CQ-VAE: Coordinate Quantized VAE for Uncertainty Estimation with Application to Disk Shape Analysis from Lumbar Spine MRI Images
| Autor: | Weiyong Gu, Liang Liang, Jiasong Chen, Linchen Qian, Timur Urakov |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) Quantization (signal processing) 0206 medical engineering Computer Science - Computer Vision and Pattern Recognition Probabilistic logic Sampling (statistics) Pattern recognition 02 engineering and technology 010501 environmental sciences 020601 biomedical engineering 01 natural sciences Autoencoder Backpropagation Machine Learning (cs.LG) Generative model Linear regression Probability distribution Artificial intelligence business 0105 earth and related environmental sciences Shape analysis (digital geometry) |
| Zdroj: | ICMLA |
| DOI: | 10.1109/icmla51294.2020.00097 |
| Popis: | Ambiguity is inevitable in medical images, which often results in different image interpretations (e.g. object boundaries or segmentation maps) from different human experts. Thus, a model that learns the ambiguity and outputs a probability distribution of the target, would be valuable for medical applications to assess the uncertainty of diagnosis. In this paper, we propose a powerful generative model to learn a representation of ambiguity and to generate probabilistic outputs. Our model, named Coordinate Quantization Variational Autoencoder (CQ-VAE) employs a discrete latent space with an internal discrete probability distribution by quantizing the coordinates of a continuous latent space. As a result, the output distribution from CQ-VAE is discrete. During training, Gumbel-Softmax sampling is used to enable backpropagation through the discrete latent space. A matching algorithm is used to establish the correspondence between model-generated samples and "ground-truth" samples, which makes a trade-off between the ability to generate new samples and the ability to represent training samples. Besides these probabilistic components to generate possible outputs, our model has a deterministic path to output the best estimation. We demonstrated our method on a lumbar disk image dataset, and the results show that our CQ-VAE can learn lumbar disk shape variation and uncertainty. Comment: This paper is accepted by 19th IEEE International Conference on Machine Learning and Applications (ICMLA2020) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|