Detection of Intracranial Hemorrhage for Trauma Patients

TL;DR

This paper introduces a deep learning method with a novel loss function for detecting intracranial hemorrhages in 3D CT scans, improving accuracy and efficiency in trauma diagnosis.

Contribution

It proposes a Voxel-Complete IoU loss for better 3D bounding box detection and evaluates annotation costs and data quality impacts in clinical settings.

Findings

Achieved 0.877 AR30 and 0.728 AP30 on public dataset.

Achieved 0.653 AR30 and 0.514 AP30 on private cohort.

+5% improvement in Average Recall over other loss functions.

Abstract

Whole-body CT is used for multi-trauma patients in the search of any and all injuries. Since an initial assessment needs to be rapid and the search for lesions is done for the whole body, very little time can be allocated for the inspection of a specific anatomy. In particular, intracranial hemorrhages are still missed, especially by clinical students. In this work, we present a Deep Learning approach for highlighting such lesions to improve the diagnostic accuracy. While most works on intracranial hemorrhages perform segmentation, detection only requires bounding boxes for the localization of the bleeding. In this paper, we propose a novel Voxel-Complete IoU (VC-IoU) loss that encourages the network to learn the 3D aspect ratios of bounding boxes and leads to more precise detections. We extensively experiment on brain bleeding detection using a publicly available dataset, and validate it on a private cohort, where we achieve 0.877 AR30, 0.728 AP30, and 0.653 AR30, 0.514 AP30 respectively. These results constitute a relative +5% improvement in Average Recall for both datasets compared to other loss functions. Finally, as there is little data currently publicly available for 3D object detection and as annotation resources are limited in the clinical setting, we evaluate the cost of different annotation methods, as well as the impact of imprecise bounding boxes in the training data on the detection performance.