Leveraging Pretrained Neural Network Models for the Classification of Tumor Cells Analyzed by Label-Free Phase Holotomographic Microscopy
Computational and Structural Biotechnology Journal · 01.03.2026 · 35 (1)
DOI: 10.34133/csbj.0111 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computational and Structural Biotechnology Journal, online erschienen am 09.06.2026. Verfasst von Leonor V C Losa und 6 weiteren Autor:innen. Beteiligte Einrichtung: INL-International Iberian Nanotechnology Laboratory, Nieder Group on Quantum-,Bio- and Nanophotonics, 4719-330 Braga, Portugal. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Fundação para a Ciência e a Tecnologia, 'la Caixa' Foundation.
Abstract (Originalsprache)
We present an innovative methodology for label-free, high-resolution imaging using phase holotomographic microscopy, coupled with neural network models for the classification of cancer cells. Using 3-dimensional phase holotomographic microscopy, we imaged live A549 lung cancer cells with and without paclitaxel, converted stacks to 2-dimensional maximum-intensity projections, and evaluated pretrained convolutional networks (VGG16, ResNet18, DenseNet121, and EfficientNet-B0) for binary classification of treatment status. EfficientNet-B0 achieved 96.9% accuracy on unsegmented images. Refractive index analysis revealed bimodal distribution in treated cells, reflecting heterogeneous biophysical responses to paclitaxel exposure and supporting the network’s ability to detect subtle, label-free indicators of drug action. As further proof of concept, the same pipeline separated holotomographic images of label-free, high- versus low-grade urothelial cancer cells with high accuracy (90.6%). These findings highlight the potential of integrating label-free holotomographic imaging with deep learning techniques for rapid and efficient classification of tumor cells, paving the way for advancements in treatment optimization and personalized diagnostic strategies.
Autor:innen und Institutionen
- INL-International Iberian Nanotechnology Laboratory, Nieder Group on Quantum-,Bio- and Nanophotonics, 4719-330 Braga, Portugal.
- Department of Biomedicine, Faculty of Medicine, University of Porto, 4200-450 Porto, Portugal.
- RISE-Health, Faculty of Medicine, University of Porto, 4200-450 Porto, Portugal.
ORCID-Profile: Temple A Douglas, Lia Santos, Raquel Monteiro, Isabel Calejo, Raphaël F Canadas, Jana B Nieder
Förderung
- Fundação para a Ciência e a Tecnologia
- 'la Caixa' Foundation
Zitieren
APA
Losa, L. V. C., Douglas, T. A., Santos, L., Monteiro, R., Calejo, I., Canadas, R. F., & Nieder, J. B. (2026). Leveraging Pretrained Neural Network Models for the Classification of Tumor Cells Analyzed by Label-Free Phase Holotomographic Microscopy. Computational and Structural Biotechnology Journal, 35(1). https://doi.org/10.34133/csbj.0111
Vancouver
Losa LVC, Douglas TA, Santos L, Monteiro R, Calejo I, Canadas RF, et al. Leveraging Pretrained Neural Network Models for the Classification of Tumor Cells Analyzed by Label-Free Phase Holotomographic Microscopy. Computational and Structural Biotechnology Journal. 2026;35(1). doi:10.34133/csbj.0111
BibTeX
@article{Losa2026,
author = {Losa, Leonor V C and Douglas, Temple A and Santos, Lia and Monteiro, Raquel and Calejo, Isabel and Canadas, Raphaël F and Nieder, Jana B},
title = {Leveraging Pretrained Neural Network Models for the Classification of Tumor Cells Analyzed by Label-Free Phase Holotomographic Microscopy},
journal = {Computational and Structural Biotechnology Journal},
year = {2026},
volume = {35},
number = {1},
doi = {10.34133/csbj.0111}
}
EUVIMED