SCOPE: Structural Continuity Preservation for Medical Image Segmentation
This addresses the issue of inaccurate medical diagnoses due to discontinuous segmentations in medical imaging, though it is incremental as it builds on existing graph-based methods for a specific domain.
The paper tackled the problem of preserving anatomical continuity in medical image segmentation, which is often neglected by deep learning methods, by proposing a graph-based approach that enforces shape continuity as a constraint. The result showed significant improvements in connectivity metrics on retinal vessel segmentation benchmarks, with better or on-par performance on segmentation metrics.
Although the preservation of shape continuity and physiological anatomy is a natural assumption in the segmentation of medical images, it is often neglected by deep learning methods that mostly aim for the statistical modeling of input data as pixels rather than interconnected structures. In biological structures, however, organs are not separate entities; for example, in reality, a severed vessel is an indication of an underlying problem, but traditional segmentation models are not designed to strictly enforce the continuity of anatomy, potentially leading to inaccurate medical diagnoses. To address this issue, we propose a graph-based approach that enforces the continuity and connectivity of anatomical topology in medical images. Our method encodes the continuity of shapes as a graph constraint, ensuring that the network's predictions maintain this continuity. We evaluate our method on two public benchmarks on retinal vessel segmentation, showing significant improvements in connectivity metrics compared to traditional methods while getting better or on-par performance on segmentation metrics.