EUVIMEDObjevte EUVIMED
Open access · CC BY 4.0

Characterizing Multi-Domain Representations for Gastric Histopathological Image Classification

Zayra Reyes-Vera, Jesús Yaljá Montiel-Pérez, José Luis López-Bonilla, Elsa Rubio-Espino, Juan Humberto Sossa-Azuela, Víctor Hugo Ponce-Ponce, Osvaldo Espinosa-Sosa, Sergio Vidal-Beltrán

Mathematics · 2026-10-23 · 14 (21) · 3867

DOI: 10.3390/math14213867 ↗

At a glance

Journal article in Mathematics, published online on 2026-10-23. Written by Zayra Reyes-Vera and 7 co-authors. 41 references. The full text is freely available (open access, CC BY 4.0).

AbstraktBibliografické údajeCiteRelated studies

Abstract (original language)

This study characterizes spatial, spectral, relational, and contextual representations for binary gastric histopathological image classification using FLIGENT-Net. The framework combines an ImageNet-pretrained convolutional backbone, patch-level fast Fourier transform (FFT) descriptors, graph convolution over a cosine-similarity graph, and a Transformer Encoder. Experiments use the 160-by-160 GasHisSDB subset, a persisted stratified 60%/20%/20% partition, and one training run per configuration with seed 42. In the nine completed configurations of the revised evaluation, FLIGENT-Net achieved 97.31% accuracy, 96.57% precision, 96.61% recall, 96.59% F1-score for the Abnormal class, and 0.9964 AUC-ROC. An additional native-grid FFT control yielded 97.43% accuracy and 96.74% F1 under an alternative spectral protocol that preserved the 160-by-160 sampling grid while changing the local FFT window sizes and spectral discretization. The conventional CNN baseline (ResNet18) obtained the highest accuracy and F1-score among these completed runs, at 98.51% and 98.13%, respectively. These results do not establish a predictive advantage for the complete multi-domain architecture; rather, they characterize how the added representation domains affect predictive behavior, graph topology, computational cost, and attribution response under a common protocol. The study contributes a reproducible integration of the four representation domains and a controlled empirical characterization of their combinations. Transformer attention visualizations describe information allocation among contextualized nodes, while a common input-gradient deletion protocol examines attribution behavior. Together, these analyses identify the behavior and limitations of the implemented fusion strategy and provide a basis for its further development. Performance estimates are conditional on the available patch-level split and should not be interpreted as patient-, slide-, or source-image-independent generalization; run-to-run variability is also not estimated because one fixed seed is used per configuration.

Cite

APA

Reyes-Vera, Z., Montiel-Pérez, J. Y., López-Bonilla, J. L., Rubio-Espino, E., Sossa-Azuela, J. H., Ponce-Ponce, V. H., Espinosa-Sosa, O., & Vidal-Beltrán, S. (2026). Characterizing Multi-Domain Representations for Gastric Histopathological Image Classification. Mathematics, 14(21), 3867. https://doi.org/10.3390/math14213867

Vancouver

Reyes-Vera Z, Montiel-Pérez JY, López-Bonilla JL, Rubio-Espino E, Sossa-Azuela JH, Ponce-Ponce VH, et al. Characterizing Multi-Domain Representations for Gastric Histopathological Image Classification. Mathematics. 2026;14(21):3867. doi:10.3390/math14213867

BibTeX
@article{ReyesVera2026,
  author = {Reyes-Vera, Zayra and Montiel-Pérez, Jesús Yaljá and López-Bonilla, José Luis and Rubio-Espino, Elsa and Sossa-Azuela, Juan Humberto and Ponce-Ponce, Víctor Hugo and Espinosa-Sosa, Osvaldo and Vidal-Beltrán, Sergio},
  title = {Characterizing Multi-Domain Representations for Gastric Histopathological Image Classification},
  journal = {Mathematics},
  year = {2026},
  volume = {14},
  number = {21},
  pages = {3867},
  doi = {10.3390/math14213867}
}
Start for free →