Differentiating localized autoimmune pancreatitis and pancreatic ductal adenocarcinoma using endoscopic ultrasound images with deep learning
DEN Open · 2024-04 · 4 (1)
DOI: 10.1002/deo2.344 ↗Kurz gefasst
Fachartikel in der Zeitschrift DEN Open, online erschienen am 02.03.2024. Verfasst von Hitomi Nakamura und 12 weiteren Autor:innen. Beteiligte Einrichtung: Department of Gastroenterology Faculty of Medicine Yamagata University Yamagata Japan. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Objectives
Localized autoimmune pancreatitis is difficult to differentiate from pancreatic ductal adenocarcinoma on endoscopic ultrasound images. In recent years, deep learning methods have improved the diagnosis of diseases. Hence, we developed a special cross‐validation framework to search for effective methodologies of deep learning in distinguishing autoimmune pancreatitis from pancreatic ductal adenocarcinoma on endoscopic ultrasound images.
Methods
Data from 24 patients diagnosed with localized autoimmune pancreatitis (8751 images) and 61 patients diagnosed with pancreatic ductal adenocarcinoma (20,584 images) were collected from 2016 to 2022. We applied transfer learning to a convolutional neural network called ResNet152, together with our innovative imaging method contributing to data augmentation and temporal data process. We divided patients into five groups according to different factors for 5‐fold cross‐validation, where the ordered and balanced datasets were created for the performance evaluations.
Results
ResNet152 surpassed the endoscopists in all evaluation metrics with almost all datasets. Interestingly, when the dataset is balanced according to the factor of the endoscopists’ diagnostic accuracy, the area under the receiver operating characteristic curve and accuracy were highest at 0.85 and 0.80, respectively.
Conclusions
It is deduced that image features useful for ResNet152 correlate with those used by endoscopists for their diagnoses. This finding may contribute to sample‐efficient dataset preparation to train convolutional neural networks for endoscopic ultrasonography‐imaging diagnosis.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Gastroenterology Faculty of Medicine Yamagata University Yamagata Japan.
- Department of Science Faculty of Science Yamagata University Yamagata Japan.
- Institute of Well-Being Yamagata University Yamagata Japan.
ORCID-Profile: Hitomi Nakamura
Zitieren
APA
Nakamura, H., Fukuda, M., Matsuda, A., Makino, N., Kimura, H., Ohtaki, Y., Nawa, Y., Oyama, S., Suzuki, Y., Kobayashi, T., Ishizawa, T., Kakizaki, Y., & Ueno, Y. (2024). Differentiating localized autoimmune pancreatitis and pancreatic ductal adenocarcinoma using endoscopic ultrasound images with deep learning. DEN Open, 4(1). https://doi.org/10.1002/deo2.344
Vancouver
Nakamura H, Fukuda M, Matsuda A, Makino N, Kimura H, Ohtaki Y, et al. Differentiating localized autoimmune pancreatitis and pancreatic ductal adenocarcinoma using endoscopic ultrasound images with deep learning. DEN Open. 2024;4(1). doi:10.1002/deo2.344
BibTeX
@article{Nakamura2024,
author = {Nakamura, Hitomi and Fukuda, Motohisa and Matsuda, Akiko and Makino, Naohiko and Kimura, Hirohito and Ohtaki, Yu and Nawa, Yoshihito and Oyama, Soushi and Suzuki, Yuya and Kobayashi, Toshikazu and Ishizawa, Tetsuya and Kakizaki, Yasuharu and Ueno, Yoshiyuki},
title = {Differentiating localized autoimmune pancreatitis and pancreatic ductal adenocarcinoma using endoscopic ultrasound images with deep learning},
journal = {DEN Open},
year = {2024},
volume = {4},
number = {1},
doi = {10.1002/deo2.344}
}
EUVIMED