Détail du document
Identifiant
oai:arXiv.org:2403.03642
Sujet
Electrical Engineering and Systems... Computer Science - Computer Vision... Computer Science - Machine Learnin...Auteur
Lee, In-Gyu Oh, Jun-Young Yu, Hee-Jung Kim, Jae-Hwan Eom, Ki-Dong Jeong, Ji-HoonCatégorie
Computer Science
Année
2024
Date de référencement
13/03/2024
Mots clés
medicine computer systems radiograph science generated learning veterinary frameworkRésumé
Recently, with increasing interest in pet healthcare, the demand for computer-aided diagnosis (CAD) systems in veterinary medicine has increased.
The development of veterinary CAD has stagnated due to a lack of sufficient radiology data.
To overcome the challenge, we propose a generative active learning framework based on a variational autoencoder.
This approach aims to alleviate the scarcity of reliable data for CAD systems in veterinary medicine.
This study utilizes datasets comprising cardiomegaly radiograph data.
After removing annotations and standardizing images, we employed a framework for data augmentation, which consists of a data generation phase and a query phase for filtering the generated data.
The experimental results revealed that as the data generated through this framework was added to the training data of the generative model, the frechet inception distance consistently decreased from 84.14 to 50.75 on the radiograph.
Subsequently, when the generated data were incorporated into the training of the classification model, the false positive of the confusion matrix also improved from 0.16 to 0.66 on the radiograph.
The proposed framework has the potential to address the challenges of data scarcity in medical CAD, contributing to its advancement.
Lee, In-Gyu,Oh, Jun-Young,Yu, Hee-Jung,Kim, Jae-Hwan,Eom, Ki-Dong,Jeong, Ji-Hoon, 2024, Generative Active Learning with Variational Autoencoder for Radiology Data Generation in Veterinary Medicine
