Echo-ODE: A Dynamics Modeling Network with Neural ODE for Temporally Consistent Segmentation of Video Echocardiograms

Wenliang Lu¹Yuan Wang²Wenli Dai¹Yingnan Wu³Hao Xu^4,5*Dexing Kong^1*

• ¹Zhejiang University, Hangzhou, China
• ²School of Science, Zhejiang Sci-Tech University, Hangzhou, China
• ³Zhejiang Provincial People's Hospital, Hangzhou, China
• ⁴Zhejiang Normal University, Jinhua, China
• ⁵Puyang Institute of Big Data and Artificial Intelligence, Puyang, China

Segmentation of echocardiograms plays a crucial role in clinical diagnosis. Beyond accuracy, a major challenge of video echocardiogram analysis is the temporal consistency of consecutive frames. Stable and consistent segmentation of cardiac structures is essential for a reliable fully automatic echocardiogram interpretation. To address this issue, we propose a novel framework Echo-ODE, where the heart is regarded as a dynamical system, and we model the representation of dynamics by neural ordinary differential equations. Echo-ODE learns the spatio-temporal relationships of the input video and output continuous and consistent predictions. Experiments conducted on the Echo-Dynamic, the CAMUS and our private dataset demonstrate that Echo-ODE achieves comparable accuracy but significantly better temporal stability and consistency in video segmentation than previous mainstream CNN models. More accurate phase detection also underscores the superiority of our proposed model. Furthermore, Echo-ODE serves as a versatile backbone, not limited to segmentation tasks, and shows great potential to enable reliable, fully automated video echocardiogram interpretation. The code is publicly available at https : //github.com/luwenlianglu/EchoODE.