Voxel Scene Graph for Intracranial Hemorrhage

TL;DR

This paper introduces a novel 3D voxel scene graph generation method for intracranial hemorrhage analysis in head CTs, enabling holistic and interpretable representations to aid clinical decision-making.

Contribution

It pioneers the application of scene graph generation to 3D voxel images and combines detection and segmentation for comprehensive cerebral scene modeling.

Findings

Recalls up to 74% of clinically relevant relations

First application of SGG for 3D voxel data

Provides interpretable scene graphs for clinical insights

Abstract

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.