STD-Net: a spatio-temporal decoupling network for multiphasic liver lesion segmentation and characterization

1

Hepatocellular carcinoma (HCC) is a leading cause of cancer-related mortality, necessitating accurate imaging for effective treatment.
2

The proposed STD-Net separates spatial feature extraction from temporal dynamics modeling, enhancing lesion characterization in multiphasic imaging.
3

A shared-weight 3D encoder captures robust anatomical representations, while a transformer-based module models sequential contrast patterns.
4

STD-Net outperforms state-of-the-art methods in segmentation and characterization, particularly for small or low-contrast liver lesions.
5

The spatio-temporal decoupling framework offers a versatile approach applicable to various dynamic medical imaging tasks.

Npj Digital Medicine

by Shaoliang Zhu, Mengjie Zou, Qijun Wu, Zheng Gong, Zhangnan Huang, Yan Zou, Tingting Tan, Yanwu You, Xiaofeng Dong, Honglin Luo
December 8, 2025

1