Annotation-Efficient Deep Learning Model for Pancreatic Cancer Diagnosis and Classification Using CT Images: A Retrospective Diagnostic Study
Cancers · 28.06.2023 · 15 (13) · 3392
DOI: 10.3390/cancers15133392 ↗Kurz gefasst
Fachartikel in der Zeitschrift Cancers, online erschienen am 28.06.2023. Verfasst von Thanaporn Viriyasaranon und 9 weiteren Autor:innen. Beteiligte Einrichtung: Graduate Program in System Health Science and Engineering, Division of Mechanical and Biomedical Engineering, Ewha Womans University, Seoul 03760, Re…. Die Arbeit wurde bisher 35-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Cancer Center, National Research Foundation of Korea, Korea Medical Device Development Fund.
Abstract (Originalsprache)
The aim of this study was to develop a novel deep learning (DL) model without requiring large-annotated training datasets for detecting pancreatic cancer (PC) using computed tomography (CT) images. This retrospective diagnostic study was conducted using CT images collected from 2004 and 2019 from 4287 patients diagnosed with PC. We proposed a self-supervised learning algorithm (pseudo-lesion segmentation (PS)) for PC classification, which was trained with and without PS and validated on randomly divided training and validation sets. We further performed cross-racial external validation using open-access CT images from 361 patients. For internal validation, the accuracy and sensitivity for PC classification were 94.3% (92.8–95.4%) and 92.5% (90.0–94.4%), and 95.7% (94.5–96.7%) and 99.3 (98.4–99.7%) for the convolutional neural network (CNN) and transformer-based DL models (both with PS), respectively. Implementing PS on a small-sized training dataset (randomly sampled 10%) increased accuracy by 20.5% and sensitivity by 37.0%. For external validation, the accuracy and sensitivity were 82.5% (78.3–86.1%) and 81.7% (77.3–85.4%) and 87.8% (84.0–90.8%) and 86.5% (82.3–89.8%) for the CNN and transformer-based DL models (both with PS), respectively. PS self-supervised learning can increase DL-based PC classification performance, reliability, and robustness of the model for unseen, and even small, datasets. The proposed DL model is potentially useful for PC diagnosis.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Graduate Program in System Health Science and Engineering, Division of Mechanical and Biomedical Engineering, Ewha Womans University, Seoul 03760, Republic of Korea.
- Center for Liver and Pancreatobiliary Cancer, National Cancer Center, Goyang 10408, Republic of Korea.
- Department of Internal Medicine, Gangnam Severance Hospital, Yonsei University College of Medicine, Seoul 03722, Republic of Korea.
- Department of Internal Medicine, Kyungpook National University Hospital, Daegu 41944, Republic of Korea.
- Department of Internal Medicine, Research Institute of Clinical Medicine of Jeonbuk National University-Biomedical Research Institute of Jeonbuk National University Hospital, Jeonju 54907, Republic of Korea.
- Department of Gastroenterology, Korea University Guro Hospital, Seoul 10408, Republic of Korea.
ORCID-Profile: Jung Won Chun, Jae Hee Cho, Min Kyu Jung, Seong-Hun Kim, Woo Jin Lee, Jang-Hwan Choi, Sang Myung Woo
Förderung
- National Cancer Center
- National Research Foundation of Korea
- Korea Medical Device Development Fund
- Trade, Industry, and Energy; Health and Welfare; and Food and Drug Safety
- Korean government (MSIT)
Zitieren
APA
Viriyasaranon, T., Chun, J. W., Koh, Y. H., Cho, J. H., Jung, M. K., Kim, S. H., Kim, H. J., Lee, W. J., Choi, J. H., & Woo, S. M. (2023). Annotation-Efficient Deep Learning Model for Pancreatic Cancer Diagnosis and Classification Using CT Images: A Retrospective Diagnostic Study. Cancers, 15(13), 3392. https://doi.org/10.3390/cancers15133392
Vancouver
Viriyasaranon T, Chun JW, Koh YH, Cho JH, Jung MK, Kim SH, et al. Annotation-Efficient Deep Learning Model for Pancreatic Cancer Diagnosis and Classification Using CT Images: A Retrospective Diagnostic Study. Cancers. 2023;15(13):3392. doi:10.3390/cancers15133392
BibTeX
@article{Viriyasaranon2023,
author = {Viriyasaranon, Thanaporn and Chun, Jung Won and Koh, Young Hwan and Cho, Jae Hee and Jung, Min Kyu and Kim, Seong-Hun and Kim, Hyo Jung and Lee, Woo Jin and Choi, Jang-Hwan and Woo, Sang Myung},
title = {Annotation-Efficient Deep Learning Model for Pancreatic Cancer Diagnosis and Classification Using CT Images: A Retrospective Diagnostic Study},
journal = {Cancers},
year = {2023},
volume = {15},
number = {13},
pages = {3392},
doi = {10.3390/cancers15133392}
}
EUVIMED