EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Transfer Learning-Based Integration of Dual Imaging Modalities for Enhanced Classification Accuracy in Confocal Laser Endomicroscopy of Lung Cancer

Mircea-Sebastian Șerbănescu iD, Liliana Streba, Alin Dragoș Demetrian, Andreea-Georgiana Gheorghe, Mădălin Mămuleanu iD, Daniel-Nicolae Pirici iD, Costin-Teodor Streba

Cancers · 11.02.2025 · 17 (4) · 611

DOI: 10.3390/cancers17040611 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cancers, online erschienen am 11.02.2025. Verfasst von Mircea-Sebastian Șerbănescu und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Informatics and Statistics, University of Medicine and Pharmacy of Craiova, 200349 Craiova, Romania. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: MEN, Romania, University of Medicine and Pharmacy of Craiova, Romania.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Objectives: Lung cancer remains the leading cause of cancer-related mortality, underscoring the need for improved diagnostic methods. This study seeks to enhance the classification accuracy of confocal laser endomicroscopy (pCLE) images for lung cancer by applying a dual transfer learning (TL) approach that incorporates histological imaging data.

Methods

Histological samples and pCLE images, collected from 40 patients undergoing curative lung cancer surgeries, were selected to create 2 balanced datasets (800 benign and 800 malignant images each). Three CNN architectures—AlexNet, GoogLeNet, and ResNet—were pre-trained on ImageNet and re-trained on pCLE images (confocal TL) or using dual TL (first re-trained on histological images, then pCLE). Model performance was evaluated using accuracy and AUC across 50 independent runs with 10-fold cross-validation.

Results

The dual TL approach statistically significant outperformed confocal TL, with AlexNet achieving a mean accuracy of 94.97% and an AUC of 0.98, surpassing GoogLeNet (91.43% accuracy, 0.97 AUC) and ResNet (89.87% accuracy, 0.96 AUC). All networks demonstrated statistically significant (p < 0.001) improvements in performance with dual TL. Additionally, dual TL models showed reductions in both false positives and false negatives, with class activation mappings highlighting enhanced focus on diagnostically relevant regions.

Conclusions

Dual TL, integrating histological and pCLE imaging, results in a statistically significant improvement in lung cancer classification. This approach offers a promising framework for enhanced tissue classification. and with future development and testing, iy has the potential to improve patient outcomes.

Schlagwörter

Stichwörter der Autor:innen

classification accuracyconfocal laser endomicroscopydeep learningdual transfer learninghistological imaginglung cancermedical imagingmulti-modal integrationtransfer learning

Autor:innen und Institutionen

  • Department of Medical Informatics and Statistics, University of Medicine and Pharmacy of Craiova, 200349 Craiova, Romania.
  • Department of Oncology and Palliative Care, University of Medicine and Pharmacy of Craiova, 200349 Craiova, Romania.
  • Department of Thoracic Surgery, University of Medicine and Pharmacy of Craiova, 200349 Craiova, Romania.
  • Doctoral School, University of Medicine and Pharmacy of Craiova, 200349 Craiova, Romania.
  • Department of Automatic Control and Electronics, University of Craiova, 200585 Craiova, Romania.
  • Department of Histology, University of Medicine and Pharmacy of Craiova, 200349 Craiova, Romania.

ORCID-Profile: Mircea-Sebastian Șerbănescu, Mădălin Mămuleanu, Daniel-Nicolae Pirici

Förderung

  • MEN, Romania
  • University of Medicine and Pharmacy of Craiova, Romania

Zitieren

APA

Șerbănescu, M. S., Streba, L., Demetrian, A. D., Gheorghe, A. G., Mămuleanu, M., Pirici, D. N., & Streba, C. T. (2025). Transfer Learning-Based Integration of Dual Imaging Modalities for Enhanced Classification Accuracy in Confocal Laser Endomicroscopy of Lung Cancer. Cancers, 17(4), 611. https://doi.org/10.3390/cancers17040611

Vancouver

Șerbănescu MS, Streba L, Demetrian AD, Gheorghe AG, Mămuleanu M, Pirici DN, et al. Transfer Learning-Based Integration of Dual Imaging Modalities for Enhanced Classification Accuracy in Confocal Laser Endomicroscopy of Lung Cancer. Cancers. 2025;17(4):611. doi:10.3390/cancers17040611

BibTeX
@article{erbnescu2025,
  author = {Șerbănescu, Mircea-Sebastian and Streba, Liliana and Demetrian, Alin Dragoș and Gheorghe, Andreea-Georgiana and Mămuleanu, Mădălin and Pirici, Daniel-Nicolae and Streba, Costin-Teodor},
  title = {Transfer Learning-Based Integration of Dual Imaging Modalities for Enhanced Classification Accuracy in Confocal Laser Endomicroscopy of Lung Cancer},
  journal = {Cancers},
  year = {2025},
  volume = {17},
  number = {4},
  pages = {611},
  doi = {10.3390/cancers17040611}
}
Kostenlos starten →