Artificial Intelligence (AI) Cytopathology Trial

The University of Texas Health Science Center, Houston50 enrolled

Overview

Purpose The primary objective of the study is to compare interpretation of EUS FNA/FNB samples for adequacy between ROSE and AI at bedside. To compare accuracy of preliminary diagnosis results between ROSE and AI at bedside versus final pathology report. Research design This is a prospective single center study to compare performance characteristics in the interpretation of EUS FNA/FNB samples between AI and ROSE. Procedures to be used Eligible patients will undergo EUS guided FNA/FNA of PSLs using standard of care. Sample slides are prepared by a cytopathologist at bedside and observed under a microscope. At the same time, the slides are scanned using a slide scanner and those images are saved for interpretation by AI at a later time.

Study Type

OBSERVATIONAL

Enrollment

Conditions

Pancreatic Solid Lesions

Interventions

Artificial Intelligence software ROSEOTHER

Rapid on-site evaluation (ROSE) of Endoscopic Ultrasound (EUS) guided FNA/FNB (Fine Needle Aspirate/Fine Needle Biopsy) of pancreatic solid lesions (PSLs) has been shown in improve diagnostic yield. The availability and performance of ROSE at EUS performing centers is variable. With strides in Artificial Intelligence (AI) capabilities over the years, the University of Texas at Health Sciences Center at Houston in collaboration with Haystac is developing an artificial intelligence based proprietary system to analyze slides from EUS FNA/FNB samples at bedside.

Outcomes

Primary Outcomes

Detection the adequacy for diagnosis

The primary outcome of the study is to determine how AI compares with ROSE in determining if EUS FNA/FNB sample from PSLs is adequate for diagnosis. This will be interpreted as a percentage in each group. The main study parameter is on-site determination if an EUS FNA/FNB sample is adequate for interpretation and diagnosis

Time frame: During procedure

Secondary Outcomes

Comparing the accuracy between preliminary diagnosis

To compare the accuracy between AI and ROSE preliminary diagnosis versus the final pathology report. Interpretation of preliminary results will be divided into categories of benign vs malignancy, acinar cells vs ductal cells in benign, adenocarcinoma vs neuroendocrine tumor vs other in malignancy.