TY - JOUR
T1 - A deep learning model to detect pancreatic ductal adenocarcinoma on endoscopic ultrasound-guided fine-needle biopsy
AU - Naito, Yoshiki
AU - Tsuneki, Masayuki
AU - Fukushima, Noriyoshi
AU - Koga, Yutaka
AU - Higashi, Michiyo
AU - Notohara, Kenji
AU - Aishima, Shinichi
AU - Ohike, Nobuyuki
AU - Tajiri, Takuma
AU - Yamaguchi, Hiroshi
AU - Fukumura, Yuki
AU - Kojima, Motohiro
AU - Hirabayashi, Kenichi
AU - Hamada, Yoshihiro
AU - Norose, Tomoko
AU - Kai, Keita
AU - Omori, Yuko
AU - Sukeda, Aoi
AU - Noguchi, Hirotsugu
AU - Uchino, Kaori
AU - Itakura, Junya
AU - Okabe, Yoshinobu
AU - Yamada, Yuichi
AU - Akiba, Jun
AU - Kanavati, Fahdi
AU - Oda, Yoshinao
AU - Furukawa, Toru
AU - Yano, Hirohisa
N1 - Publisher Copyright:
© 2021, The Author(s).
PY - 2021/12
Y1 - 2021/12
N2 - Histopathological diagnosis of pancreatic ductal adenocarcinoma (PDAC) on endoscopic ultrasonography-guided fine-needle biopsy (EUS-FNB) specimens has become the mainstay of preoperative pathological diagnosis. However, on EUS-FNB specimens, accurate histopathological evaluation is difficult due to low specimen volume with isolated cancer cells and high contamination of blood, inflammatory and digestive tract cells. In this study, we performed annotations for training sets by expert pancreatic pathologists and trained a deep learning model to assess PDAC on EUS-FNB of the pancreas in histopathological whole-slide images. We obtained a high receiver operator curve area under the curve of 0.984, accuracy of 0.9417, sensitivity of 0.9302 and specificity of 0.9706. Our model was able to accurately detect difficult cases of isolated and low volume cancer cells. If adopted as a supportive system in routine diagnosis of pancreatic EUS-FNB specimens, our model has the potential to aid pathologists diagnose difficult cases.
AB - Histopathological diagnosis of pancreatic ductal adenocarcinoma (PDAC) on endoscopic ultrasonography-guided fine-needle biopsy (EUS-FNB) specimens has become the mainstay of preoperative pathological diagnosis. However, on EUS-FNB specimens, accurate histopathological evaluation is difficult due to low specimen volume with isolated cancer cells and high contamination of blood, inflammatory and digestive tract cells. In this study, we performed annotations for training sets by expert pancreatic pathologists and trained a deep learning model to assess PDAC on EUS-FNB of the pancreas in histopathological whole-slide images. We obtained a high receiver operator curve area under the curve of 0.984, accuracy of 0.9417, sensitivity of 0.9302 and specificity of 0.9706. Our model was able to accurately detect difficult cases of isolated and low volume cancer cells. If adopted as a supportive system in routine diagnosis of pancreatic EUS-FNB specimens, our model has the potential to aid pathologists diagnose difficult cases.
UR - http://www.scopus.com/inward/record.url?scp=85104566896&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85104566896&partnerID=8YFLogxK
U2 - 10.1038/s41598-021-87748-0
DO - 10.1038/s41598-021-87748-0
M3 - Article
C2 - 33875703
AN - SCOPUS:85104566896
SN - 2045-2322
VL - 11
JO - Scientific reports
JF - Scientific reports
IS - 1
M1 - 8454
ER -
