DeepRecon: Joint 2D Cardiac Segmentation and 3D Volume Reconstruction via A Structure-Specific Generative Method
This work addresses the problem of building statistical cardiac anatomy models for medical imaging researchers and clinicians, but it appears incremental as it builds on existing latent-space methods for a specific domain.
The paper tackled the challenge of joint 2D cardiac segmentation and 3D volume reconstruction from low-resolution cine MR images by proposing DeepRecon, an end-to-end latent-space-based framework that generates accurate segmentation, synthetic high-resolution 3D images, and 3D reconstructed volumes, with experimental results showing effectiveness in 2D segmentation, 3D reconstruction, and 4D motion pattern adaptation.
Joint 2D cardiac segmentation and 3D volume reconstruction are fundamental to building statistical cardiac anatomy models and understanding functional mechanisms from motion patterns. However, due to the low through-plane resolution of cine MR and high inter-subject variance, accurately segmenting cardiac images and reconstructing the 3D volume are challenging. In this study, we propose an end-to-end latent-space-based framework, DeepRecon, that generates multiple clinically essential outcomes, including accurate image segmentation, synthetic high-resolution 3D image, and 3D reconstructed volume. Our method identifies the optimal latent representation of the cine image that contains accurate semantic information for cardiac structures. In particular, our model jointly generates synthetic images with accurate semantic information and segmentation of the cardiac structures using the optimal latent representation. We further explore downstream applications of 3D shape reconstruction and 4D motion pattern adaptation by the different latent-space manipulation strategies.The simultaneously generated high-resolution images present a high interpretable value to assess the cardiac shape and motion.Experimental results demonstrate the effectiveness of our approach on multiple fronts including 2D segmentation, 3D reconstruction, downstream 4D motion pattern adaption performance.