Generative Active Learning with Variational Autoencoder for Radiology Data Generation in Veterinary Medicine
This work addresses data scarcity for veterinary CAD systems, but it is incremental as it applies existing methods to a new domain.
The paper tackled the problem of data scarcity for computer-aided diagnosis in veterinary medicine by proposing a generative active learning framework with a variational autoencoder, resulting in a decrease in Frechet Inception Distance from 84.14 to 50.75 and an improvement in false positive rate from 0.16 to 0.66 on radiograph data.
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.