TransConv: a lightweight architecture based on transformers and convolutional neural networks for adenocarcinoma and Barrett’s esophagus identification

  • Barrett’s esophagus, also known as BE, is commonly associated with repeated exposure to stomach acid. If not treated properly, it may evolve into esophageal adenocarcinoma, aka esophageal cancer. This paper proposes TransConv, a hybrid architecture that benefits from features learned by pre-trained vision transformers (ViTs) and convolutional neural networks (CNNs), followed by a shallow neuralBarrett’s esophagus, also known as BE, is commonly associated with repeated exposure to stomach acid. If not treated properly, it may evolve into esophageal adenocarcinoma, aka esophageal cancer. This paper proposes TransConv, a hybrid architecture that benefits from features learned by pre-trained vision transformers (ViTs) and convolutional neural networks (CNNs), followed by a shallow neural network composed of three normalizations, ReLU activations, and fully connected layers, and a SoftMax head to distinguish between BE and esophageal cancer. TransConv is designed to be training-lightweight, and for the ViT and CNN backbone models, weights are kept frozen during training, i.e., the primary goal of TransConv is to learn the weights of the fully connected layer from both backbones only, avoiding the burden of updating their weights but still learning their final descriptions for the lightweight convolutional model. We report promising results with low computational training costs in two datasets, one public and another private. From our achievements, TransConv was able to deliver balanced accuracy results around 85% and 86% for each evaluated dataset, respectively, in a design that required only 50 epochs of model training, a very reduced number compared to state-of-the-art conducted studies in the same domain.show moreshow less

Export metadata

Additional Services

Share in Twitter Search Google Scholar Statistics
Metadaten
Author:Luis A. Souza, André G.C. Pacheco, Alberto F. de Souza, Thiago Oliveira-Santos, Claudine Badue, Christoph PalmORCiDGND, João Paulo PapaORCiD
DOI:https://doi.org/10.1007/s00521-025-11299-y
Parent Title (English):Neural Computing and Applications
Publisher:Springer
Document Type:Article
Language:English
Date of first Publication:2025/05/25
Release Date:2025/06/13
Issue:37
Pagenumber:12
First Page:15535
Last Page:15546
Institutes:Fakultät Informatik und Mathematik
Fakultät Informatik und Mathematik / Labor Regensburg Medical Image Computing (ReMIC)
Begutachtungsstatus:peer-reviewed
research focus:Lebenswissenschaften und Ethik
Licence (German):Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG
Einverstanden ✔
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.