AI-Assisted Real-Time Cytologic Diagnosis During EUS-FNA of Pancreatic Masses (With Video)
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.Artificial intelligence-assisted rapid on-site evaluation (AI-ROSE) significantly improves diagnostic accuracy and speed for endoscopic ultrasound-guided fine needle aspiration (EUS-FNA) of pancreatic masses. This AI tool offers a promising solution to enhance diagnostic yield in EUS-FNA procedures.
Area Of Science
- Gastroenterology and Hepatology
- Pathology
- Artificial Intelligence in Medicine
Background
- Rapid on-site evaluation (ROSE) is crucial for enhancing the diagnostic yield of endoscopic ultrasound-guided fine needle aspiration (EUS-FNA).
- Limitations in cytopathologist availability can hinder the effectiveness of traditional ROSE.
- This study investigates the diagnostic capability of an artificial intelligence-assisted ROSE (AI-ROSE) system for EUS-FNA.
Purpose Of The Study
- To assess the diagnostic performance of an AI-ROSE system in evaluating pancreatic cell clusters obtained via EUS-FNA.
- To compare the accuracy and efficiency of AI-ROSE with human experts (endosonographers and cytotechnologists) in ROSE.
Main Methods
- A semantic segmentation architecture was developed using digital images of cell clusters from a training cohort (n=96).
- The AI-ROSE model was evaluated on a test cohort (n=26) of 120 cell clusters.
- Diagnostic performance and evaluation time were compared between AI-ROSE, endosonographers, and cytotechnologists.
Main Results
- AI-ROSE achieved 89.8% accuracy for three-category classification and 95.1% accuracy for two-category classification in the test cohort.
- AI-ROSE accuracy (93.3%) significantly surpassed that of endosonographers (68.3%) and cytotechnologists (76.3%) in a comparison cohort.
- AI-ROSE evaluation time (6.04 seconds) was substantially shorter than that of human experts (endosonographers: 1800 seconds; cytotechnologists: 2160 seconds).
Conclusions
- The AI-ROSE model demonstrates high speed and accuracy in diagnosing pancreatic cell clusters during EUS-FNA.
- AI-ROSE facilitates rapid decision-making, potentially improving patient management.
- The AI-ROSE system presents a valuable tool for enhancing the diagnostic process in EUS-FNA procedures.
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
Related Concept Videos
Capsule endoscopy, or wireless or video capsule endoscopy, is a diagnostic procedure for examining the entire gastrointestinal tract. Patients swallow a capsule about the size of a vitamin tablet. The capsule is equipped with a transmitter, a battery, an LED light source, and a color video camera to capture images throughout the gastrointestinal tract. This procedure is particularly useful for diagnosing conditions such as Crohn's disease, ulcerative colitis, tumors, polyps, ulcers,...
Endoscopic Ultrasound (EUS) and FibroScan are valuable diagnostic tools in gastroenterology and hepatology, each with specific applications and techniques.
Endoscopic Ultrasound (EUS):
Technological Integration: EUS is a sophisticated integration of optical endoscopy and ultrasonography. The endoscope visualizes the mucosal surface directly, while the ultrasound component penetrates deeper to visualize organs and structures beyond the gastrointestinal wall.
Image Formation: The ultrasound...