Application of deep learning as an ancillary diagnostic tool for thyroid FNA cytology
Cancer Cytopathology · 2023-04 · 131 (4) · 217-225
DOI: 10.1002/cncy.22669 ↗Kurz gefasst
Fachartikel in der Zeitschrift Cancer Cytopathology, online erschienen am 16.12.2022. Verfasst von Mitsuyoshi Hirokawa und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Diagnostic Pathology and Cytology, Kuma Hospital, Kobe, Japan. Hauptthemen laut MEDLINE: Deep Learning, Thyroid Nodule, Thyroid Neoplasms, Adenocarcinoma, Follicular. Die Arbeit wurde bisher 44-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Background
Several studies have used artificial intelligence (AI) to analyze cytology images, but AI has yet to be adopted in clinical practice. The objective of this study was to demonstrate the accuracy of AI‐based image analysis for thyroid fine‐needle aspiration cytology (FNAC) and to propose its application in clinical practice.
Methods
In total, 148,395 microscopic images of FNAC were obtained from 393 thyroid nodules to train and validate the data, and EfficientNetV2‐L was used as the image‐classification model. The 35 nodules that were classified as atypia of undetermined significance (AUS) were predicted using AI training.
Results
The precision‐recall area under the curve (PR AUC) was >0.95, except for poorly differentiated thyroid carcinoma (PR AUC = 0.49) and medullary thyroid carcinoma (PR AUC = 0.91). Poorly differentiated thyroid carcinoma had the lowest recall (35.4%) and was difficult to distinguish from papillary thyroid carcinoma, medullary thyroid carcinoma, and follicular thyroid carcinoma. Follicular adenomas and follicular thyroid carcinomas were distinguished from each other by 86.7% and 93.9% recall, respectively. For two‐dimensional mapping of the data using t‐distributed stochastic neighbor embedding, the lymphomas, follicular adenomas, and anaplastic thyroid carcinomas were divided into three, two, and two groups, respectively. Analysis of the AUS nodules showed 94.7% sensitivity, 14.4% specificity, 56.3% positive predictive value, and 66.7% negative predictive value.
Conclusions
The authors developed an AI‐based approach to analyze thyroid FNAC cases encountered in routine practice. This analysis could be useful for the clinical management of AUS and follicular neoplasm nodules (e.g., an online AI platform for thyroid cytology consultations).
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Diagnostic Pathology and Cytology, Kuma Hospital, Kobe, Japan.
- Institute for Datability Science, Osaka University, Suita, Japan.
- Department of Surgery, Kuma Hospital, Kobe, Japan.
- Department of Internal Medicine, Kuma Hospital, Kobe, Japan.
ORCID-Profile: Mitsuyoshi Hirokawa, Hirohiko Niioka, Ayana Suzuki, Masatoshi Abe, Yusuke Arai, Hajime Nagahara, Akira Miyauchi, Takashi Akamizu
Zitieren
APA
Hirokawa, M., Niioka, H., Suzuki, A., Abe, M., Arai, Y., Nagahara, H., Miyauchi, A., & Akamizu, T. (2023). Application of deep learning as an ancillary diagnostic tool for thyroid FNA cytology. Cancer Cytopathology, 131(4), 217-225. https://doi.org/10.1002/cncy.22669
Vancouver
Hirokawa M, Niioka H, Suzuki A, Abe M, Arai Y, Nagahara H, et al. Application of deep learning as an ancillary diagnostic tool for thyroid FNA cytology. Cancer Cytopathology. 2023;131(4):217-225. doi:10.1002/cncy.22669
BibTeX
@article{Hirokawa2023,
author = {Hirokawa, Mitsuyoshi and Niioka, Hirohiko and Suzuki, Ayana and Abe, Masatoshi and Arai, Yusuke and Nagahara, Hajime and Miyauchi, Akira and Akamizu, Takashi},
title = {Application of deep learning as an ancillary diagnostic tool for thyroid FNA cytology},
journal = {Cancer Cytopathology},
year = {2023},
volume = {131},
number = {4},
pages = {217--225},
doi = {10.1002/cncy.22669}
}
EUVIMED