CHeart: A Conditional Spatio-Temporal Generative Model for Cardiac Anatomy

TY - JOUR

T1 - CHeart

T2 - A Conditional Spatio-Temporal Generative Model for Cardiac Anatomy

AU - Qiao, Mengyun

AU - Wang, Shuo

AU - Qiu, Huaqi

AU - De Marvao, Antonio

AU - O'Regan, Declan P

AU - Rueckert, Daniel

AU - Bai, Wenjia

N1 - Publisher Copyright: IEEE

PY - 2023/11/10

Y1 - 2023/11/10

N2 - Two key questions in cardiac image analysis are to assess the anatomy and motion of the heart from images; and to understand how they are associated with non-imaging clinical factors such as gender, age and diseases. While the first question can often be addressed by image segmentation and motion tracking algorithms, our capability to model and answer the second question is still limited. In this work, we propose a novel conditional generative model to describe the 4D spatio-temporal anatomy of the heart and its interaction with non-imaging clinical factors. The clinical factors are integrated as the conditions of the generative modelling, which allows us to investigate how these factors influence the cardiac anatomy. We evaluate the model performance in mainly two tasks, anatomical sequence completion and sequence generation. The model achieves high performance in anatomical sequence completion, comparable to or outperforming other state-of-the-art generative models. In terms of sequence generation, given clinical conditions, the model can generate realistic synthetic 4D sequential anatomies that share similar distributions with the real data. We will share the code and the trained generative model at https://github.com/MengyunQ/CHeart.

AB - Two key questions in cardiac image analysis are to assess the anatomy and motion of the heart from images; and to understand how they are associated with non-imaging clinical factors such as gender, age and diseases. While the first question can often be addressed by image segmentation and motion tracking algorithms, our capability to model and answer the second question is still limited. In this work, we propose a novel conditional generative model to describe the 4D spatio-temporal anatomy of the heart and its interaction with non-imaging clinical factors. The clinical factors are integrated as the conditions of the generative modelling, which allows us to investigate how these factors influence the cardiac anatomy. We evaluate the model performance in mainly two tasks, anatomical sequence completion and sequence generation. The model achieves high performance in anatomical sequence completion, comparable to or outperforming other state-of-the-art generative models. In terms of sequence generation, given clinical conditions, the model can generate realistic synthetic 4D sequential anatomies that share similar distributions with the real data. We will share the code and the trained generative model at https://github.com/MengyunQ/CHeart.

UR - https://www.scopus.com/pages/publications/85177091932

U2 - 10.1109/TMI.2023.3331982

DO - 10.1109/TMI.2023.3331982

M3 - Article

C2 - 37948142

SN - 0278-0062

VL - PP

SP - 1

JO - IEEE transactions on medical imaging

JF - IEEE transactions on medical imaging

ER -