Training high-performance deep learning classifier for diagnosis in oral cytology using diverse annotations

Training high-performance deep learning classifier for diagnosis in oral cytology using diverse annotations

Abstract The uncertainty of true labels in medical images hinders diagnosis owing to the variability across professionals when applying deep learning models. We used deep learning to obtain an optimal convolutional neural network (CNN) by adequately annotating data for oral exfoliative cytology cons...

Full description

Bibliographic Details
Main Authors: Shintaro Sukegawa, Futa Tanaka, Keisuke Nakano, Takeshi Hara, Takanaga Ochiai, Katsumitsu Shimada, Yuta Inoue, Yoshihiro Taki, Fumi Nakai, Yasuhiro Nakai, Takanori Ishihama, Ryo Miyazaki, Satoshi Murakami, Hitoshi Nagatsuka, Minoru Miyake
Format: Article
Language:English
Published: Nature Portfolio 2024-07-01
Series:Scientific Reports
Subjects:
Deep learning
Oral cytology
Classification
Convolutional neural network
Probabilistic labeling
Online Access:https://doi.org/10.1038/s41598-024-67879-w

Internet

https://doi.org/10.1038/s41598-024-67879-w

Similar Items