Optical Coherence Tomography Harmonization with Anatomy-Guided Latent Metric Schrödinger Bridges

Junyu Chen (Southwest University of Finance and Economics) · Shuwen Wei (Johns Hopkins University) · Samuel Remedios (Johns Hopkins University) · Blake Dewey (Johns Hopkins University) · Zhangxing Bian (Johns Hopkins Univ) · Shimeng Wang (Johns Hopkins University) · Bruno Jedynak (Portland state university) · shiv saidha (Johns Hopkins University) · Peter Calabresi (Johns Hopkins University) · Aaron Carass (Johns Hopkins University) · Jerry L Prince (John Hopkins University)

anatomical information preservationanatomy consistencyinvertible networklatent euclidean metric spacelatent metric schrödinger bridgemedical image harmonizationoptical coherence tomography imagesoptimal transport problempaired imagespullback latent metricscanner hardware variationsschrödinger bridge frameworkstyle transfer performancetransport costunpaired harmonization

Medical image harmonization aims to reduce the differences in appearance caused by scanner hardware variations to allow for consistent and reliable comparisons across devices. Harmonization based on paired images from different devices has limited applicability in real-world clinical settings. On the other hand, unpaired harmonization typically does not guarantee anatomy consistency, which is problematic because anatomical information preservation is paramount. The Schrödinger bridge framework has achieved state-of-the-art style transfer performance with natural images by matching distributions of unpaired images, but this approach can also introduce anatomy changes when applied to medical images. We show that such changes occur because the Schrödinger bridge uses the square of the Euclidean distance between images as the transport cost in an entropy-regularized optimal transport problem. Such a transport cost is not appropriate for measuring anatomical distances, as medical images with the same anatomy need not have a small Euclidean distance between them. In this paper, we propose a latent metric Schrödinger bridge (LMSB) framework to improve the anatomical consistency for the harmonization of medical images. We develop an invertible network that maps medical images into a latent Euclidean metric space where the distances among images with the same anatomy are minimized using the pullback latent metric. Within this latent space, we train a Schrödinger bridge to match distributions. We show that the proposed LMSB is superior to the direct application of a Schrödinger bridge to harmonize optical coherence tomography (OCT) images.