Accurate segmentation of thin, tubular structures (e.g., blood vessels) is challenging for deep neural networks. These networks classify individual pixels, and even minor misclassifications can break the thin connections within these structures. Existing methods for improving topology accuracy, such as topology loss functions, rely on very precise, topologically-accurate training labels, which are difficult to obtain. This is because annotating images, especially 3D images, is extremely laborious and time-consuming. Low image resolution and contrast further complicates the annotation by causing tubular structures to appear disconnected. We present CoLeTra, a data augmentation strategy that integrates to the models the prior knowledge that structures that appear broken are actually connected. This is achieved by creating images with the appearance of disconnected structures while maintaining the original labels. Our extensive experiments, involving different architectures, loss functions, and datasets, demonstrate that CoLeTra leads to segmentations topologically more accurate while often improving the Dice coefficient and Hausdorff distance. CoLeTra's hyper-parameters are intuitive to tune, and our sensitivity analysis shows that CoLeTra is robust to changes in these hyper-parameters. We also release a dataset specifically suited for image segmentation methods with a focus on topology accuracy. CoLetra's code can be found atthis https URL.
View on arXiv@article{valverde2025_2503.05541,
title={ Disconnect to Connect: A Data Augmentation Method for Improving Topology Accuracy in Image Segmentation },
author={ Juan Miguel Valverde and Maja Østergaard and Adrian Rodriguez-Palomo and Peter Alling Strange Vibe and Nina Kølln Wittig and Henrik Birkedal and Anders Bjorholm Dahl },
journal={arXiv preprint arXiv:2503.05541},
year={ 2025 }
}