmentation is a recognized challenge in medical image segmentation. Convolutional neural network (CNN) and Transformer-based networks perform well but have limitations: CNN have constrained receptive fields, and Transformer underutilize image features. This work proposes an improved pancreas segmentation method by combining CNN and Transformer. Point-wise separable convolution was introduced in a stage-wise encoder to extract more features with fewer parameters. A densely connected ensemble decoder enabled multi-scale feature fusion, addressing the structural constraints of skip connections. Consistency terms and contrastive loss were integrated into deep supervision to ensure model accuracy. Extensive experiments on the Changhai and National Institute of Health (NIH) pancreas datasets achieved the highest Dice similarity coefficient (DSC) values of 76.32% and 86.78%, with superiority in other metrics. Ablation studies validated each component's contributions to performance and parameter reduction. Results demonstrate that the proposed loss function smooths training and optimizes performance. Overall, the method outperforms other advanced methods, enhances pancreas segmentation performance, supports physician diagnosis, and provides a reliable reference for future research.
Humans ; Neural Networks, Computer ; Pancreas/diagnostic imaging* ; Image Processing, Computer-Assisted/methods* ; Algorithms ; Deep Learning

OBJECTIVES: In recent years, the incidence and detection rate of pancreatic cystic lesions (PCLs) have increased significantly. Endoscopic ultrasound (EUS) plays an indispensable role in the diagnosis and differential diagnosis of PCLs. However, evidence comparing the diagnostic performance of EUS-guided fine-needle aspiration (EUS-FNA) and fine-needle biopsy (FNB) remains limited. This study aims to compare the diagnostic yield, adequacy of tissue acquisition, and safety between EUS-FNA and EUS-FNB in evaluating PCLs to inform clinical practice. METHODS: A retrospective review was conducted on patients with PCLs who underwent either EUS-FNA or EUS-FNB between January 2014 and August 2021. The diagnostic yield, tissue acquisition adequacy, and incidence of adverse events were compared between the 2 groups. RESULTS: A total of 90 patients with PCLs were included (52 in the FNA group and 38 in the FNB group). The diagnostic yield was similar between the FNA and FNB groups (94.2% vs 94.7%, P>0.05). The adequacy of tissue acquisition was 71.2% in the FNA group and 81.6% in the FNB group (P>0.05). No statistically significant difference was observed in the incidence of adverse events between the 2 groups (P>0.05). CONCLUSIONS Both EUS-FNA and EUS-FNB demonstrate equally high diagnostic yields and tissue adequacy in PCLs, with excellent safety profiles. Both methods are safe and effective diagnostic tools for evaluating PCLs.
Humans ; Endoscopic Ultrasound-Guided Fine Needle Aspiration/adverse effects* ; Retrospective Studies ; Female ; Male ; Pancreatic Cyst/diagnostic imaging* ; Middle Aged ; Biopsy, Fine-Needle/adverse effects* ; Aged ; Pancreatic Neoplasms/diagnosis* ; Adult ; Endosonography/methods* ; Pancreas/pathology* ; Diagnosis, Differential

OBJECTIVE: To propose a non-contrast CT-based algorithm for automated and accurate detection of pancreatic lesions at a low cost. METHODS: With Faster RCNN as the benchmark model, an advanced Faster RCNN (aFaster RCNN) model for pancreatic lesions detection based on plain CT was constructed. The model uses the residual connection network Resnet50 as the feature extraction module to extract the deep image features of pancreatic lesions. According to the morphology of pancreatic lesions, 9 anchor frame sizes were redesigned to construct the RPN module. A new Bounding Box regression loss function was proposed to constrain the training process of RPN module regression subnetwork by comprehensively considering the constraints of the lesion shape and anatomical structure. Finally, a detection frame was generated using the detector in the second stage. The data from a total of 728 cases of pancreatic diseases from 4 clinical centers in China were used for training (518 cases, 71.15%) and testing (210 cases, 28.85%) of the model. The performance of aFaster RCNN was verified through ablation experiments and comparison experiments with 3 classical target detection models SSD, YOLO and CenterNet. RESULTS: The aFaster RCNN model for pancreatic lesion detection achieved recall rates of 73.64% at the image level and 92.38% at the patient level, with an average precision of 45.29% and 53.80% at the image and patient levels, respectively, which were higher than those of the 3 models for comparison. CONCLUSION The proposed method can effectively extract the imaging features of pancreatic lesions from non-contrast CT images to detect the pancreatic lesions.
Humans ; Pancreas/diagnostic imaging* ; Algorithms ; China ; Pancreatic Neoplasms/diagnostic imaging* ; Tomography, X-Ray Computed

Objective To determine the appropriate averaging strategy for pancreatic perfusion datasets to create images for routine reading of insulinoma.Methods Thirty-nine patients undergoing pancreatic perfusion CT in Peking Union Medical College Hospital and diagnosed as insulinoma by pathology were enrolled in this retrospective study.The time-density curve of abdominal aorta calculated by software dynamic angio was used to decide the timings for averaging.Five strategies,by averaging 3,5,7,9 and 11 dynamic scans in perfusion,all including peak enhancement of the abdominal aorta,were investigated in the study.The image noise,pancreas signal-to-noise ratio(SNR),lesion contrast and lesion contrast-to-noise ratio(CNR)were recorded and compared.Besides,overall image quality and insulinoma depiction were also compared.ANOVA and Friedman's test were performed.Results The image noise decreased and the SNR of pancreas increased with the increase in averaging time points(all P<0.001).The lesion contrast(69.81±41.35)averaged from 5 scans showed no significant difference compared with that(72.77±45.25)averaged from 3 scans(P=0.103),both of which were higher than that in other groups(all P≤0.001).The lesion CNRs of the last four groups showed no significant difference(all P>0.99)and were higher than that of the first group(all P<0.05).There was no significant difference in overall image quality among the 5 groups(P=0.977).Conclusions Image averaged from 5 scans showed moderate image noise,pancreas SNR and relatively high lesion contrast and lesion CNR.Therefore,it is advised to be used in image averaging to detect insulinoma.
Contrast Media ; Humans ; Insulinoma/diagnostic imaging* ; Pancreas/diagnostic imaging* ; Pancreatic Neoplasms/diagnostic imaging* ; Perfusion ; Radiographic Image Interpretation, Computer-Assisted ; Reading ; Retrospective Studies ; Signal-To-Noise Ratio

Cases of acute pancreatitis induced by organophosphate intoxication are encountered occasionally in clinics, but very few of them develop into severe pancreas necrosis and irreversible pancreatic function impairment. Here, we report a 47-year-old female organophosphate poisoning case after ingestion of massive insecticides; she was considered to have total necrosis and function failure of the pancreas via serum amylase test, glucose level test, and CT imaging. The patient exhibited no relief under the regular medicine treatment, which included sandostatin, antibiotics, intravenous atropine, and pralidoxime methiodide. She received percutaneous catheterization and drainage of pancreatic zone to expel hazardous necrotic waste, also by which the pathogenic evidence was obtained and the antibiotics were adjusted subsequently. The patient recovered gradually, was discharged after 2 weeks, and was prescribed with oral pancreatin capsules before meals and hypodermic insulin at meals and bedtime to compensate the impaired pancreatic function.
Acute Disease ; Anti-Bacterial Agents ; therapeutic use ; Catheterization ; Female ; Humans ; Insecticides ; poisoning ; Middle Aged ; Organophosphate Poisoning ; Pancreas ; diagnostic imaging ; pathology ; Pancreatin ; therapeutic use ; Pancreatitis ; chemically induced ; diagnostic imaging ; therapy ; Treatment Outcome

OBJECTIVE: To analyze clinical manifestations, diagnosis and treatment of annular pancreas in neonates. METHODS: Clinical data of 114 neonates with annular pancreas admitted in the Children's Hospital of Zhejiang University from January 2009 to December 2018 were reviewed. The demographic parameters (gestational age, birth weight), clinical manifestations, onset time, results of antenatal examination, associated anomalies, radiological findings, operations, postoperative complications were analyzed. RESULTS: One hundred and two cases were examined by abdominal echography, in which 68 cases showed duodenal obstruction, 4 cases showed annular pancreas. Plain abdomen X-ray examination performed in 113 cases before operation, 76 cases presented double-bubble sign, 12 cases presented single-bubble sign and 5 cases had high-position intestinal obstruction. Upper gastrointestinal radiography (UGI) was performed in 103 cases, which suggested duodenal obstruction in 102 cases. Operations were performed in all cases, of which 69 cases were operated under laparoscopy including 1 case converted to open laparotomy. The mean fasting time after surgery was (7.8±2.7) d, and the mean length of hospital stay was (16.9±10.1) d. Five patients had postoperative complications. The incidence of postoperative complications in antenatal abnormal group was lower than that in the antenatal non-abnormal group (<0.05); the average fasting time in laparoendscopic surgery group was shorter than that in traditional laparotomy group (<0.05). CONCLUSIONS Neonates with recurrent vomiting early after birth should be highly suspected to have annular pancreas. The fetal chromosome examination should be performed with abnormal antenatal screening. Surgery is the only effective way to diagnose and treat annular pancreas, and laparoscopic surgery could be the first choice for experienced doctors.
Duodenal Obstruction ; diagnostic imaging ; surgery ; Humans ; Infant, Newborn ; Laparoscopy ; Pancreas ; abnormalities ; diagnostic imaging ; pathology ; surgery ; Pancreatic Diseases ; diagnostic imaging ; pathology ; surgery ; Retrospective Studies

BACKGROUND: Although fat accumulation in human organs is associated with a variety of diseases, there is little evidence about the effect of a fatty pancreas on the development of subclinical chronic pancreatitis over the clinical course. METHODS: We conducted a prospective cohort study from 2008 to 2014 of patients who underwent a medical checkup consultation for fat accumulated in the pancreas. Patients included in the analysis were divided into a non-fatty pancreas group (n = 9710) and fatty pancreas group (n = 223). The primary end point was the odds ratio (OR) for chronic pancreatitis associated with fatty pancreas, which was diagnosed using ultrasonography. We used a multiple logistic regression model to estimate the OR and the corresponding 95% confidence interval (CI). RESULTS: Ninety-two people were diagnosed with chronic pancreatitis, including both presumptive and definitive diagnoses. Twelve people were diagnosed with chronic pancreatitis by ultrasonography among the 223 patients with fatty pancreas, and 80 patients among 9710 were diagnosed with non-fatty pancreas. The crude OR was 6.85 (95% CI 3.68, 12.75), and the multiple adjusted OR was 3.96 (95% CI 2.04, 7.66). CONCLUSIONS Fat accumulation in the pancreas could be a risk factor for developing subclinical chronic pancreatitis.
Adipose Tissue ; diagnostic imaging ; pathology ; Adult ; Alcohol Drinking ; epidemiology ; Female ; Humans ; Japan ; epidemiology ; Life Style ; Logistic Models ; Male ; Middle Aged ; Pancreas ; diagnostic imaging ; pathology ; Pancreatitis, Chronic ; diagnosis ; epidemiology ; etiology ; Physical Examination ; Prospective Studies ; Risk Factors ; Smoking ; epidemiology

Contrast-enhanced ultrasound (CEUS) is a relatively novel, but increasingly used, diagnostic imaging modality. In recent years, due to its safety, quickness, and repeatability, several studies have demonstrated the accuracy, specificity, and sensitivity of CEUS. The European Federation of Societies for Ultrasound in Medicine and Biology has recently updated the previous guidelines from 2012 for the use of CEUS in non-hepatic applications. This review deals with the clinical use and applications of CEUS for the evaluation of non-hepatic abdominal organs, focusing on renal, splenic, and pancreatic applications.
Biology ; Diagnostic Imaging ; Kidney ; Liver ; Pancreas ; Sensitivity and Specificity ; Spleen ; Ultrasonography

The pathogenesis of pancreatic pseudocyst is still not understood. A 5-year-old, 24-kg intact female Shetland Sheepdog was presented with anorexia and vomiting. Diagnostic imaging tests revealed that the left limb of the pancreas was thickened and contained two cystic lesions (6.3 × 5.6 × 4 cm³ and 3.5 × 4.6 × 5.5 cm³). During the laparotomy, lesions were opened with de-roofing of superabundant tissue, and omentalization was performed. The dog recovered uneventfully after surgery and was discharged on postoperative day 12. Histopathologically, it was diagnosed as chronic pancreatic pseudocyst. This case report describes the diagnosis and successful omentalization of pancreatic pseudocysts in a dog.
Animals ; Anorexia ; Child, Preschool ; Diagnosis ; Diagnostic Imaging ; Dogs ; Extremities ; Female ; Humans ; Laparotomy ; Pancreas ; Pancreatic Pseudocyst ; Vomiting

Objective To evaluate the image quality and radiation exposure in multidetector computed tomography (MDCT) with automated topogram-based tube potential selection,compared to fixed tube potential,in patients with solid pancreatic lesions. Methods The preoperative pancreatic dual-source CT images of 113 patients who were confirmed as solid pancreatic lesions by postoperative pathology in the Peking Union Medical College Hospital from January 2014 to August 2016 were retrospectively analyzed.Among them,53 patients were examined on fixed tube potential at 120 kV,and tube current was automatically modulated (group 1). Sixty patients underwent topogram-based automatic tube potential selection (Tube voltage step:90,100 kV) and automated mA modulation (group 2). Two experienced radiologists measured the body sizes,assessed subjective and objective image quality of arterial phase and portal phase,and recorded radiation parameters including CT dose index volume (CTDI) and dose-length product (DLP). Results Of 60 patients in group 2,45 patients were scaned at 90 kV,15 patients were scaned at 100 kV.The average body diameter [(287±24) mm] in 90 kV group was significantly lower than that [(328±22) mm] in 100 kV group(t=0.731,P=0.0008). The mean CTDI[(3.9±1.0) mGy] in group 2 was significantly lower than in group 1 [(9.0±1.9) mGy],reduced by 56.7% (t=17.5,P=0.0003). The average DLP [(109±38) mGy·cm] in group 2 was significantly lower than that in group 1 [(276±83) mGy·cm],reduced by 60.5% (t=14.0,P=0.0007). In group 2,the standard deviations of images background noise in arterial and portal phase were (6.4±0.9) and (6.4±1.0)HU,respectively,which were significantly higher than those in group 1 [(5.6±1.4)HU,t=-3.757,P=0.0003;(5.5±1.4)HU,t=-3.828,P=0.0006]. In group 2,the signal to noise ratios of pancreatic lesions, abdominal aorta in arterial phase and pancreatic lesions, the portal vein in portal phase were 18.8±9.3,76.0±19.3 and 17.4±6.7,33.1±7.2,which were significantly higher than those in group 1 (13.1±8.7,t=-3.379,P=0.001;56.5±22.6,t=-2.268,P=0.025;14.1±8.1,t=-2.283,P=0.024;28.9±8.8,t=-2.613,P=0.009). Conclusion Compared with fixed tube voltage on the second-generation dual-source CT techniques,topogram-based automatic tube potential selection on third-generation dual-source CT can reduce radiation dose without decreasing image quality in imaging solid pancreatic lesions.
Humans ; Multidetector Computed Tomography ; methods ; Pancreas ; diagnostic imaging ; pathology ; Radiation Dosage ; Retrospective Studies ; Signal-To-Noise Ratio