Portable Multispectral Optoelectronic System for Thyroid Cancer Detection
Sensors · 13.07.2026 · 26 (14) · 4448
DOI: 10.3390/s26144448 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 13.07.2026. Verfasst von Edmilson Roberto Braga und 4 weiteren Autor:innen. Beteiligte Einrichtung: Polytechnic School, Department of Electronic Systems, University of São Paulo (USP), São Paulo 05508-220, SP, Brazil. Hauptthemen laut MEDLINE: Thyroid Neoplasms. Die Arbeit nennt 113 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Coordenação de Aperfeicoamento de Pessoal de Nível Superior, Coordenação de Aperfeiçoamento de Pessoal de Nível Superior—Brazil.
Abstract (Originalsprache)
This study reports the development of a portable multispectral optoelectronic system for automated thyroid cancer detection in immunohistochemically stained histological slides. The platform integrates a 14-band AS7343 multispectral sensor, a dual-fiber optical setup operating in transreflectance geometry, and a two-dimensional scanning subsystem for spatially resolved acquisition. Data acquisition and management were implemented on a Raspberry Pi using Python, Flask, React 19.1.0, Redis, and SocketIO for control, visualization, and real-time updates. A standardized Dark–White–Sample protocol was adopted for baseline correction and the generation of multispectral cubes organized by spatial position and spectral band. The dataset comprised 29 patients, 84 FFPE biomarker-stained histological sections, and 66,510 original point-by-point multispectral measurements. Spectral patterns associated with malignant and non-malignant thyroid samples were analyzed using Linear Discriminant Analysis (LDA), Support Vector Machine with radial basis function kernel (SVM-RBF), and Multilayer Perceptron (MLP). All metrics were evaluated on an independent slide-level test set. LDA achieved 86.8% sensitivity, 95.9% specificity, and 91.0% accuracy. SVM-RBF and MLP achieved accuracies of 90.8% and 90.4%, respectively. Macro-averaged AUC-ROC values were 0.836, 0.865, and 0.761, respectively. These findings support the system as a portable proof-of-concept platform for computer-aided thyroid pathology.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Polytechnic School, Department of Electronic Systems, University of São Paulo (USP), São Paulo 05508-220, SP, Brazil.
- Center for Exact Sciences, Architecture, and Engineering (CCEAE), Catholic University of Santos (UniSantos), Santos 11015-002, SP, Brazil.
- Department of Control and Automation Engineering, Federal Institute of Education, Science and Technology of São Paulo (IFSP), São Paulo 01109-010, SP, Brazil.
- Genetic Bases of Thyroid Tumor Laboratory, Division of Genetics, Department of Morphology and Genetics, Federal University of São Paulo (UNIFESP), São Paulo 04023-062, SP, Brazil.
ORCID-Profile: Mauro Sérgio Braga, Janete Maria Cerutti
Förderung
- Coordenação de Aperfeicoamento de Pessoal de Nível Superior
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior—Brazil
Zitieren
APA
Braga, E. R., Braga Júnior, R. M., Braga, M. S., Cerutti, J. M., & Salcedo, W. J. (2026). Portable Multispectral Optoelectronic System for Thyroid Cancer Detection. Sensors, 26(14), 4448. https://doi.org/10.3390/s26144448
Vancouver
Braga ER, Braga Júnior RM, Braga MS, Cerutti JM, Salcedo WJ. Portable Multispectral Optoelectronic System for Thyroid Cancer Detection. Sensors. 2026;26(14):4448. doi:10.3390/s26144448
BibTeX
@article{Braga2026,
author = {Braga, Edmilson Roberto and Braga Júnior, Roberto Márcio and Braga, Mauro Sérgio and Cerutti, Janete Maria and Salcedo, Walter Jaimes},
title = {Portable Multispectral Optoelectronic System for Thyroid Cancer Detection},
journal = {Sensors},
year = {2026},
volume = {26},
number = {14},
pages = {4448},
doi = {10.3390/s26144448}
}
EUVIMED