Chandrasekhara, Vinay

ABSTRACT Background Sampling techniques have poor accuracy for classifying biliary strictures as benign or malignant. Previously, a cholangioscopy artificial intelligence (AI) outperfromed sampling techniques based solely on analysis of previously recorded cholangioscopy footage. The aim of this trial was to compare the performance of a real-time cholangioscopy AI to both sampling techniques and human observers for the task of biliary stricture classification. Methods A cholangioscopy AI computer connected directly to a cholangioscope console. The computer analyzed the cholangioscopy video stream during procedures for suspected biliary strictures. The primary outcome of the study was comparison of the performance of cholangioscopy AI to sampling techniques – brush cytology and transpapillary forceps biopsy – for biliary stricture classification. Secondary outcomes included comparison of the AI classification performance to that of human observers (separated into junior-level and experienced-level cohorts) who reviewed the cholangioscopy footage. Results A total of 41 patients were enrolled in the trial and had biliary strictures analyzed by cholangioscopy AI. For the classification of strictures, the AI had greater classification accuracy than standard sampling techniques (87.8% versus 67.4%; p = 0.043). Additionally, the cholangioscopy AI was significantly more accurate for biliary stricture classification than both junior-level (87.8% versus 61.5%; p = 0.001) and experienced endoscopists (87.8% versus 63.15%; p = 0.011). Conclusions This trial demonstrates that sampling techniques and human assessment of biliary strictures are flawed and there may be a benefit to the use of a cholangioscopy AI system to aid in biliary stricture classification.

Background: Fluorescence in situ hybridization (FISH) is recommended as part of multimodality sampling in the evaluation of biliary strictures, but can be false negative in 40%–50% cases. The aim of this study was to comprehensively assess predictors of false-negative FISH in patients with biliary strictures. Methods: Patients undergoing tissue sampling for biliary strictures from October 20 to February 22 were prospectively enrolled (NCT04572711). Procedural factors such as sampling techniques, order, and utilization of combination sampling were recorded. Results of an optimized pancreatobiliary FISH panel with locus-specific probes for 1q21, 7p12, 8q24, and 9p21 were reported per guidelines. Statistical analyses were performed using BlueSky Statistics v.10.3.1, R package v8.81. Results: Of 327 patients, 93 (28.5%) were diagnosed with malignancy. A false-negative pancreatobiliary fluorescence in situ hybridization (PB-FISH) was reported in 40 (43.1%) patients. A history of primary sclerosing cholangitis was associated with lower odds of having a false-negative PB-FISH (aOR=0.38, 95% CI=0.16–0.82, p=0.02), whereas a hilar stricture was associated with a significantly higher false-negative PB-FISH in those with cholangiocarcinoma (aOR=3.2 [1.4–7.9], p=0.009). Dilation of biliary strictures prior to brushing was not associated with a lower rate of false-negative PB-FISH. Conclusions: In this prospective study, hilar strictures were more likely to have false-negative PB-FISH. Dilation of strictures did not affect PB-FISH performance. These results can help guide PB-FISH interpretation.

Abstract Clinicians struggle to accurately classify biliary strictures as benign or malignant. Current endoscopic retrograde cholangiopancreatography (ERCP)-based sampling modalities including brush cytology and forceps biopsy have poor sensitivity for pathologic confirmation of malignancy. Cholangioscopy allows for direct visualization and sampling of biliary pathology; however, this technology is also associated with inaccurate classification of biliary disease. Previously, an artificial intelligence (AI) system that analyzes cholangioscopy footage was found to be more accurate in diagnosing biliary malignancy than ERCP sampling techniques. The aim of this study was to validate this AI system on a new series of examinations. Three academic centers collected all available unedited cholangioscopy recordings. The videos were processed by the cholangioscopy AI system. After analyzing videos, the AI system provided predictions as to whether malignancy was present. AI performance in classifying strictures was compared with the performance of brush cytology and forceps biopsy. 112 cholangioscopy examinations (containing 4 817 081 images) were generated from 99 patients. Of those examinations, 61 (54.5%) were for investigation of biliary strictures (31 [50.8%] benign, 30 [49.2%] malignant). For the correct classification of strictures, the AI system was 80.0% sensitive and 90.3% specific. It was also significantly more accurate for stricture classification (85.2%) than brush cytology (52.5%; P<0.001), forceps biopsy (68.2%; P=0.04), and the combination of brush cytology and forceps biopsy (66.7%; P=0.02). A previously developed cholangioscopy AI system was found to continually outperform standard ERCP sampling modalities for accurate identification of malignancy, without additional retraining, in a multicenter validation cohort.

Background and Aims: This systematic review and meta-analysis aims to compare the performance of UroVysion® FISH based on the different definitions of a positive result used in published literature with the goal of determining the optimal FISH definition for detecting pancreaticobiliary malignancy. Methods: A systematic literature search identified studies from database inception to Sept 2024 that evaluated the diagnostic performance of FISH in determining malignancy among patients with biliary strictures. All thresholds for positive FISH, as defined by the individual study, were included in this review. Subgroup analysis was performed based on the definitions of positive FISH as follows: (1) polysomy only; (2) polysomy, tetrasomy, or trisomy; and (3) polysomy or 9p deletion. Results: Eighteen studies comprising 2516 FISH specimens were analyzed, including 1133 (45.0%) with malignancy. Using a threshold for positivity as defined in individual studies, the overall sensitivity of FISH was 57.6% (95% confidence interval [CI], 49.4–65.4%), and the overall specificity was 87.8% (95% CI, 79.2–93.2%). Subgroup analysis showed that polysomy as the threshold for positive FISH yielded a sensitivity of 49.4% (95% CI, 43.2–55.5%), with an increased specificity of 96.2% (95% CI, 92.7–98.1%), while polysomy + tetrasomy/trisomy as positive FISH resulted in an increased sensitivity of 64.3% (95% CI 55.4–72.2%) but a decreased specificity of 78.9% (95% CI 64.4–88.5%). The addition of 9p deletion to polysomy as the criteria for a positive test resulted in a non-significant increase in sensitivity (54.7% (95% CI 42.4–66.5%) while maintaining specificity (95.1% (95% CI 84.0–98.6%). Conclusions: Based on these findings, polysomy only or polysomy/9p deletion should be considered as the criterion for defining a positive FISH test to improve diagnostic sensitivity while maintaining high specificity.