LiNUS: Lightweight Automatic Segmentation of Deep Brain Nuclei for Real-Time DBS Surgery

TL;DR

LiNUS is a lightweight deep learning model that accurately and rapidly segments deep brain nuclei, specifically the Subthalamic Nucleus, to assist real-time DBS surgery with high robustness and efficiency.

Contribution

The paper introduces LiNUS, a novel lightweight segmentation framework with spectral normalization and multi-scale features, optimized for real-time deep brain structure segmentation in clinical settings.

Findings

Achieves a Dice score of 0.679 on Tsinghua DBS dataset.

Inference time of only 0.05 seconds per subject.

Robust performance with a Dice score of 0.89 on high-resolution data.

Abstract

This paper proposes LiNUS, a lightweight deep learning framework for the automatic segmentation of the Subthalamic Nucleus (STN) in Deep Brain Stimulation (DBS) surgery. Addressing the challenges of small target volume and class imbalance in MRI data, LiNUS improves upon the U-Net architecture by introducing spectral normalization constraints, bilinear interpolation upsampling, and a multi-scale feature fusion mechanism. Experimental results on the Tsinghua DBS dataset (TT14) demonstrate that LiNUS achieves a Dice coefficient of 0.679 with an inference time of only 0.05 seconds per subject, significantly outperforming traditional manual and registration-based methods. Further validation on high-resolution data confirms the model's robustness, achieving a Dice score of 0.89. A dedicated Graphical User Interface (GUI) was also developed to facilitate real-time clinical application.