A critical assessment of LGN segmentation quality based on volume, contour, and location
- 1Maastricht University
Abstract
Reliable segmentation of the lateral geniculate nucleus (LGN), a small thalamic relay nucleus essential for visual processing, is necessary for characterizing its anatomy in healthy populations and structural alterations in neurological disorders. However, accurate delineation remains challenging on routinely acquired T1-weighted images because the LGN is small, deeply located, and has limited contrast relative to surrounding thalamic tissue. Although manual segmentation remains the reference standard, it is time consuming and susceptible to rater variability, limiting its use in large datasets. Automated approaches may therefore provide a more scalable alternative. In this study, we performed a systematic benchmarking of seven automated approaches: FreeSurfer, NextBrain, DeepThalamus, HIPS-THOMAS, MASSP 2.0, BigBrain alignment, and manual novice segmentation against expert-defined ground truth. We applied a multi-metric evaluation incorporating the Dice similarity coefficient, Hausdorff distance and balanced average Hausdorff distance, volumetric similarity, and Euclidean distance. Together, these measures evaluate overlap, contour, volume, and location against expert manual segmentations. Our results indicate that HIPS-THOMAS and DeepThalamus outperformed the other automated methods in all metrics. However, manual segmentation retained high precision despite exhibiting greater inter-subject variance than the top-performing automated segmentation tools. The different metrics do not necessarily report the same order of quality, highlighting the need of using multiple metrics for evaluation segmentation quality.
Related
- How Self-Location Predicts the Degree and Quality of the Felt Sense of Connection
- For-me-ness: a critical assessment of the phenomenal mineness thesis
- Empirical Assessment of Non-Invasive Population Genetics in Bats: Comparison of DNA Quality from Faecal and Tissue Samples
- Contribution of data acquired from spectroscopic, genomic and microbiological analyses to enhance mussels’ quality assessment
- Application of spectroscopic and multispectral imaging technologies on the assessment of ready-to-eat pineapple quality: A performance evaluation study of machine learning models generated from two commercial data analytics tools
BibTeX
@misc{schroeder2026critical,
title = {{A critical assessment of LGN segmentation quality based on volume, contour, and location}},
author = {J.-L. Schroeder and F. O. Gulban and C. Mueller-Axt and R. Goebel and J. W. Kurzawski},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.19.759668},
url = {https://www.biorxiv.org/content/10.64898/2026.10.19.759668v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - A critical assessment of LGN segmentation quality based on volume, contour, and location
AU - J.-L. Schroeder
AU - F. O. Gulban
AU - C. Mueller-Axt
AU - R. Goebel
AU - J. W. Kurzawski
PY - 2026
DA - 2026/10/19
PB - bioRxiv
DO - 10.64898/2026.10.19.759668
UR - https://www.biorxiv.org/content/10.64898/2026.10.19.759668v1
AB - Reliable segmentation of the lateral geniculate nucleus (LGN), a small thalamic relay nucleus essential for visual processing, is necessary for characterizing its anatomy in healthy populations and structural alterations in neurological disorders. However, accurate delineation remains challenging on routinely acquired T1-weighted images because the LGN is small, deeply located, and has limited contrast relative to surrounding thalamic tissue. Although manual segmentation remains the reference standard, it is time consuming and susceptible to rater variability, limiting its use in large datasets. Automated approaches may therefore provide a more scalable alternative. In this study, we performed a systematic benchmarking of seven automated approaches: FreeSurfer, NextBrain, DeepThalamus, HIPS-THOMAS, MASSP 2.0, BigBrain alignment, and manual novice segmentation against expert-defined ground truth. We applied a multi-metric evaluation incorporating the Dice similarity coefficient, Hausdorff distance and balanced average Hausdorff distance, volumetric similarity, and Euclidean distance. Together, these measures evaluate overlap, contour, volume, and location against expert manual segmentations. Our results indicate that HIPS-THOMAS and DeepThalamus outperformed the other automated methods in all metrics. However, manual segmentation retained high precision despite exhibiting greater inter-subject variance than the top-performing automated segmentation tools. The different metrics do not necessarily report the same order of quality, highlighting the need of using multiple metrics for evaluation segmentation quality.
ER -