Many biological and medical tasks require the delineation of 3D curvilinear structures such as blood vessels and neurites from image volumes. This is typically done using neural networks trained by minimizing voxel-wise loss functions that do not capture the topological properties of these structures. As a result, the connectivity of the recovered structures is often wrong, which lessens their usefulness. In this paper, we propose to improve the 3D connectivity of our results by minimizing a sum of topology-aware losses on their 2D projections. This suffices to increase the accuracy and to reduce the annotation effort required to provide the required annotated training data. Code is available at https://github.com/doruk-oner/ConnectivityOnProjections.
翻译:许多生物和医疗任务要求从图象量中划定3D曲线结构,如血管和神经细胞,通常使用经培训的神经网络,尽量减少不捕捉这些结构的地形特性的恶性毒素损失功能,结果,回收的结构的连接往往错误,降低了其效用。在本文件中,我们提议通过将2D预测的地表意识损失总量减少到最低限度,改进我们结果的3D连接性。这足以提高准确性,减少提供所需附加说明的培训数据所需的说明性努力。代码可在https://github.com/doruk-oner/connectivityOnProjections上查阅。