CT Scans As Video: Efficient Intracranial Hemorrhage Detection Using Multi-Object Tracking

TL;DR

This paper introduces a lightweight video-based framework for intracranial hemorrhage detection in CT scans, achieving high accuracy and efficiency suitable for edge devices by reformulating volumetric data as video streams.

Contribution

It proposes a novel approach that combines 2D detection with 3D context using video reformulation, optimized YOLO models, and a hybrid tracking strategy for real-time intracranial hemorrhage detection.

Findings

Detection precision improved from 0.703 to 0.779

Maintains high sensitivity in resource-constrained environments

Provides a scalable, real-time solution for remote medical settings

Abstract

Automated analysis of volumetric medical imaging on edge devices is severely constrained by the high memory and computational demands of 3D Convolutional Neural Networks (CNNs). This paper develops a lightweight computer vision framework that reconciles the efficiency of 2D detection with the necessity of 3D context by reformulating volumetric Computer Tomography (CT) data as sequential video streams. This video-viewpoint paradigm is applied to the time-sensitive task of Intracranial Hemorrhage (ICH) detection using the Hemorica dataset. To ensure operational efficiency, we benchmarked multiple generations of the YOLO architecture (v8, v10, v11 and v12) in their Nano configurations, selecting the version with the highest mAP@50 to serve as the slice-level backbone. A ByteTrack algorithm is then introduced to enforce anatomical consistency across the $z$-axis. To address the initialization lag inherent in video trackers, a hybrid inference strategy and a spatiotemporal consistency filter are proposed to distinguish true pathology from transient prediction noise. Experimental results on independent test data demonstrate that the proposed framework serves as a rigorous temporal validator, increasing detection Precision from 0.703 to 0.779 compared to the baseline 2D detector, while maintaining high sensitivity. By approximating 3D contextual reasoning at a fraction of the computational cost, this method provides a scalable solution for real-time patient prioritization in resource-constrained environments, such as mobile stroke units and IoT-enabled remote clinics.