BAPGAN: GAN-based Bone Age Progression of Femur and Phalange X-ray Images
This work addresses a gap in medical imaging for bone-related disease diagnosis and education, but it is incremental as it applies GANs to a new specific domain.
The paper tackled the problem of bone age progression and regression in femur and phalange X-ray images, which had not been addressed before, and proposed BAPGAN to generate realistic images while preserving identity, with validation through expert tests and metrics like Frechet Inception Distance.
Convolutional Neural Networks play a key role in bone age assessment for investigating endocrinology, genetic, and growth disorders under various modalities and body regions. However, no researcher has tackled bone age progression/regression despite its valuable potential applications: bone-related disease diagnosis, clinical knowledge acquisition, and museum education. Therefore, we propose Bone Age Progression Generative Adversarial Network (BAPGAN) to progress/regress both femur/phalange X-ray images while preserving identity and realism. We exhaustively confirm the BAPGAN's clinical potential via Frechet Inception Distance, Visual Turing Test by two expert orthopedists, and t-Distributed Stochastic Neighbor Embedding.