Application of artificial intelligence to digital‐rapid on‐site cytopathology evaluation during endoscopic ultrasound‐guided fine needle aspiration: A proof‐of‐concept study
- 23 January 2023
- journal article
- research article
- Published by Wiley in Journal of Gastroenterology and Hepatology
- Vol. 38 (6), 883-887
- https://doi.org/10.1111/jgh.16073
Abstract
BackgroundDuring endoscopic ultrasound-guided fine needle aspiration (EUS-FNA), cytopathology with rapid on-site evaluation (ROSE) can improve diagnostic yield and accuracy. However, ROSE is unavailable in most Asian and European institutions because of the shortage of cytopathologists. Therefore, developing computer-assisted diagnostic tools to replace manual ROSE is crucial. Herein, we reported the validation of an artificial intelligence (AI)-based model (ROSE-AI model) to substitute manual ROSE during EUS-FNA. MethodsA total of 467 digitized images from Diff-Quik (D&F)-stained EUS-FNA slides were divided into training (3642 tiles from 367 images) and internal validation (916 tiles from 100 images) datasets. The ROSE-AI model was trained and validated using training and internal validation datasets, respectively. The specificity was emphasized while developing the model. Then, we evaluated the AI model on a 693-image external dataset. We assessed the performance of the AI model to detect cancer cells (CCs) regarding the accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). ResultsThe ROSE-AI model achieved an accuracy of 83.4% in the internal validation dataset and 88.7% in the external test dataset. The sensitivity and PPV were 79.1% and 71.7% in internal validation dataset and 78.0% and 60.7% in external test dataset, respectively. ConclusionWe provided a proof of concept that AI can be used to replace manual ROSE during EUS-FNA. The ROSE-AI model can address the shortage of cytopathologists and make ROSE available in more institutes.Keywords
Funding Information
- National Natural Science Foundation of China (82070667)
This publication has 25 references indexed in Scilit:
- The Clinical Impact of Immediate On-Site Cytopathology Evaluation During Endoscopic Ultrasound-Guided Fine Needle Aspiration of Pancreatic Masses: A Prospective Multicenter Randomized Controlled TrialThe American Journal of Gastroenterology, 2015
- Structure-preserved color normalization for histological imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Standardized terminology and nomenclature for pancreatobiliary cytology: The Papanicolaou Society of Cytopathology GuidelinesCytojournal, 2014
- Impact of rapid on‐site evaluation on the adequacy of endoscopic‐ultrasound guided fine‐needle aspiration of solid pancreatic lesions: A systematic review and meta‐analysisJournal of Gastroenterology and Hepatology, 2013
- Rapid On-Site Evaluation Reduces Needle Passes in Endoscopic Ultrasound-Guided Fine-Needle Aspiration for Solid Pancreatic Lesions: A Risk–Benefit AnalysisDigestive Diseases and Sciences, 2013
- Rapid on‐site evaluation by endosonographer during endoscopic ultrasound‐guided fine needle aspiration for pancreatic solid massesJournal of Gastroenterology and Hepatology, 2013
- Rapid On-Site Evaluation Increases Endoscopic Ultrasound-Guided Fine-Needle Aspiration Adequacy for Pancreatic LesionsDigestive Diseases and Sciences, 2012
- Endoscopic ultrasound-guided fine-needle aspiration of solid pancreatic masses with rapid on-site cytological evaluation by endosonographers without attendance of cytopathologistsThe Esophagus, 2009
- Clinical impact of on-site cytopathology interpretation on endoscopic ultrasound-guided fine needle aspirationThe American Journal of Gastroenterology, 2003
- The clinical utility of endoscopic ultrasound–guided fine-needle aspiration in the diagnosisand staging of pancreatic carcinomaGastrointestinal Endoscopy, 1997