atTRACTive: Semi-automatic white matter tract segmentation using active learning

TL;DR

This paper introduces atTRACTive, a semi-automatic active learning method for white matter tract segmentation that performs well on tumor cases with minimal annotations, outperforming automatic methods like TractSeg.

Contribution

The paper presents a novel entropy-based active learning approach for tract segmentation, effective on pathological cases with limited manual annotations.

Findings

Segmentation on tumor cases achieved dice=0.71 with few annotations.

Automatic methods like TractSeg dropped to dice=0.34 on tumor data.

Manual experiments showed higher efficiency compared to traditional segmentation.

Abstract

Accurately identifying white matter tracts in medical images is essential for various applications, including surgery planning and tract-specific analysis. Supervised machine learning models have reached state-of-the-art solving this task automatically. However, these models are primarily trained on healthy subjects and struggle with strong anatomical aberrations, e.g. caused by brain tumors. This limitation makes them unsuitable for tasks such as preoperative planning, wherefore time-consuming and challenging manual delineation of the target tract is typically employed. We propose semi-automatic entropy-based active learning for quick and intuitive segmentation of white matter tracts from whole-brain tractography consisting of millions of streamlines. The method is evaluated on 21 openly available healthy subjects from the Human Connectome Project and an internal dataset of ten neurosurgical cases. With only a few annotations, the proposed approach enables segmenting tracts on tumor cases comparable to healthy subjects (dice=0.71), while the performance of automatic methods, like TractSeg dropped substantially (dice=0.34) in comparison to healthy subjects. The method is implemented as a prototype named atTRACTive in the freely available software MITK Diffusion. Manual experiments on tumor data showed higher efficiency due to lower segmentation times compared to traditional ROI-based segmentation.