EUVIMEDEUVIMED entdecken
Crossref

Deep Learning-Based Differential Diagnosis of Follicular Thyroid Tumors Using Histopathological Images

Satoshi Nojima, Tokimu Kadoi, Ayana Suzuki, Chiharu Kato, Shoichi Ishida, Kansuke Kido, Kazutoshi Fujita, Yasushi Okuno, Mitsuyoshi Hirokawa, Kei Terayama, Eiichi Morii

Modern Pathology · 2023-11 · 36 (11) · 100296

DOI: 10.1016/j.modpat.2023.100296 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Modern Pathology, 2023-11. Verfasst von Satoshi Nojima und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pathology, Osaka University Graduate School of Medicine, Osaka, Japan. Electronic address: s_nojima@molpath.med.osaka-u.ac.jp. Hauptthemen laut MEDLINE: Deep Learning, Thyroid Neoplasms, Adenocarcinoma, Follicular, Adenoma. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 26 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning systems (DLSs) have been developed for the histopathological assessment of various types of tumors, but none are suitable for differential diagnosis between follicular thyroid carcinoma (FTC) and follicular adenoma (FA). Furthermore, whether DLSs can identify the malignant characteristics of thyroid tumors based only on random views of tumor tissue histology has not been evaluated. In this study, we developed DLSs able to differentiate between FTC and FA based on 3 types of convolutional neural network architecture: EfficientNet, VGG16, and ResNet50. The performance of all 3 DLSs was excellent (area under the receiver operating characteristic curve = 0.91 ± 0.04; F1 score = 0.82 ± 0.06). Visual explanations using gradient-weighted class activation mapping suggested that the diagnosis of both FTC and FA was largely dependent on nuclear features. The DLSs were then trained with FTC images and linked information (presence or absence of recurrence within 10 years, vascular invasion, and wide capsular invasion). The ability of the DLSs to diagnose these characteristics was then determined. The results showed that, based on the random views of histology, the DLSs could predict the risk of FTC recurrence, vascular invasion, and wide capsular invasion with a certain level of accuracy (area under the receiver operating characteristic curve = 0.67 ± 0.13, 0.62 ± 0.11, and 0.65 ± 0.09, respectively). Further improvement of our DLSs could lead to the establishment of automated differential diagnosis systems requiring only biopsy specimens.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningThyroid NeoplasmsAdenocarcinoma, FollicularAdenomaHumansDiagnosis, Differential

Stichwörter der Autor:innen

deep learningfollicular adenomafollicular thyroid carcinoma

Autor:innen und Institutionen

  • Department of Pathology, Osaka University Graduate School of Medicine, Osaka, Japan. Electronic address: s_nojima@molpath.med.osaka-u.ac.jp.
  • Graduate School of Medical Life Science, Yokohama City University, Kanagawa, Japan.
  • Department of Pathology, Osaka University Graduate School of Medicine, Osaka, Japan; Department of Diagnostic Pathology and Cytology, Kuma Hospital, Kobe, Japan.
  • International College of Arts and Science, Yokohama City University, Kanagawa, Japan.
  • Department of Pathology, Osaka University Graduate School of Medicine, Osaka, Japan.
  • Department of Urology, Kindai University Faculty of Medicine, Osaka, Japan.

Zitieren

APA

Nojima, S., Kadoi, T., Suzuki, A., Kato, C., Ishida, S., Kido, K., Fujita, K., Okuno, Y., Hirokawa, M., Terayama, K., & Morii, E. (2023). Deep Learning-Based Differential Diagnosis of Follicular Thyroid Tumors Using Histopathological Images. Modern Pathology, 36(11), 100296. https://doi.org/10.1016/j.modpat.2023.100296

Vancouver

Nojima S, Kadoi T, Suzuki A, Kato C, Ishida S, Kido K, et al. Deep Learning-Based Differential Diagnosis of Follicular Thyroid Tumors Using Histopathological Images. Modern Pathology. 2023;36(11):100296. doi:10.1016/j.modpat.2023.100296

BibTeX
@article{Nojima2023,
  author = {Nojima, Satoshi and Kadoi, Tokimu and Suzuki, Ayana and Kato, Chiharu and Ishida, Shoichi and Kido, Kansuke and Fujita, Kazutoshi and Okuno, Yasushi and Hirokawa, Mitsuyoshi and Terayama, Kei and Morii, Eiichi},
  title = {Deep Learning-Based Differential Diagnosis of Follicular Thyroid Tumors Using Histopathological Images},
  journal = {Modern Pathology},
  year = {2023},
  volume = {36},
  number = {11},
  pages = {100296},
  doi = {10.1016/j.modpat.2023.100296}
}
Kostenlos starten →