Acquiring a Low-Dimensional, Environment-Independent Representation of Brain MR Images for Content-Based Image Retrieval.

To make content-based image retrieval (CBIR) technology for magnetic resonance (MR) images of the brain practical and useful for diagnosis and research, it is important to obtain low-dimensional representations that embody pathological attributes. However, recent evidence suggests that variations in domains resulting from differences in imaging equipment and protocols at each imaging facility can overshadow pathological attributes. In this study, we propose a novel approach known as multidecoder adversarial domain adaptation (MD-ADA) to obtain low-dimensional representations of brain MR images that preserve pathological features while mitigating domain differences. This method combines adversarial domain adaptation techniques with convolutional autoencoders that have distinct decoders for each domain and employs adversarial learning to prevent domain discrimination from the produced low-dimensional representations. Experimental evaluations on two datasets, ADNI and PPMI, comprising 4,168 brain images demonstrate that the proposed MD-ADA significantly reduces domain differences between datasets without compromising the recoverability of brain images or the accuracy of disease classification.