Tractogram foundation model

• URL: http://arxiv.org/abs/2606.09893v1
• Date: Wed, 03 Jun 2026 19:45:23 GMT
• Title: Tractogram foundation model
• Abstract summary: We introduce TractFM, a tractogram foundation model that learns reusable representations directly from whole-brain streamline sets.<n> TractFM combines a local streamline encoder with a permutation-equivariant tractogram encoder, allowing all streamlines from a subject to be contextualized jointly.<n>Its frozen representations achieve accurate tract parcellation and predict age and sex across independent datasets.
• Score: 46.43770468662999
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion MRI (dMRI) tractography is the only noninvasive approach for mapping white-matter pathways in the living human brain. It represents each brain as a tractogram: a large, unordered set of three-dimensional streamlines that includes information about both local streamline geometry and whole-brain anatomical organization. This structure makes tractograms a natural but challenging target for representation learning. Existing methods treat streamline classification and subject-level prediction as separate problems: streamline classifiers focus on geometric patterns, whereas subject-level prediction often depends on hand-crafted features. As a result, current methods do not learn reusable representations that connect streamline anatomy with whole-brain inter-subject variation. Here we introduce TractFM, a tractogram foundation model that learns reusable representations directly from whole-brain streamline sets. TractFM combines a local streamline encoder with a permutation-equivariant tractogram encoder, allowing all streamlines from a subject to be contextualized jointly in a single forward pass. Pretraining on dense anatomical tract parcellation, i.e., assigning anatomical labels to individual streamlines, yields two complementary representations: contextualized streamline-level embeddings for tract parcellation and compact subject-level descriptors for downstream prediction of subject phenotypes. Across three tractography algorithms and five dMRI datasets, TractFM transfers to both streamline-level and subject-level tasks. Its frozen representations achieve accurate tract parcellation and predict age and sex across independent datasets. These results show that whole-brain geometric context, learned once, can generalize across tractography pipelines, datasets, and prediction tasks.

Related papers

• TractGraphFormer: Anatomically Informed Hybrid Graph CNN-Transformer Network for Interpretable Sex and Age Prediction from Diffusion MRI Tractography [22.12146729607869]
  Local and global properties of brain white matter networks are often overlooked in convolutional network design.<n>We introduce TractGraphFormer, a hybrid Graph CNN-Transformer deep learning framework tailored for diffusion MRI tractography.
  arXiv  Detail & Related papers  (2024-07-11T22:14:57Z)
• Learning Multimodal Volumetric Features for Large-Scale Neuron Tracing [72.45257414889478]
  We aim to reduce human workload by predicting connectivity between over-segmented neuron pieces. We first construct a dataset, named FlyTracing, that contains millions of pairwise connections of segments expanding the whole fly brain. We propose a novel connectivity-aware contrastive learning method to generate dense volumetric EM image embedding.
  arXiv  Detail & Related papers  (2024-01-05T19:45:12Z)
• TractCloud: Registration-free tractography parcellation with a novel local-global streamline point cloud representation [63.842881844791094]
  Current tractography parcellation methods rely heavily on registration, but registration inaccuracies can affect parcellation. We propose TractCloud, a registration-free framework that performs whole-brain tractography parcellation directly in individual subject space.
  arXiv  Detail & Related papers  (2023-07-18T06:35:12Z)
• TractGraphCNN: anatomically informed graph CNN for classification using diffusion MRI tractography [21.929440352687458]
  We propose TractGraphCNN, a novel, anatomically informed graph CNN framework for machine learning tasks. Results in a sex prediction testbed task demonstrate strong performance of TractGraphCNN in two large datasets. This work shows the potential of incorporating anatomical information, especially known anatomical similarities between input features, to guide convolutions in neural networks.
  arXiv  Detail & Related papers  (2023-01-05T05:00:03Z)
• Superficial White Matter Analysis: An Efficient Point-cloud-based Deep Learning Framework with Supervised Contrastive Learning for Consistent Tractography Parcellation across Populations and dMRI Acquisitions [68.41088365582831]
  White matter parcellation classifies tractography streamlines into clusters or anatomically meaningful tracts. Most parcellation methods focus on the deep white matter (DWM), whereas fewer methods address the superficial white matter (SWM) due to its complexity. We propose a novel two-stage deep-learning-based framework, Superficial White Matter Analysis (SupWMA), that performs an efficient parcellation of 198 SWM clusters from whole-brain tractography.
  arXiv  Detail & Related papers  (2022-07-18T23:07:53Z)
• Two-Stream Graph Convolutional Network for Intra-oral Scanner Image Segmentation [133.02190910009384]
  We propose a two-stream graph convolutional network (i.e., TSGCN) to handle inter-view confusion between different raw attributes. Our TSGCN significantly outperforms state-of-the-art methods in 3D tooth (surface) segmentation.
  arXiv  Detail & Related papers  (2022-04-19T10:41:09Z)
• Semi-supervised, Topology-Aware Segmentation of Tubular Structures from Live Imaging 3D Microscopy [6.2651370198971295]
  This paper tackles two commonly encountered problems in biomedical imaging: Topological consistency of the segmentation, and limited annotations. We propose a topological score which measures both topological and geometric consistency between the predicted and ground truth segmentations. Our contributions are validated on a challenging segmentation task, locating tubular structures in the fetal pancreas from noisy live imaging confocal microscopy.
  arXiv  Detail & Related papers  (2021-05-20T13:35:44Z)
• Structured Landmark Detection via Topology-Adapting Deep Graph Learning [75.20602712947016]
  We present a new topology-adapting deep graph learning approach for accurate anatomical facial and medical landmark detection. The proposed method constructs graph signals leveraging both local image features and global shape features. Experiments are conducted on three public facial image datasets (WFLW, 300W, and COFW-68) as well as three real-world X-ray medical datasets (Cephalometric (public), Hand and Pelvis)
  arXiv  Detail & Related papers  (2020-04-17T11:55:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.