Ensembles of GANs as a Data Augmentation Technique for Alzheimer research

Data scarcity is a regular problem in research, and in medicine it’s especially difficult to find datasets publicly available. The main reason is its rarity, by definition images of anomalies are scattered and/or not common, and also there are a lot of legal issues that prevent sharing personal information about patients. In this talk, I’m going to give an introduction to ensembles, and more specifically to Generative Adversarial Networks (GANs) ensembles, applied to this problem of data scarcity, generating MRI images of demented brains that could be use in Alzheimer research.

Presented at Pycon Italia 2023 - https://pycon.it/en/event/ensembles-of-gans-as-a-data-augmentation-technique-for-alzheimer-research
Repo: https://github.com/p1nox/gan_ensembles

Transcript

1. Ensemble of GANs as a Data Augmentation Technique for Alzheimer research by Raul Pino PyCon Italia 2023
2. Designing and Developing your own Capstone Project by Raul Pino PyCon Italia 2023
3. Using PyTorch to Generate Demented Brains by Raul Pino PyCon Italia 2023
4. • Alzheimer, motivation, and research. • Capstone project: Idea + value added + metrics. • Bases: ◦ Intro to Deep Learning. ◦ Original DCGAN paper. ◦ Ensembles of GANs paper. • Solution & Demo: ◦ Dataset exploration. ◦ GAN base architecture. ◦ Ensemble techniques implementation. ◦ Results. • Takeaways & beyond. Agenda
5. About me • Born in Venezuela. • +10 years of exp as Software Engineer & AI enthusiast (ML Eng recently). • Living in Chile. ◦ Elementus - uBiome - Groupon. • <3 AI, Coffee, Scuba Diving, …
6. Alzheimer, motivation & research • Data scarcity. • Anonymization. • Sampling Bias. • Art & awareness. • Most common case of dementia. • Neurodegenerative, loss of neurons. • Difficult diagnosis. • No cure.
7. Capstone project: idea + value added + metrics Deep Learning & Machine Learning Engineer programs. • Something related to Alzheimer? Datasets? • Background research? Previous work? • Anything new? Any papers? Any interesting mix? ◦ Ensembles of GANs? #wat? • Any metrics to test solution?
8. Basics: Intro Deep Learning Neural Network on structured data like a csv.
9. Basics: Intro Deep Learning Neural Network on structured data like a csv.
10. Basics: Intro Deep Learning Neural Network on structured data like a csv.
11. Basics: Intro Deep Learning Unstructured data like an img. (But what is a neural network? | Chapter 1, Deep learning - 3Blue1Brown)
12. Basics: Intro Deep Learning Supervised Learning
13. Basics: GANs & DCGAN Paper Unsupervised Learning
14. Basics: GANs & DCGAN Paper Architecture guidelines for stable Deep Convolutional GANs: • Replace any pooling layers with strided convolutions (discriminator) and fractional-strided convolutions (generator). • Use batchnorm in both the generator and the discriminator. • Remove fully connected hidden layers for deeper architectures. • Use ReLU activation in generator for all layers except for the output, which uses Tanh. • Use LeakyReLU activation in the discriminator for all layers. .
15. Basics: Ensembles of GANs Ensemble learners - Udacity
16. Suggest three different training techniques: • Standard Ensemble of GANs (eGANs). • Self-ensemble of GANs (seGANs). • Cascade of GANs (cGANs). Basics: Ensembles of GANs
17. Standard Ensemble of GANs (eGANs) Basics: Ensembles of GANs
18. Self-ensemble of GANs (seGANs) Basics: Ensembles of GANs
19. Cascade of GANs (cGANs) Basics: Ensembles of GANs
20. Solution & Demo: Dataset exploration Go to https://github.com/p1nox/gan_ensembles/blob/master/data_exploration_viz.ipynb
21. Solution & Demo: GAN base architecture Go to https://github.com/p1nox/gan_ensembles/blob/master/dcgan_control_model.ipynb
22. Solution & Demo: Ensemble techniques implementation Go to https://github.com/p1nox/gan_ensembles/blob/master/data_exploration_viz.ipynb
23. Solution & Demo: Dataset exploration Go to https://github.com/p1nox/gan_ensembles/blob/master/data_exploration_viz.ipynb
24. Takeaways & beyond Stable Diffusion Midjourney v5 01 Brain Imaging Generation with Latent Diffusion Models 02
25. Resources • Ensemble of Generative Adversarial Networks as a Data Augmentation Technique for Alzheimer research https://github.com/p1nox/gan_ensembles/blob/master/capstone_project_docs/proposal.pdf • Hello Future (2022) Generative AI: a new approach to overcome data scarcity. https://hellofuture.orange.com/en/generative-ai-a-new-approach-to-overcome-data-scarcity/ • 3Blue1Brown: “But what is a neural network? | Chapter 1, Deep learning” - https://www.youtube.com/watch?v=aircAruvnKk • Ian Good fellow at Lex Fridman Podcast (2019) Ian Goodfellow: Generative Adversarial Networks (GANs) | Lex Fridman Podcast #19. https://www.youtube.com/watch?v=Z6rxFNMGdn0&t=3013s • Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter (2018) GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. https://arxiv.org/pdf/1706.08500.pdf • Kaggle (2019) Alzheimer's Dataset ( 4 class of Images) - Images of MRI Segementation. https://www.kaggle.com/datasets/tourist55/alzheimers-dataset-4-class-of-images • Kaggle (2020) I'm Something of a Painter Myself: Use GANs to create art - will you be the next Monet?. https://www.kaggle.com/competitions/gan-getting-started/overview/evaluation • Can Kocagil (2021) DCGAN paper implementation using PyTorch to generate faces. https://github.com/cankocagil/DCGAN • Steven Lang (2021) FID score for PyTorch. https://github.com/mseitzer/pytorch-fid • Udacity Ensembles learners https://www.youtube.com/watch?v=Un9zObFjBH0
26. “mri happy brain“ Grazie