The automatic diagnosis artificial intelligence system for preoperative magnetic resonance imaging of uterine sarcoma
Journal of Gynecologic Oncology · 2024
DOI: 10.3802/jgo.2024.35.e24 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Gynecologic Oncology, 2024. Verfasst von Yusuke Toyohara und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Obstetrics and Gynecology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Uterine Neoplasms, Sarcoma, Artificial Intelligence. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Kanto - Rengo Society of Obstetrics and Gynecology Award and BRIDGE.
Abstract (Originalsprache)
OBJECTIVE: Magnetic resonance imaging (MRI) is efficient for the diagnosis of preoperative uterine sarcoma; however, misdiagnoses may occur. In this study, we developed a new artificial intelligence (AI) system to overcome the limitations of requiring specialists to manually process datasets and a large amount of computer resources. METHODS: The AI system comprises a tumor image filter, which extracts MRI slices containing tumors, and sarcoma evaluator, which diagnoses uterine sarcomas. We used 15 types of MRI patient sequences to train deep neural network (DNN) models used by tumor filter and sarcoma evaluator with 8 cross-validation sets. We implemented tumor filter and sarcoma evaluator using ensemble prediction technique with 9 DNN models. Ten tumor filters and sarcoma evaluator sets were developed to evaluate fluctuation accuracy. Finally, AutoDiag-AI was used to evaluate the new validation dataset, including 8 cases of sarcomas and 24 leiomyomas. RESULTS: Tumor image filter and sarcoma evaluator accuracies were 92.68% and 90.50%, respectively. AutoDiag-AI with the original dataset accuracy was 89.32%, with 90.47% sensitivity and 88.95% specificity, whereas AutoDiag-AI with the new validation dataset accuracy was 92.44%, with 92.25% sensitivity and 92.50% specificity. CONCLUSION: Our newly established AI system automatically extracts tumor sites from MRI images and diagnoses them as uterine sarcomas without human intervention. Its accuracy is comparable to that of a radiologist. With further validation, the system could be applied for diagnosis of other diseases. Further improvement of the system's accuracy may enable its clinical application in the future.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Obstetrics and Gynecology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan.
- Department of Obstetrics and Gynecology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan. ksone5274@gmail.com.
- SIOS Technology, Inc., Tokyo, Japan.
- Department of Radiology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan.
ORCID-Profile: Yusuke Toyohara, Kenbun Sone, Katsuhiko Noda, Kaname Yoshida, Shimpei Kato, Masafumi Kaiume, Ayumi Taguchi, Ryo Kurokawa, Yutaka Osuga
Förderung
- Kanto - Rengo Society of Obstetrics and Gynecology Award and BRIDGE
Zitieren
APA
Toyohara, Y., Sone, K., Noda, K., Yoshida, K., Kato, S., Kaiume, M., Taguchi, A., Kurokawa, R., & Osuga, Y. (2024). The automatic diagnosis artificial intelligence system for preoperative magnetic resonance imaging of uterine sarcoma. Journal of Gynecologic Oncology. https://doi.org/10.3802/jgo.2024.35.e24
Vancouver
Toyohara Y, Sone K, Noda K, Yoshida K, Kato S, Kaiume M, et al. The automatic diagnosis artificial intelligence system for preoperative magnetic resonance imaging of uterine sarcoma. Journal of Gynecologic Oncology. 2024. doi:10.3802/jgo.2024.35.e24
BibTeX
@article{Toyohara2024,
author = {Toyohara, Yusuke and Sone, Kenbun and Noda, Katsuhiko and Yoshida, Kaname and Kato, Shimpei and Kaiume, Masafumi and Taguchi, Ayumi and Kurokawa, Ryo and Osuga, Yutaka},
title = {The automatic diagnosis artificial intelligence system for preoperative magnetic resonance imaging of uterine sarcoma},
journal = {Journal of Gynecologic Oncology},
year = {2024},
doi = {10.3802/jgo.2024.35.e24}
}
EUVIMED