Voxel Scene Graph for Intracranial Hemorrhage
This work addresses the challenge of patient-centered individualized treatment for ICH by providing a holistic representation of cerebral scenes, though it is incremental as it adapts existing SGG methods to a new domain.
The paper tackles the problem of modeling complex relations between intracranial hemorrhage (ICH) and adjacent brain structures in head CT scans, achieving up to 74% recall of clinically relevant relations by combining object detection with segmentation-grounded Scene Graph Generation (SGG) for 3D voxel images.
Patients with Intracranial Hemorrhage (ICH) face a potentially life-threatening condition, and patient-centered individualized treatment remains challenging due to possible clinical complications. Deep-Learning-based methods can efficiently analyze the routinely acquired head CTs to support the clinical decision-making. The majority of early work focuses on the detection and segmentation of ICH, but do not model the complex relations between ICH and adjacent brain structures. In this work, we design a tailored object detection method for ICH, which we unite with segmentation-grounded Scene Graph Generation (SGG) methods to learn a holistic representation of the clinical cerebral scene. To the best of our knowledge, this is the first application of SGG for 3D voxel images. We evaluate our method on two head-CT datasets and demonstrate that our model can recall up to 74% of clinically relevant relations. This work lays the foundation towards SGG for 3D voxel data. The generated Scene Graphs can already provide insights for the clinician, but are also valuable for all downstream tasks as a compact and interpretable representation.