TractCloud-FOV: Deep Learning-based Robust Tractography Parcellation in Diffusion MRI with Incomplete Field of View

2025-02-28

AI Summary

Clinical diffusion MRI often suffers from incomplete field-of-view (FOV), leading to truncation of cerebral white matter tracts and severely compromising tract segmentation and anatomical interpretation. To address this, we propose the first end-to-end, streamline-level tract classification framework explicitly designed for incomplete-FOV data. Our key contributions are: (1) FOV-Cut—a novel data augmentation strategy that realistically simulates diverse inferior FOV truncation patterns, substantially improving model generalizability; and (2) a deep neural network architecture integrating geometric-topological feature encoding with multi-scale contextual modeling. Evaluated on synthetic data and two real-world incomplete-FOV datasets, our method outperforms existing state-of-the-art approaches in classification accuracy, anatomical consistency, cross-dataset generalizability, and inference efficiency.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-instance/Multi-view Learning
• Data Mining & Knowledge Management: Data Stream Mining

Application Category

• Security and Privacy: Data transparency and provenance
• Web Mining and Content Analysis: Content-based information diffusion
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications

Abstract

Tractography parcellation classifies streamlines reconstructed from diffusion MRI into anatomically defined fiber tracts for clinical and research applications. However, clinical scans often have incomplete fields of view (FOV) where brain regions are partially imaged, leading to partial or truncated fiber tracts. To address this challenge, we introduce TractCloud-FOV, a deep learning framework that robustly parcellates tractography under conditions of incomplete FOV. We propose a novel training strategy, FOV-Cut Augmentation (FOV-CA), in which we synthetically cut tractograms to simulate a spectrum of real-world inferior FOV cutoff scenarios. This data augmentation approach enriches the training set with realistic truncated streamlines, enabling the model to achieve superior generalization. We evaluate the proposed TractCloud-FOV on both synthetically cut tractography and two real-life datasets with incomplete FOV. TractCloud-FOV significantly outperforms several state-of-the-art methods on all testing datasets in terms of streamline classification accuracy, generalization ability, tract anatomical depiction, and computational efficiency. Overall, TractCloud-FOV achieves efficient and consistent tractography parcellation in diffusion MRI with incomplete FOV.

Problem

• Classifies streamlines in incomplete FOV diffusion MRI
• Addresses partial fiber tracts due to incomplete imaging
• Enhances generalization with FOV-Cut Augmentation training

Innovation

• Deep learning for tractography parcellation
• FOV-Cut Augmentation for training
• Superior generalization with incomplete FOV