Fully Automated Segmentation of Fiber Bundles in Anatomic Tracing Data

2025-08-18

AI Summary

Manual annotation of sparse fiber bundles in macaque tissue sections is time-consuming and labor-intensive, while existing automated methods suffer from high false-negative rates, reliance on post-processing across serial sections, and poor generalizability. This paper proposes a fully automatic, single-section fiber bundle segmentation framework built upon a U-Net architecture enhanced with a large-receptive-field design, foreground-aware sampling, and semi-supervised pretraining—collectively improving detection sensitivity for sparse structures and suppressing background false positives. Crucially, the method operates independently per section without requiring inter-slice correspondence, enabling efficient, standalone analysis. Evaluated on real macaque anatomical tracer data, it achieves over a 20% improvement in sparse fiber bundle detection rate and a 40% reduction in false discovery rate. Moreover, it consistently generates high-quality pseudo-labels, substantially supporting validation and optimization of dMRI tractography modeling.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Semi-Supervised Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Anatomic tracer studies are critical for validating and improving diffusion MRI (dMRI) tractography. However, large-scale analysis of data from such studies is hampered by the labor-intensive process of annotating fiber bundles manually on histological slides. Existing automated methods often miss sparse bundles or require complex post-processing across consecutive sections, limiting their flexibility and generalizability. We present a streamlined, fully automated framework for fiber bundle segmentation in macaque tracer data, based on a U-Net architecture with large patch sizes, foreground aware sampling, and semisupervised pre-training. Our approach eliminates common errors such as mislabeling terminals as bundles, improves detection of sparse bundles by over 20% and reduces the False Discovery Rate (FDR) by 40% compared to the state-of-the-art, all while enabling analysis of standalone slices. This new framework will facilitate the automated analysis of anatomic tracing data at a large scale, generating more ground-truth data that can be used to validate and optimize dMRI tractography methods.

Problem

• Automating labor-intensive manual fiber bundle annotation
• Improving detection of sparse fiber bundles
• Reducing false discovery rates in segmentation

Innovation

• U-Net architecture with large patch sizes
• Foreground aware sampling technique
• Semisupervised pre-training for accuracy