Hyperbolic Space Feature Enhancement and Interaction Mechanism for Classification on Small Multimodal Medical Datasets
Expert Systems · 2025-10 · 42 (10)
DOI: 10.1111/exsy.70130 ↗Kurz gefasst
Fachartikel in der Zeitschrift Expert Systems, online erschienen am 04.09.2025. Verfasst von Leandro Muniz de Lima und 1 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 76 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundação de Amparo à Pesquisa e Inovação do Espírito Santo, Conselho Nacional de Desenvolvimento Científico e Tecnológico, Coordenação de Aperfeiçoamento de Pessoal de Nível Superior.
Abstract (Originalsprache)
Cancer is one of the leading causes of death worldwide, and early diagnosis of the disease is one of the most important factors in reducing mortality or increasing lifespan. Traditionally, healthcare experts use various sources of information to determine a diagnosis, often including some form of imaging along with clinical and demographic data. In this work, we propose a method to improve fusion of medical images and multi‐field complementary data for classification in small datasets using deep learning models. To achieve that, we introduce a novel complementary data extraction block using hyperbolic space feature enhancement by Poincaré transformation and a mechanism for multi‐field feature interactions. We evaluate it using datasets for the diagnosis of skin cancer (PAD‐UFES‐20) and oral cavity cancer (NDB‐UFES). The experimental results show statistically significant improvement in performance on PAD‐UFES‐20 dataset of the proposed model over baseline. The SingleS Poincaré Conv–Concat with MetaBlock fusion model using PiT image backbone achieved performance of in balanced accuracy metric. For NBD‐UFES dataset, the ViT architecture with SingleDS Poincaré Conv–Concat using MetaBlock fusion () obtained the best mean among all the results evaluated. The results indicate the feasibility of the proposed approach. The source code is public available at GitHub at https://github.com/lmlima/Hyperbolic‐space‐feature‐enhancement‐and‐interaction‐mechanism‐for‐classification .
Förderung
- Fundação de Amparo à Pesquisa e Inovação do Espírito Santo
- Conselho Nacional de Desenvolvimento Científico e Tecnológico
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
Zitieren
APA
Lima, L. M. D., & Krohling, R. A. (2025). Hyperbolic Space Feature Enhancement and Interaction Mechanism for Classification on Small Multimodal Medical Datasets. Expert Systems, 42(10). https://doi.org/10.1111/exsy.70130
Vancouver
Lima LMD, Krohling RA. Hyperbolic Space Feature Enhancement and Interaction Mechanism for Classification on Small Multimodal Medical Datasets. Expert Systems. 2025;42(10). doi:10.1111/exsy.70130
BibTeX
@article{Lima2025,
author = {Lima, Leandro Muniz de and Krohling, Renato Antonio},
title = {Hyperbolic Space Feature Enhancement and Interaction Mechanism for Classification on Small Multimodal Medical Datasets},
journal = {Expert Systems},
year = {2025},
volume = {42},
number = {10},
doi = {10.1111/exsy.70130}
}
EUVIMED