ORF-Net: Deep Omni-supervised Rib Fracture Detection from Chest CT Scans
This work addresses the challenge of reducing annotation burden for radiologists in medical imaging, though it is incremental as it builds on existing weakly- and semi-supervised methods by integrating them into a unified framework.
The paper tackles the labor-intensive annotation problem for rib fracture detection in chest CT scans by proposing ORF-Net, a deep omni-supervised object detection network that exploits multiple forms of annotated data, resulting in consistent outperformance over state-of-the-art approaches in experiments.
Most of the existing object detection works are based on the bounding box annotation: each object has a precise annotated box. However, for rib fractures, the bounding box annotation is very labor-intensive and time-consuming because radiologists need to investigate and annotate the rib fractures on a slice-by-slice basis. Although a few studies have proposed weakly-supervised methods or semi-supervised methods, they could not handle different forms of supervision simultaneously. In this paper, we proposed a novel omni-supervised object detection network, which can exploit multiple different forms of annotated data to further improve the detection performance. Specifically, the proposed network contains an omni-supervised detection head, in which each form of annotation data corresponds to a unique classification branch. Furthermore, we proposed a dynamic label assignment strategy for different annotated forms of data to facilitate better learning for each branch. Moreover, we also design a confidence-aware classification loss to emphasize the samples with high confidence and further improve the model's performance. Extensive experiments conducted on the testing dataset show our proposed method outperforms other state-of-the-art approaches consistently, demonstrating the efficacy of deep omni-supervised learning on improving rib fracture detection performance.