EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Artificial Intelligence for Liquid Biopsy: FTIR Spectroscopy and Autoencoder-Based Detection of Cancer Biomarkers in Extracellular Vesicles

Riccardo Di Santo, Benedetta Niccolini, Enrico Rosa iD, Marco De Spirito iD, Fabrizio Pizzolante iD, Dario Pitocco, Linda Tartaglione, Alessandro Rizzi, Umberto Basile iD, Valentina Petito, Antonio Gasbarrini iD, Guido Gigante iD und 1 weitere

Cells · 2025

DOI: 10.3390/cells14231909 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cells, 2025. Verfasst von Riccardo Di Santo und 12 weiteren Autor:innen. Beteiligte Einrichtung: Department of Life Science, Health and Health Professions, Link Campus University, 00165 Rome, Italy. Hauptthemen laut MEDLINE: Extracellular Vesicles, Biomarkers, Tumor, Artificial Intelligence, Liver Neoplasms. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Extracellular vesicles (EVs) are increasingly recognized as promising non-invasive biomarkers for cancer and other diseases, but their clinical translation remains limited by the lack of comprehensive characterization strategies. Spectroscopic approaches such as Fourier-transform infrared (FTIR) spectroscopy can provide a global biochemical fingerprint of intact EVs, but their interpretation requires advanced analytical tools. In this study, we applied an autoencoder-based framework to attenuated total reflection FTIR (ATR-FTIR) spectra of blood-derived components, including plasma, red blood cells (RBCs), RBC-ghosts, and EVs, comprising 278 samples collected from 135 patients, to obtain latent features capable of capturing biologically meaningful variability. The autoencoder compressed spectra into 12 latent features while preserving spectral information with low reconstruction error. Unsupervised UMAP projection of the latent features separated the blood components into different clusters, supporting their biological relevance. The model was then applied to EV spectra from patients with hepatocellular carcinoma (HCC) and cirrhotic controls. Four features significantly differed between the two groups, and an elastic-net regularized logistic model evaluated with a leave-one-out cross-validation framework retained a single latent feature, achieving an out-of-fold ROC AUC of 0.785 (95% CI 0.602–0.967), with performance broadly comparable to that typically reported for AFP, the most commonly used biomarker for HCC. This study provides the first proof-of-concept that an autoencoder can be applied to FTIR spectra of EVs, extracting biologically relevant latent features with potential application in cancer detection.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Extracellular VesiclesBiomarkers, TumorArtificial IntelligenceLiver NeoplasmsHumansSpectroscopy, Fourier Transform InfraredLiquid BiopsyFemaleMaleMiddle AgedAgedCarcinoma, HepatocellularAutoencoder

Stichwörter der Autor:innen

FTIR spectroscopyautoencodercancer biomarkersextracellular vesicleshepatocellular carcinomainfrared spectroscopylatent featuresliquid biopsymachine learning

Substanzen

Biomarkers, Tumor

Autor:innen und Institutionen

  • Department of Life Science, Health and Health Professions, Link Campus University, 00165 Rome, Italy.
  • Dipartimento di Neuroscienze, Sezione di Fisica, Università Cattolica del Sacro Cuore (UCSC), Largo Francesco Vito 1, 00168 Rome, Italy.
  • Dipartimento di Scienze della Vita e Sanità Pubblica, Sezione di Medicina Genomica, Università Cattolica del Sacro Cuore (UCSC), Largo Francesco Vito 1, 00168 Rome, Italy.
  • Unità Operativa Complessa Fisica per le Scienze della Vita, Dipartimento di Diagnostica per Immagini, Radioterapia Oncologica ed Ematologia, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, 00168 Rome, Italy.
  • CEMAD, Medical and Surgery Sciences Department, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, 00168 Rome, Italy.
  • UOSA Diabetologia, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, 00168 Rome, Italy.

ORCID-Profile: Enrico Rosa, Marco De Spirito, Fabrizio Pizzolante, Umberto Basile, Antonio Gasbarrini, Guido Gigante

Zitieren

APA

Di Santo, R., Niccolini, B., Rosa, E., De Spirito, M., Pizzolante, F., Pitocco, D., Tartaglione, L., Rizzi, A., Basile, U., Petito, V., Gasbarrini, A., Gigante, G., & Ciasca, G. (2025). Artificial Intelligence for Liquid Biopsy: FTIR Spectroscopy and Autoencoder-Based Detection of Cancer Biomarkers in Extracellular Vesicles. Cells. https://doi.org/10.3390/cells14231909

Vancouver

Di Santo R, Niccolini B, Rosa E, De Spirito M, Pizzolante F, Pitocco D, et al. Artificial Intelligence for Liquid Biopsy: FTIR Spectroscopy and Autoencoder-Based Detection of Cancer Biomarkers in Extracellular Vesicles. Cells. 2025. doi:10.3390/cells14231909

BibTeX
@article{DiSanto2025,
  author = {Di Santo, Riccardo and Niccolini, Benedetta and Rosa, Enrico and De Spirito, Marco and Pizzolante, Fabrizio and Pitocco, Dario and Tartaglione, Linda and Rizzi, Alessandro and Basile, Umberto and Petito, Valentina and Gasbarrini, Antonio and Gigante, Guido and Ciasca, Gabriele},
  title = {Artificial Intelligence for Liquid Biopsy: FTIR Spectroscopy and Autoencoder-Based Detection of Cancer Biomarkers in Extracellular Vesicles},
  journal = {Cells},
  year = {2025},
  doi = {10.3390/cells14231909}
}
Kostenlos starten →