# Automatic Landmark-Based Segmentation of Human Subcortical Structures in MRI

arXiv: https://arxiv.org/abs/2605.14221 · HTML: https://mlsanity.com/paper/2605.14221/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 16 references that are in the map.
- First posted on arXiv 14 May 2026.

## Builds on (most cited first, 7 of 7)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [SynthStrip: Skull-Stripping for Any Brain Image](https://mlsanity.com/paper/2203.09974/) (2022)
- [Multi-Atlas Segmentation of Biomedical Images: A Survey](https://mlsanity.com/paper/1412.3421/) (2014)
- [Deep Learning-Based Regression and Classification for Automatic Landmark Localization in Medical Images](https://mlsanity.com/paper/2007.05295/) (2020)
- [Fast Multiple Landmark Localisation Using a Patch-based Iterative Network](https://mlsanity.com/paper/1806.06987/) (2018)
- [Segmentation of MRI head anatomy using deep volumetric networks and multiple spatial priors](https://mlsanity.com/paper/1905.10010/) (2019)

## Abstract (arXiv)

Precise segmentation of brain structures in magnetic resonance imaging (MRI) is essential for reliable neuroimaging analysis, yet voxel-wise deep models often yield anatomically inconsistent results that diverge from expert-defined boundaries. In this research, we propose a landmark-guided 3D brain segmentation approach that explicitly mimics the manual segmentation protocol of the Harvard--Oxford Atlas. A Global-to-Local network automatically detects 16 landmarks representing key subcortical reference points. Then, a semantic segmentation model produces a coarse segmentation of 12 anatomical labels, each grouping multiple subcortical regions. Finally, a landmark-driven post-processing step separates these 12 labels into 26 distinct structures by enforcing local anatomical constraints. Experimental results demonstrate consistent improvements in boundary accuracy. Overall, integrating learned landmarks aligns segmentations more closely with manual protocols.