Semi-Supervised Biomedical Translation With Cycle Wasserstein Regression GANs

Abstract

The biomedical field offers many learning tasks that share unique challenges: large amounts of unpaired data, and a high cost to generate labels. In this work, we develop a method to address these issues with semi-supervised learning in regression tasks (e.g., translation from source to target). Our model uses adversarial signals to learn from unpaired datapoints, and imposes a cycle-loss reconstruction error penalty to regularize mappings in either direction against one another. We first evaluate our method on synthetic experiments, demonstrating two primary advantages of the system: 1) distribution matching via the adversarial loss and 2) regularization towards invertible mappings via the cycle loss. We then show a regularization effect and improved performance when paired data is supplemented by additional unpaired data on two real biomedical regression tasks: estimating the physiological effect of medical treatments, and extrapolating gene expression (transcriptomics) signals. Our proposed technique is a promising initial step towards more robust use of adversarial signals in semi-supervised regression, and could be useful for other tasks (e.g., causal inference or modality translation) in the biomedical field.

Flexible-Window Predictions on Electronic Health Records

“…Similar to our work, recently the generative capabilities of GANs have also been explored for semi-supervised learning. For instance, McDermott et al (2018) use adversarial loss and cyclical reconstruction loss to predict individualized treatment effects. Instead of cyclical reconstruction loss, we use the adversarial loss to distinguish between real and fake labels for labeled and unlabeled samples.…”

Synthetic Observational Health Data with GANs: from slow adoption to a boom in medical research and ultimately digital twins?

“…To solve similar problems in medical imaging, various GAN algorithms were developed for domain translation, mapping a sample from its to original class to the paired equivalent. This includes bidirectional transformations, allowing GAN to learn mappings from very few, or a lack of paired samples (Wolterink et al, 2017;Zhu et al, 2017a;McDermott et al, 2018).…”

“…ITEs refer to the response of a patient to a certain treatment given a set of characterizing features. The problem is that counterfactual outcomes are never observed or treatment selection is highly biased (Yoon et al, 2018a;McDermott et al, 2018;…”

“…The prediction performance of the model is compared against benchmarks of the same type on real data (Cui et al, 2019;Yoon et al, 2018a;Yu et al, 2019;Zhu et al, 2020a;Baowaly et al, 2019;Wang et al, 2019a;Walsh et al, 2020;Yoon et al, 2018b;McDermott et al, 2018;Yang et al, 2019c;Yoon et al, 2018c;Beaulieu-Jones et al, 2019;Bae et al, 2020a). Models trained to make forward predictions from past observations or from real data transformed with a known function can simply be evaluated for accuracy.…”

“…Similarly, domain translation and Semi-supervised learning (SSL) training approaches with GANs could support predictive tasks that lack data with accurate labels, lack paired samples or suffer class imbalance McDermott et al, 2018;Yoon et al, 2018a). Another example is correcting discrepancies between datasets collected in different locations or under different conditions inducing bias (Yoon et al, 2018c).…”