Home | Publications | SDJ+25

Geometrically-Grounded Implicit Representations of 3D+time Cardiac Function From Magnetic Resonance Slices

MCML Authors

Nil Stolt-Ansó

→ Group Daniel Rückert
Artificial Intelligence in Healthcare and Medicine

Julian McGinnis

→ Group Benedikt Wiestler
AI for Image-Guided Diagnosis and Therapy

Daniel Rückert

Prof. Dr.

Director

Artificial Intelligence in Healthcare and Medicine

Abstract

Clinical acquisition in cardiac magnetic resonance (CMR) imaging involves obtaining cross-sectional planes of the heart along the radial and longitudinal directions. Despite these planes being 2D cross-sectional images of the heart, radiologists understand the 3D spatial and continuous temporal nature of the organ being imaged. The same can not be said about the conventional deep learning architectures used to process CMR images, which rely on in-plane and grid-based operations and are hence unable to integrate all imaging planes. In this paper, we build upon previous work on neural implicit segmentation functions (NISF) to overcome unaddressed challenges in cardiac function modeling in the CMR domain. For a given subject, our architecture builds a shared 3D+time representations from all available acquisition planes regardless of orientation. By design, predictions along any imaging plane orientation are cross-sections of the overall 3D representation, leading to spatio-temporal consistency across all slices. Moreover, our architecture makes the rotation and translation parameters of imaging planes learnable, allowing us to correct for the commonplace respiratory and patient motion between slice acquisitions under a rigid assumption. Furthermore, interpolation of intensities and segmentation can be performed in 4D at any desired resolution. We perform our study on a 120 subject sub-cohort of CMR imaging data from the UK-Biobank. We show our in-plane segmentation performance to be on-par with existing CMR segmentation methods and explore how the majority of failure cases arise from limitations in the ground-truth segmentation, for which our representations make predictions with better anatomical accuracy than its original training data. We also evaluate our motion-correction capabilities, displaying quantitative and qualitative improvements in slice alignment. Our qualitative results explore how our representations can be derived irrespective of missing acquisition planes and opens up avenues towards modeling complex sub-structures such as papillary muscles.

misc SDJ+25