Abstract
We aimed to develop a new artificial intelligence (AI)-based method for evaluating endoscopic ultrasound-guided fine-needle biopsy (EUS-FNB) specimens in pancreatic diseases using deep learning and contrastive learning. We analysed a total of 173 specimens from 96 patients who underwent EUS-FNB with a 22 G Franseen needle for pancreatic diseases. In the initial study, the deep learning method based on stereomicroscopic images of 98 EUS-FNB specimens from 63 patients showed an accuracy of 71.8% for predicting the histological diagnosis, which was lower than that of macroscopic on-site evaluation (MOSE) performed by EUS experts (81.6%). Then, we used image analysis software to mark the core tissues in the photomicrographs of EUS-FNB specimens after haematoxylin and eosin staining and verified whether the diagnostic performance could be improved by applying contrastive learning for the features of the stereomicroscopic images and stained images. The sensitivity, specificity, and accuracy of MOSE were 88.97%, 53.5%, and 83.24%, respectively, while those of the AI-based diagnostic method using contrastive learning were 90.34%, 53.5%, and 84.39%, respectively. The AI-based evaluation method using contrastive learning was comparable to MOSE performed by EUS experts and can be a novel objective evaluation method for EUS-FNB.
Highlights
Introduction published maps and institutional affilEndoscopic ultrasound-guided fine-needle aspiration (EUS-FNA) has been widely used as a technique to collect pancreatic tissue [1]
The corresponding values for macroscopic on-site evaluation (MOSE) were 88.9%, 47.1%, 81.6%, 88.9%, and 47.1%, respectively, showing that the diagnostic accuracy of the artificial intelligence (AI)-based evaluation method using deep learning was not as high as that of MOSE performed by an EUS expert (Table 2)
We aimed to develop a new evaluation method for endoscopic ultrasound-guided fine-needle biopsy (EUS-FNB) specimens in pancreatic diseases, and AI-based evaluation using contrastive learning showed a diagnostic performance as good as that of MOSE performed by EUS experts
Summary
Endoscopic ultrasound-guided fine-needle aspiration (EUS-FNA) has been widely used as a technique to collect pancreatic tissue [1]. Several new needles with novel needle tip shapes have been developed, making it possible to collect a larger amount of tissue [2,3]. These new core needles are used in a technique called endoscopic ultrasound-guided fine-needle biopsy (EUS-FNB). Various attempts have been made to evaluate whether proper specimens are being collected under EUS guidance. In 2011, the usefulness of rapid on-site cytology (ROSE) [4] was reported as a specimen evaluation method during EUS-FNA. A touch imprint cytology technique was reported for EUS-FNB specimens, which allows to obtain both cytological and histological specimens at the same time with the same iations
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
