Fibre tract segmentation for intraoperative diffusion MRI in neurosurgical patients using tract-specific orientation atlas and tumour deformation modelling

Abstract

Purpose: Intraoperative diffusion MRI could provide a means of visualising brain fibre tracts near a neurosurgical target after preoperative images have been invalidated by brain shift. We propose an atlas-based intraoperative tract segmentation method, as the standard preoperative method, streamline tractography, is unsuitable for intraoperative implementation. Methods: A tract-specific voxel-wise fibre orientation atlas is constructed from healthy training data. After registration with a target image, a radial tumour deformation model is applied to the orientation atlas to account for displacement caused by lesions. The final tract map is obtained from the inner product of the atlas and target image fibre orientation data derived from intraoperative diffusion MRI. Results: The simple tumour model takes only seconds to effectively deform the atlas into alignment with the target image. With minimal processing time and operator effort, maps of surgically relevant tracts can be achieved that are visually and qualitatively comparable with results obtained from streamline tractography. Conclusion: Preliminary results demonstrate feasibility of intraoperative streamline-free tract segmentation in challenging neurosurgical cases. Demonstrated results in a small number of representative sample subjects are realistic despite the simplicity of the tumour deformation model employed. Following this proof of concept, future studies will focus on achieving robustness in a wide range of tumour types and clinical scenarios, as well as quantitative validation of segmentations.

Fibre orientation atlas guided rapid segmentation of white matter tracts

“…For the present analysis we included clinical scans with non‐deforming lesions, meaning the orientation atlas could be registered to the target image using only affine registration without the need for tumour deformation modelling. For qualitative results in clinical scans featuring deforming lesions, see Young et al ( 2022 ).…”

“…The ideal acquisition is at least 60 diffusion directions at $$$ b=1000 $$$, although fully acceptable results can be obtained with just 30 directions, as in the presented intraoperative data. The full breakdown of data quality and FOD modelling effects can be found in Young and Clayden (2022).…”

“…We have previously investigated the effect of reduced number of diffusion weighting directions and different fibre orientation distribution reconstruction approaches on segmentation stability for the segmentation methods analysed here (Young & Clayden, 2022). Segmentation results using tractfinder remained consistent within a subject even with decreasing data acquisition quality, from 120 directions and two (nonzero) b ‐value shells down to as few as 12 directions at $$$ b=1000 $$$.…”

“…Using these inputs, tractfinder is fully automated, although the user can specify a custom value for thresholding. An addition tumour deformation modelling step is also possible (not covered here; see Young et al, 2022 ), which requires a segmentation of a tumour in subject space.…”

“…Furthermore, the anatomical definitions of many tracts are not universally agreed upon, and new or understudied tracts can gain new neurosurgical importance, making it all the more important that methods can be retrained or generalised to new applications using a small number of samples. Preliminary results for this approach have been published in Young et al ( 2022 ), where we focused on qualitative results in the context of neurosurgical subjects with significantly deforming tumours. Here we provide a more detailed description of the technique and two additional tract atlases, as well as extensive quantitative validation of general applicability to both healthy and clinical datasets.…”