A Lightweight Cross-Gated Dual-Branch Attention Network for Colon and Lung Cancer Diagnosis from Histopathological Images
Medical Sciences · 2025
DOI: 10.3390/medsci13040286 ↗Kurz gefasst
Fachartikel in der Zeitschrift Medical Sciences, 2025. Verfasst von Raquel Ochoa-Ornelas und 5 weiteren Autor:innen. Beteiligte Einrichtung: Systems and Computation Department, Instituto Tecnológico de Ciudad Guzmán, Tecnológico Nacional de México, Ciudad Guzmán 49100, Jalisco, Mexico. Hauptthemen laut MEDLINE: Lung Neoplasms, Colonic Neoplasms. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background/Objectives: Accurate histopathological classification of lung and colon tissues remains difficult due to subtle morphological overlap between benign and malignant regions. Deep learning approaches have advanced diagnostic precision, yet models often lack interpretability or require complex multi-stage pipelines. This study aimed to develop an end-to-end dual-branch attention network capable of achieving high accuracy while preserving computational efficiency and transparency.
Methods
The architecture integrates EfficientNetV2-B0 and MobileNetV3-Small backbones through a cross-gated fusion mechanism that adaptively balances global context and fine structural details. Efficient channel attention and generalized mean pooling enhance discriminative learning without external feature extraction or optimization stages.
Results
The network achieved 99.84% accuracy, precision, recall, and F1-score, with an MCC of 0.998. Grad-CAM maps showed strong spatial correspondence with diagnostically relevant histological structures.
Conclusions
The end-to-end framework enables the reliable, interpretable, and computationally efficient classification of lung and colon histopathology and has potential applicability to computer-assisted diagnostic workflows.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Systems and Computation Department, Instituto Tecnológico de Ciudad Guzmán, Tecnológico Nacional de México, Ciudad Guzmán 49100, Jalisco, Mexico.
- Centro Universitario de Ciencias Exactas e Ingenierías (CUCEI), Electronics and Computing Division, Universidad de Guadalajara, Guadalajara 44430, Jalisco, Mexico.
- Electronics Department, Instituto Tecnológico de Ciudad Guzmán, Tecnológico Nacional de México, Ciudad Guzmán 49100, Jalisco, Mexico.
- Instituto Tecnológico de Tepic, Tecnológico Nacional de México, Tepic 63175, Nayarit, Mexico.
- Instituto Tecnológico de Ciudad Guzmán, Tecnológico Nacional de México, Ciudad Guzmán 49100, Jalisco, Mexico.
ORCID-Profile: Raquel Ochoa-Ornelas, Alberto Gudiño-Ochoa, Sergio Octavio Rosales-Aguayo, Jesús Ezequiel Molinar-Solís, Sonia Espinoza-Morales
Zitieren
APA
Ochoa-Ornelas, R., Gudiño-Ochoa, A., Rosales-Aguayo, S. O., Molinar-Solís, J. E., Espinoza-Morales, S., & Gudiño-Venegas, R. (2025). A Lightweight Cross-Gated Dual-Branch Attention Network for Colon and Lung Cancer Diagnosis from Histopathological Images. Medical Sciences. https://doi.org/10.3390/medsci13040286
Vancouver
Ochoa-Ornelas R, Gudiño-Ochoa A, Rosales-Aguayo SO, Molinar-Solís JE, Espinoza-Morales S, Gudiño-Venegas R. A Lightweight Cross-Gated Dual-Branch Attention Network for Colon and Lung Cancer Diagnosis from Histopathological Images. Medical Sciences. 2025. doi:10.3390/medsci13040286
BibTeX
@article{OchoaOrnelas2025,
author = {Ochoa-Ornelas, Raquel and Gudiño-Ochoa, Alberto and Rosales-Aguayo, Sergio Octavio and Molinar-Solís, Jesús Ezequiel and Espinoza-Morales, Sonia and Gudiño-Venegas, René},
title = {A Lightweight Cross-Gated Dual-Branch Attention Network for Colon and Lung Cancer Diagnosis from Histopathological Images},
journal = {Medical Sciences},
year = {2025},
doi = {10.3390/medsci13040286}
}
EUVIMED