Data Augmentation of 3D Brain Environment Using Deep Convolutional Refined Auto-Encoding Alpha GAN
| Autor: | Valentina Corbetta, Luca Pozzi, Elena De Momi, Marco Di Marzo, Alice Segato |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Discriminator
Artificial neural network Computer science business.industry Intersection (set theory) Pattern recognition 010501 environmental sciences 01 natural sciences Generative Adversarial Network 030218 nuclear medicine & medical imaging 03 medical and health sciences Alpha (programming language) Magnetic resonance imaging 0302 clinical medicine Encoding (memory) Metric (mathematics) Medical imaging Artificial intelligence business 0105 earth and related environmental sciences Generator (mathematics) |
| Zdroj: | IEEE Transactions on Medical Robotics and Bionics |
| ISSN: | 2576-3202 |
| DOI: | 10.1109/tmrb.2020.3045230 |
| Popis: | Learning-based methods represent the state of the art in path planning problems. Their performance, however, depend on the number of medical images available for the training. Generative Adversarial Networks (GANs) are unsupervised neural networks that can be exploited to synthesize realistic images avoiding the dependency from the original data. In this article, we propose an innovative type of GAN, Deep Convolutional Refined Auto-Encoding Alpha GAN, able to successfully generate 3D brain Magnetic Resonance Imaging (MRI) data from random vectors by learning the data distribution. We combined a Variational Auto-Encoder GAN with a Code Discriminator to solve the common mode collapse problem and reduce the image blurriness. Finally, we inserted a Refiner in series with the Generator Network in order to smooth the shapes of the images and generate more realistic samples. A qualitative comparison between the generated images and the real ones has been used to test our model’s quality. With the use of three indexes, namely the Multi-Scale Structural Similarity Metric, the Maximum Mean Discrepancy and the Intersection over Union, we also performed a quantitative analysis. The final results suggest that our model can be a suitable solution to overcome the shortage of medical images needed for learning-based methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|