Convolutional neural network model for automatic recognition and classification of pancreatic cancer cell based on analysis of lipid droplet on unlabeled sample by 3D optical diffraction tomography.

INTRODUCTION: Pancreatic cancer cells generally accumulate large numbers of lipid droplets (LDs), which regulate lipid storage. To promote rapid diagnosis, an automatic pancreatic cancer cell recognition system based on a deep convolutional neural network was proposed in this study using quantitative images of LDs from stain-free cytologic samples by optical diffraction tomography. METHODS: We retrieved 3D refractive index tomograms and reconstructed 37 optical images of one cell. From the four cell lines, the obtained fields were separated into training and test datasets with 10,397 and 3,478 images, respectively. Furthermore, we adopted several machine learning techniques based on a single image-based prediction model to improve the performance of the computer-aided diagnostic system. RESULTS: Pancreatic cancer cells had a significantly lower total cell volume and dry mass than did normal pancreatic cells and were accompanied by greater numbers of lipid droplets (LDs). When evaluating multitask learning techniques utilizing the EfficientNet-b3 model through confusion matrices, the overall 2-category accuracy for cancer classification reached 96.7 %. Simultaneously, the overall 4-category accuracy for individual cell line classification achieved a high accuracy of 96.2 %. Furthermore, when we added the core techniques one by one, the overall performance of the proposed technique significantly improved, reaching an area under the curve (AUC) of 0.997 and an accuracy of 97.06 %. Finally, the AUC reached 0.998 through the ablation study with the score fusion technique. DISCUSSION: Our novel training strategy has significant potential for automating and promoting rapid recognition of pancreatic cancer cells. In the near future, deep learning-embedded medical devices will substitute laborious manual cytopathologic examinations for sustainable economic potential.

Clinical impact of pancreatic steatosis measured by CT on the risk of post-ERCP pancreatitis: a multicenter prospective trial.

BACKGROUND AND AIMS: Pancreatic steatosis (PS) may be a risk factor for acute pancreatitis. Whether it is also a risk factor for post-ERCP pancreatitis (PEP) has not been evaluated. This study aimed to determine the impact of PS on PEP development. METHODS: This multicenter prospective trial enrolled 786 consecutive patients who underwent contrast-enhanced abdominal CT and subsequent first-time ERCP. PS was evaluated based on pancreatic attenuation on unenhanced CT images. The risk of PS for the development of PEP was evaluated using a logistic regression model. RESULTS: Of 527 patients included in the study, 157 (29.8%) had PS and 370 (70.2%) did not. At 24 hours after ERCP, there was a significant difference in the PEP identified in 22 patients (14.0%) in the PS group and 23 patients (6.2%) in the "no PS" (NPS) group (P = .017). Diabetes and hypertension were more common in the PS group than in the NPS group; no differences in dyslipidemia were found. Patients with PS had a higher risk for the development of PEP than those with NPS (odds ratio, 2.09; 95% confidence interval, 1.08-4.03). No other variables were identified as risk factors for PEP. CONCLUSIONS: PS is a significant risk factor for PEP for which preventive measures should be considered. Standardized measurement protocols to assess PS by CT are needed. (Clinical trial registration number: KCT0006068.).

Gallbladder perforation in acute acalculous vs. calculous cholecystitis: a retrospective comparative cohort study with 10-year single-center experience.

BACKGROUND: Gallstones are a well-known risk factor for acute cholecystitis. However, their role as a risk factor for gallbladder perforation (GBP) remains unclear. Therefore, this study aimed to determine the effect of gallstones on the development of GBP. MATERIALS AND METHODS: This large-scale retrospective cohort study enroled consecutive patients who underwent cholecystectomy for acute cholecystitis. The primary endpoint was the role of gallstones as a risk factor for developing GBP. Secondary endpoints included the clinical characteristics of GBP, other risk factors for GBP, differences in clinical outcomes between patients with acalculous cholecystitis (AC) and calculous cholecystitis (CC), and the influence of cholecystectomy timing. RESULTS: A total of 4497 patients were included in this study. The incidence of GBP was significantly higher in the AC group compared to the CC group (5.6% vs. 1.0%, P <0.001). However, there were no differences in ICU admission and hospital stay durations. The incidence of overall complications was significantly higher in the AC group than in the CC group (2.2% vs. 1.0%, P <0.001). Patients with AC had a higher risk of developing GBP than those with CC (odds ratio, 5.00; 95% CI, 2.94-8.33). In addition, older age (≥60 years), male sex, comorbidities, poor performance status, and concomitant acute cholangitis were associated with the development of GBP. Furthermore, the incidence of GBP was significantly higher in the delayed cholecystectomy group than in the early cholecystectomy group (2.0% vs. 0.9%, P <0.001). CONCLUSIONS: AC is a significant risk factor for GBP. Furthermore, early cholecystectomy can significantly reduce GBP-related morbidity and mortality.

Placement of Plastic Stents after Direct Endoscopic Necrosectomy through a Novel Lumen-Apposing Metal Stent for Effective Treatment of Laterally Extended Walled-Off Necrosis: A Pilot Study.

Direct endoscopic necrosectomy (DEN) using a lumen-apposing metal stent (LAMS) is a standard therapy for the management of symptomatic walled-off necrosis (WON). Here, we demonstrated the efficacy of the routine placement of long plastic stents after a DEN session to treat laterally extended WON. Patients (n = 6) with symptomatic laterally extended WON who underwent DEN after long plastic stent placement were included. The primary endpoint was clinical efficacy of the procedure. The technical and clinical success rates were 100% without major adverse events. The WON extended to the pelvic cavity or pericolic area, and the WON size was between 18.6 and 35.8 cm in length. The median number of DEN sessions was 10 (range 6-16), and two or three long plastic stents were placed after every DEN session. Only one patient suffered from pneumoperitoneum during DEN, which spontaneously resolved within 20 min. Placement of a long plastic stent after DEN using LAMS is a minimally invasive and effective treatment for symptomatic laterally extended WON. Further studies are needed to define the indications and most suitable patients.

Successful Intubation Using a Cap-Assisted Colonoscope for Endoscopic Retrograde Cholangiopancreatography in Patients Undergoing Roux-en-Y Reconstruction.

Endoscopic retrograde cholangiopancreatography (ERCP) is challenging in patients undergoing Roux-en-Y (REY) reconstruction; although balloon-assisted enteroscopy is the first-line treatment, it is not always available considering equipment and expertise. We aimed to evaluate the feasibility of using a cap-assisted colonoscope as the primary approach for ERCP in REY reconstruction. We included 47 patients with REY who underwent ERCP using a cap-assisted colonoscope between January 2017 and February 2022. The primary outcome was intubation success for ERCP using a cap-assisted colonoscope during REY reconstruction. The secondary outcomes were cannulation success, procedure-related adverse events, and variables affecting successful intubation. Comparing side-to-side jejunojejunostomy (SS-JJ) and side-to-end jejunojejunostomy (SE-JJ) groups, the intubation success rate using a cap-assisted colonoscope in the SS-JJ group was higher than that in the SE-JJ group (34 of 38 (89.5%) vs. 1 of 9 (11.1%), p < 0.001). Successful intubation was achieved in 37 (97.4%) and 8 (88.9%) patients in the SS-JJ and SE-JJ groups, respectively, after applying the rescue technique using a balloon-assisted enteroscope for failed ERCP using only a colonoscope. No perforation occurred. Multivariable analysis showed that SS-JJ was a predictive factor for successful intubation (odds ratio [95% confidence interval] = 37.06 [3.91-925.56], p = 0.005). Usage of a cap-assisted colonoscope can be crucial for ERCP in patients undergoing REY reconstruction. Anatomically, SS-JJ can facilitate easy and accurate identification of the afferent limb and a highly successful ERCP using a cap-assisted colonoscope.

Long-term outcomes and predictors of adverse events of EUS-guided hepatico-gastrostomy for malignant biliary obstruction: Multicenter, retrospective study.

BACKGROUND AND AIMS: Endoscopic ultrasound (EUS)-guided hepaticogastrostomy (HGS) may be a feasible and useful alternative in patients with malignant biliary obstruction (MBO) after failed endoscopic retrograde cholangiopancreatography (ERCP). To date, the risk factors for adverse events (AEs) and long-term outcomes of EUS-HGS have not been fully explored according to stent type. Therefore, we evaluated potential risk factors for AEs and long-term outcomes of EUS-HGS. METHODS: In total, 120 patients who underwent EUS-HGS were retrospectively reviewed. A multivariate analysis through Cox proportional hazard and logistic regression model was used to identify the risk factors for stent dysfunction and AEs, respectively. Stent patency and patient survival were evaluated using Kaplan-Meier plots with a log-rank test for each stent. RESULTS: The technical and clinical success rates were 96.2% (102/106) and 83.0% (88/106). The median duration of stent patency was longer in self-expandable metal stents (SEMS) compared to plastic stents (PS) (158 vs. 108 days). Kaplan-Meier analysis indicated that the type of stent was not associated with stent patency (Hazard ratios [HR] 0.997, 95% confidence interval [CI] [0.525-1.896]) or overall survival. In addition, multivariate analysis indicated that hilar MBO significantly associated with stent dysfunction (HR, 2.340; 95% CI, 1.028-5.326, p = 0.043) and late AEs. CONCLUSIONS: Given the lower incidence of AEs and better long-term outcomes of EUS-HGS, it can be considered a safe alternative to ERCP or percutaneous approaches regardless of which stent is used. Furthermore, hilar MBO was established as a potential risk factor for stent dysfunction and late AEs.

Impact of pancreatic fat on the risk of post-endoscopic retrograde cholangiopancreatography pancreatitis.

BACKGROUND AND STUDY AIMS: Fatty pancreas is a potential risk factor for acute pancreatitis; however, whether it is also a risk factor for post-endoscopic retrograde cholangiopancreatography pancreatitis (PEP) has not been evaluated. We aimed to determine the impact of fatty pancreas on the development of PEP. METHODS: We analyzed the data of patients who underwent abdominal computed tomography (CT) scan and sequential therapeutic endoscopic retrograde cholangiopancreatography (ERCP). Fatty change in the pancreas was evaluated based on pancreatic attenuation of unenhanced image on CT scan. The risk of fatty pancreas for the development of PEP was evaluated using a logistic regression model. RESULTS: Of a total of 858 patients included in the study, 354 (41.3%) had fatty pancreas, while 504 (58.7%) did not have fatty pancreas. PEP developed in 28 patients (7.9%) in the fatty pancreas group and in 13 patients (2.6%) in the no fatty pancreas group. Fatty pancreas was significantly associated with the development of PEP (odds ratio [OR] [95% confidence interval [CI]] 2.38 [1.16-4.87]). A history of acute pancreatitis, female sex, difficult cannulation, and endoscopic papillary balloon dilation were also risk factors for the development of PEP. The risk for moderate-to-severe PEP development tended to be higher in the fatty pancreas group than in the no fatty pancreas group (OR [95% CI] 5.61 [0.63-49.62]). CONCLUSIONS: Fatty pancreas is a significant risk factor for the development of PEP. Clinicians need to be aware of the risk of fatty pancreas for the development of PEP prior to performing ERCP.

Pre- and post-procedure risk prediction models for post-endoscopic retrograde cholangiopancreatography pancreatitis.

BACKGROUND: Post-endoscopic retrograde cholangiopancreatography pancreatitis (PEP) is the most common serious adverse event. Given recent endoscopic advances, we aimed to develop and validate a risk prediction model for PEP using the latest clinical database. METHODS: We analyzed the data of patients with naïve papilla who underwent endoscopic retrograde cholangiopancreatography (ERCP). Pre-ERCP and post-ERCP risk prediction models for PEP were developed using logistic regression analysis. Patients were classified into low- (0 points), intermediate- (1-2 points), and high-risk (≥ 3 points) groups according to point scores. RESULTS: We included 760 and 735 patients in the derivation and validation cohorts, respectively. The incidence of PEP was 5.5% in the derivation cohort and 3.9% in the validation cohort. Age ≤ 65 (1 point), female sex (1 point), acute pancreatitis history (2 points), malignant biliary obstruction (2 points [pre-ERCP model] or 1 point [post-ERCP model]), and pancreatic sphincterotomy (2 points, post-ERCP model only) were independent risk factors. In the validation cohort, the high-risk group (≥ 3 points) had a significantly higher risk of PEP compared to the low- or intermediate-risk groups under the post-ERCP risk prediction model (low: 2.0%; intermediate: 3.4%; high: 18.4%), while there was no significant between-group difference under the pre-ERCP risk prediction model (low: 2.2%; intermediate: 3.8%; high: 6.9%). CONCLUSIONS: We developed and validated pre-ERCP and post-ERCP risk prediction models. In the latter, the high-risk group had a higher risk of PEP development than the low- or intermediate-risk groups. Our study findings will help clinicians stratify patient risk for the development of PEP.

Efficacy of an artificial neural network algorithm based on thick-slab magnetic resonance cholangiopancreatography images for the automated diagnosis of common bile duct stones.

BACKGROUND AND AIM: Magnetic resonance cholangiopancreatography (MRCP) can accurately diagnose common bile duct (CBD) stones but is laborious to interpret. We developed an artificial neural network (ANN) capable of automatically assisting physicians with the diagnosis of CBD stones. This study aimed to evaluate the ANN's diagnostic performance for detecting CBD stones in thick-slab MRCP images and identify clinical factors predictive of accurate diagnosis. METHODS: The presence of CBD stones was confirmed via direct visualization through endoscopic retrograde cholangiopancreatography (ERCP). The absence of CBD stones was confirmed by either a negative endoscopic ultrasound accompanied by clinical improvements or negative findings on ERCP. Our base networks were constructed using state-of-the-art EfficientNet-B5 neural network models, which are widely used for image classification. RESULTS: In total, 3156 images were collected from 789 patients. Of these, 2628 images from 657 patients were used for training. An additional 1924 images from 481 patients were prospectively collected for validation. Across the entire prospective validation cohort, the ANN achieved a sensitivity, specificity, positive predictive value, negative predictive value, and overall accuracy of 93.03%, 97.05%, 97.01%, 93.12%, and 95.01%, respectively. Similarly, a radiologist achieved a sensitivity, specificity, positive predictive value, negative predictive value, and overall accuracy 91.16%, 93.25%, 93.22%, 90.20%, and 91.68%, respectively. In multivariate analysis, only bile duct diameter > 10 mm (odds ratio = 2.45, 95% confidence interval [1.08-6.07], P = 0.040) was related to ANN diagnostic accuracy. CONCLUSION: Our ANN algorithm automatically and quickly diagnoses CBD stones in thick-slab MRCP images, therein aiding physicians with optimizing clinical practice, such as whether to perform ERCP.

Bedside risk-scoring model for predicting 6-week mortality in cirrhotic patients undergoing endoscopic band ligation for acute variceal bleeding.

BACKGROUND AND AIM: Acute variceal bleeding (AVB) is a fatal adverse event of cirrhosis, and endoscopic band ligation (EBL) is the standard treatment for AVB. We developed a novel bedside risk-scoring model to predict the 6-week mortality in cirrhotic patients undergoing EBL for AVB. METHODS: Cox regression analysis was used to assess the relationship of clinical, biological, and endoscopic variables with the 6-week mortality risk after EBL in a derivation cohort (n = 1373). The primary outcome was the predictive accuracy of the new model for the 6-week mortality in the validation cohort. Moreover, we tested the adequacy of the mortality risk-based stratification and the discriminative performance of our new model in comparison with the Child-Turcotte-Pugh (CTP) and the model for end-stage liver disease scores in the validation cohort (n = 200). RESULTS: On multivariate Cox regression analysis, five objective variables (use of beta-blockers, hepatocellular carcinoma, CTP class C, hypovolemic shock at initial presentation, and history of hepatic encephalopathy) were scored to generate a 12-point risk-prediction model. The model stratified the 6-week mortality risk in patients as low (3.5%), intermediate (21.1%), and high (53.4%) (P < 0.001). Time-dependent area under the receiver operating characteristic curve for 6-week mortality showed that this model was a better prognostic indicator than the CTP class alone in the derivation (P < 0.001) and validation (P < 0.001) cohorts. CONCLUSIONS: A simplified scoring model with high potential for generalization refines the prediction of 6-week mortality in high-risk cirrhotic patients, thereby aiding the targeting and individualization of treatment strategies for decreasing the mortality rate.

Comparative Efficacy of Various Stents for Palliation in Patients with Malignant Extrahepatic Biliary Obstruction: A Systematic Review and Network Meta-Analysis.

Although many studies have investigated the efficacy of stent placement for patients with malignant extrahepatic biliary obstruction, the clinical outcomes and adverse events of biliary stenting have not been comprehensively evaluated. We searched all relevant randomized-controlled trials that evaluated the comparative efficacy of biliary stents, including the plastic stents, uncovered self-expandable metal stents (SEMSs), and covered SEMSs in patients with malignant extrahepatic biliary obstructions. Twenty-one studies with 2326 patients were included. Both uncovered and covered SEMSs had a lower risk of recurrent biliary obstruction (RBO) compared to plastic stents (risk ratio (RR) (95% confidence interval [CI]): uncovered vs. plastic, 0.46 (0.35-0.62); covered vs. plastic, 0.46 (0.34-0.62)). A comparison of the groups using SEMSs revealed that tumor ingrowth was common in the uncovered SEMS group, while stent migration, tumor overgrowth, and occlusion by sludge were common in the covered SEMS group; however, the overall risk of RBO did not differ between these groups (RR (95% CI): uncovered vs. covered: 1.02 (0.80-1.30)). Although the main causes of RBO vary across stents, RBO risk was similar between uncovered and covered SEMS groups. Both SEMSs have superior efficacy in terms of RBO compared to plastic stents.

Comparison of the Diagnostic Performance of Novel Slim Biopsy Forceps with Conventional Biopsy Forceps for Biliary Stricture: A Multicenter Retrospective Study.

Novel slim biopsy forceps provide some technical advantages to facilitate a more accurate diagnosis, although we are not aware of any comparative studies. Therefore, we compared tissue acquisition and diagnostic accuracy between novel slim biopsy forceps and conventional biopsy forceps in cases with a biliary stricture. We reviewed 341 patients who underwent endoscopic retrograde cholangiopancreatography for the histological confirmation of biliary stricture at two tertiary hospitals between 2013 and 2020. The primary endpoint was the forceps' diagnostic accuracies. We included 276 patients who underwent biopsy using the novel forceps (n = 130) or conventional forceps (n = 146). The novel forceps provided 81.7% sensitivity, 100.0% specificity, positive-predictive value (PPV) of 100.0%, and negative-predictive value (NPV) of 57.8%, with an accuracy of 85.4% when the diagnosis by endobiliary biopsy included suspected or positive malignancy. The conventional forceps provided 61.7% sensitivity, 100.0% specificity, PPV of 100.0%, and NPV of 36.1%, with an accuracy of 68.5%. Only novel forceps use was significantly associated with an accurate diagnosis (odds ratio: 2.70, 95% confidence interval: 1.52-5.00). There were no significant inter-group differences in the procedure-related rates of adverse events. Endobiliary biopsy using novel forceps offered better diagnostic performance and more acceptable procedure-related adverse events than conventional forceps.

Development of SYBR Green real-time RT-PCR for rapid detection, quantitation and diagnosis of unclassified bovine enteric calicivirus.

Unclassified bovine enteric calicivirus (BECV) is a newly recognized bovine enteric calicivirus that differs from bovine norovirus, and which causes diarrhea in the small intestines of calves. To date, methods such as real-time reverse transcription-polymerase chain reaction (RT-PCR) have not been developed for the rapid detection, quantitation and diagnosis of BECV. Presently, a BECV-specific SYBR Green real-time RT-PCR assay was evaluated and optimized. Diarrheic specimens (n=118) collected from 2004 to 2005 were subjected to RT-PCR, nested PCR and SYBR Green real-time RT-PCR. By conventional RT-PCR and nested PCR, 9 (7.6%) and 59 (50%) samples tested positive, respectively, whereas the SYBR Green assay detected BECV in 91 (77.1%) samples. Using BECV RNA standards generated by in vitro transcription, the SYBR Green real-time RT-PCR assay sensitively detected BECV RNA to 1.1 x 10(0)copies/microl (correlation coefficiency=0.98). The detection limits of the RT-PCR and nested PCR were 1.1 x 10(5) and 1.1 x 10(2)copies/microl, respectively. These results indicate that the SYBR Green real-time RT-PCR assay is more sensitive than conventional RT-PCR and nested PCR assays, and has potential as a reliable, reproducible, specific, sensitive and rapid tool for the detection, quantitation and diagnosis of unclassified BECV.