Robust thalamic nuclei segmentation from T1-weighted MRI using polynomial intensity transformation

Abstract

Accurate segmentation of thalamic nuclei, crucial for understanding their role in healthy cognition and in pathologies, is challenging to achieve on standard T1-weighted (T1w) magnetic resonance imaging (MRI) due to poor image contrast. White-matter-nulled (WMn) MRI sequences improve intrathalamic contrast but are not part of clinical protocols or extant databases. In this study, we introduce histogram-based polynomial synthesis (HIPS), a fast preprocessing transform step that synthesizes WMn-like image contrast from standard T1w MRI using a polynomial approximation for intensity transformation. HIPS was incorporated into Thalamus Optimized Multi-Atlas Segmentation (THOMAS) pipeline, a method developed and optimized for WMn MRI. HIPS-THOMAS was compared to a convolutional neural network (CNN)-based segmentation method and THOMAS modified for T1w images (T1w-THOMAS). The robustness and accuracy of the three methods were tested across different image contrasts (MPRAGE, SPGR, and MP2RAGE), scanner manufacturers (PHILIPS, GE, and Siemens), and field strengths (3T and 7T). HIPS-transformed images improved intra-thalamic contrast and thalamic boundaries, and HIPS-THOMAS yielded significantly higher mean Dice coefficients and reduced volume errors compared to both the CNN method and T1w-THOMAS. Finally, all three methods were compared using the frequently travelling human phantom MRI dataset for inter- and intra-scanner variability, with HIPS displaying the least inter-scanner variability and performing comparably with T1w-THOMAS for intra-scanner variability. In conclusion, our findings highlight the efficacy and robustness of HIPS in enhancing thalamic nuclei segmentation from standard T1w MRI.

Prior‐guided individualized thalamic parcellation based on local diffusion characteristics

“…The GA‐reg method nonlinearly registered the MPM to native diffusion space and regarded it as the thalamic parcellation for a new subject. In addition to the clustering goodness, we ran THOMAS (Su et al, 2019 ; Vidal et al, 2024 ) on T1 data ( https://github.com/thalamicseg/hipsthomasdocker ) as the silver standard to compare PG‐par with IC‐par and GA‐reg. THOMAS is an automatic multi‐atlas segmentation method for thalamic parcellation and has already been validated against manual segmentation.…”

Normative modeling of thalamic nuclear volumes

“…To segment standard T1 MPRAGE data which is the structural MRI sequence used in most clinical protocols and in public databases, a variant was recently proposed that uses a Histogram-based polynomial synthesis (HIPS) to first generate WMn-like images from T1 prior to segmentation. This variant termed HIPS-THOMAS was shown to significantly improve accuracy characterized using Dice and volume similarity indices (Vidal et al 2024). Briefly, input T1 images are N4-bias corrected to remove shading artifacts and then automatically cropped to extract a 3D volume encompassing both thalami and then converted to WMn-like contrast using a polynomial transformation.…”

“…This is in part due to the lack of accurate methods of thalamic nuclei segmentation from structural MRI. Recently, several promising methods for thalamic nuclei segmentation from structural MRI at 3T have been proposed, such as Bayesian estimation from probabilistic atlases (Iglesias et al 2018), multi-atlas segmentation from specialized white-matter nulled image contrast (Su et al 2019) or adapted to standard T1 (Bernstein et al 2021; Vidal et al 2024). These methods have recently been used to delineate atrophy of specific thalamic nuclei in Frontotemporal dementia (Bocchetta et al 2020; McKenna et al 2023), Alzheimer’s disease (Low et al 2019; Bernstein et al 2021), and alcohol use disorder (Zahr et al 2020).…”