EUVIMEDEUVIMED entdecken
Crossref

Application of Artificial Intelligence–Based Transfer Learning Models to the Bethesda System for Thyroid Cytopathology

Pranab Dey iD, Rajiv Savala, Uma Nahar Saikia

Cytopathology · 2025

DOI: 10.1111/cyt.70045 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cytopathology, 2025. Verfasst von Pranab Dey und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cytology, Post Graduate Institute of Medical Education and Research, Chandigarh, India. Hauptthemen laut MEDLINE: Thyroid Gland, Thyroid Neoplasms, Artificial Intelligence, Cytodiagnosis. Die Arbeit nennt 17 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

The Bethesda System for Reporting Thyroid Cytopathology (TBSRTC) provides a standardised framework for thyroid fine needle aspiration cytology (FNAC). Deep learning approaches, particularly transfer learning, have shown potential for cytology but are rarely applied to TBSRTC categorisation. Aims and Objectives To evaluate the performance of an ensemble soft voting transfer learning model in categorising thyroid cytology smears according to TBSRTC. Materials and Methods A retrospective study of 94 thyroid FNAC cases with 949 representative images was conducted. Six transfer learning models (Xception, ResNet50V2, DenseNet121, MobileNetV2, InceptionV3, EfficientNetB3) were combined using ensemble soft voting with a weighted average. Model performance was assessed using sensitivity, specificity, precision (PPV), negative predictive value (NPV), F1 score and area under the receiver operating characteristic curve (AUCROC).

Results

DenseNet121 achieved the highest overall sensitivity (0.91) and specificity (0.98) among all single models. The weighted ensemble model achieved an F1 score of 0.867, marginally below DenseNet121 but with superior precision (0.882) and NPV (0.968). AUCROC was highest in DenseNet 121 (0.99) followed by the weighted ensemble (0.98).

Conclusion

This is the first study to apply ensemble transfer learning to TBSRTC categorisation. The approach demonstrated strong predictive accuracy, particularly for benign and malignant categories. Larger datasets, ideally with whole‐slide imaging, are needed to further validate these findings.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Thyroid GlandThyroid NeoplasmsArtificial IntelligenceCytodiagnosisHumansBiopsy, Fine-NeedleRetrospective StudiesThyroid NoduleFemaleSensitivity and SpecificityROC CurveDeep LearningMale

Stichwörter der Autor:innen

deep learningensemble learningthyroidtransfer learning

Autor:innen und Institutionen

  • Department of Cytology, Post Graduate Institute of Medical Education and Research, Chandigarh, India.
  • Department of Pathology, Post Graduate Institute of Medical Education and Research, Chandigarh, India.
  • Department of Histopathology, Post Graduate Institute of Medical Education and Research, Chandigarh, India.

ORCID-Profile: Pranab Dey

Zitieren

APA

Dey, P., Savala, R., & Saikia, U. N. (2025). Application of Artificial Intelligence–Based Transfer Learning Models to the Bethesda System for Thyroid Cytopathology. Cytopathology. https://doi.org/10.1111/cyt.70045

Vancouver

Dey P, Savala R, Saikia UN. Application of Artificial Intelligence–Based Transfer Learning Models to the Bethesda System for Thyroid Cytopathology. Cytopathology. 2025. doi:10.1111/cyt.70045

BibTeX
@article{Dey2025,
  author = {Dey, Pranab and Savala, Rajiv and Saikia, Uma Nahar},
  title = {Application of Artificial Intelligence–Based Transfer Learning Models to the Bethesda System for Thyroid Cytopathology},
  journal = {Cytopathology},
  year = {2025},
  doi = {10.1111/cyt.70045}
}
Kostenlos starten →