🤖 AI Summary
This study addresses the loss of patient-specific accuracy in template-space segmentation of small subcortical nuclei—such as the subthalamic nucleus (STN), red nucleus (RN), and substantia nigra (SN)—which is critical for Parkinson’s disease surgical planning. The authors propose a native-space segmentation pipeline based on UNet, leveraging multi-center 7T and 3T MRI data to systematically evaluate, for the first time, the advantages of native-space over template-based approaches. To mitigate domain shift between field strengths, they employ disentangled representation learning to generate synthetic 3T images. Performance is assessed using Dice coefficient and Hausdorff Distance at 95% (HD95). Results demonstrate that the native-space method significantly outperforms template registration on 7T data (STN Dice: 0.775 vs. 0.713) with superior boundary precision; however, direct transfer of the 7T model to 3T leads to performance degradation, and synthetic data yields only marginal improvement.
📝 Abstract
Accurate segmentation of subcortical regions is critical for neurosurgical planning and functional research. Most automated methods rely on template space coregistration, which may compromise patient-specific accuracy, particularly in small structures. We identify a need to evaluate whether native space approaches offer a measurable advantage, which we evaluate in the context of movement disorders. We developed two UNet-based segmentation pipelines of the Subthalamic Nucleus (STN) - a common surgical target in Parkinson's Disease - and the neighbouring Red Nucleus (RN) and Substantia Nigra (SN). We collected 7T and 3T MRI data from five public datasets. The pipelines were evaluated in the native-space against manual labels. We further investigated the effect of the template resolution. Motivated by the hypothesis that models may better learn target boundaries in higher field, we tested the transferability of 7T-trained models to 3T clinical images, and whether synthetic 3T training data - generated via a disentangled representation learning method - could help bridging this domain gap. On held-out 7T data, the native pipeline consistently outperformed the template one. For the STN, native-space Dice reached 0.775 +- 0.055 versus 0.713 +- 0.051 (1 mm template), with HD95 of 0.79 +- 0.24 mm versus 1.17 +- 1.10 mm, respectively. Similar advantages were observed for the RN and SN. Increasing template resolution did not improve accuracy. When applied to 3T images, all models showed a considerable performance drop. Adding synthetic 3T data yielded only modest improvements, though without degrading 7T performance. Native-space segmentation is preferable for applications requiring patient specific anatomical fidelity, such as the surgical planning in PD. Bridging the 7T-to-3T domain gap remains an open challenge, motivating future work on domain adaptation tailored to subcortical structures.