Erase to Enhance: Data-Efficient Machine Unlearning in MRI Reconstruction
This work addresses bias removal in medical imaging for compliance with privacy regulations, though it is incremental as it extends unlearning to a new domain.
The paper tackled the problem of applying machine unlearning to MRI reconstruction tasks to remove unwanted data, such as hallucinations, and found that unlearning is possible without full retraining while maintaining high performance with a subset of retain data.
Machine unlearning is a promising paradigm for removing unwanted data samples from a trained model, towards ensuring compliance with privacy regulations and limiting harmful biases. Although unlearning has been shown in, e.g., classification and recommendation systems, its potential in medical image-to-image translation, specifically in image recon-struction, has not been thoroughly investigated. This paper shows that machine unlearning is possible in MRI tasks and has the potential to benefit for bias removal. We set up a protocol to study how much shared knowledge exists between datasets of different organs, allowing us to effectively quantify the effect of unlearning. Our study reveals that combining training data can lead to hallucinations and reduced image quality in the reconstructed data. We use unlearning to remove hallucinations as a proxy exemplar of undesired data removal. Indeed, we show that machine unlearning is possible without full retraining. Furthermore, our observations indicate that maintaining high performance is feasible even when using only a subset of retain data. We have made our code publicly accessible.