Multi-dimensional Gated Recurrent Units for Automated Anatomical Landmark Localization
This addresses the problem of precise anatomical landmark localization in medical imaging for clinicians, but it is incremental as it builds on existing techniques with specific improvements.
The paper tackles automated localization of anatomical landmarks in 3D medical images by combining two recurrent neural networks in a coarse-to-fine approach, achieving a mean localization error of 1.7 mm, which matches expert performance.
We present an automated method for localizing an anatomical landmark in three-dimensional medical images. The method combines two recurrent neural networks in a coarse-to-fine approach: The first network determines a candidate neighborhood by analyzing the complete given image volume. The second network localizes the actual landmark precisely and accurately in the candidate neighborhood. Both networks take advantage of multi-dimensional gated recurrent units in their main layers, which allow for high model complexity with a comparatively small set of parameters. We localize the medullopontine sulcus in 3D magnetic resonance images of the head and neck. We show that the proposed approach outperforms similar localization techniques both in terms of mean distance in millimeters and voxels w.r.t. manual labelings of the data. With a mean localization error of 1.7 mm, the proposed approach performs on par with neurological experts, as we demonstrate in an interrater comparison.