---
title: "RF-DTR: A Multi-Stage DCT Token Regression Network for Progressive Rib Fracture Mask Refinement"
authors:
  - "ShouYu Chen"
  - "Liang Hu"
  - "JunTao Wang"
  - "Usman Naseem"
  - "Zhongyuan Lai"
  - "Qi Zhang"
doi: "10.24963/ijcai.2025/1017"
url: "https://ijcai.org/proceedings/2025/1017"
pdf: "https://ijcai.org/proceedings/2025/1017.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "9149-9157"
track: "AI4Tech: AI Enabling Technologies"
keywords:
  - "Domain-specific AI4Tech: AI4Care and AI4Health"
  - "Advanced AI4Tech: Data-driven AI4Tech"
---

# RF-DTR: A Multi-Stage DCT Token Regression Network for Progressive Rib Fracture Mask Refinement

ShouYu Chen, Liang Hu, JunTao Wang, Usman Naseem, Zhongyuan Lai, Qi Zhang

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 9149-9157. DOI: [10.24963/ijcai.2025/1017](https://doi.org/10.24963/ijcai.2025/1017)

## Abstract

Rib fracture patterns are key indicators of trauma severity. Detecting and locating these fractures is a critical yet time-consuming task, especially in 3D imaging, due to their minute size and irregular geometries. Existing voxel-based spatial methods fail to capture frequency-domain variations inherent in imaging and do not replicate the progressive refinement process used by clinicians during manual annotation, leading to suboptimal results. We propose a novel regression network, RF-DTR, incorporating a gated regressor mechanism and operating entirely in the frequency domain to address these challenges. Specifically, we present an innovative spatial-frequency transform applied to volumes and corresponding masks. Furthermore, we introduce a Mahalanobis regularization technique to enhance the model and learn high-frequency DCT components relevant to clinical tasks. Finally, a hierarchical penalty is proposed to improve the confidence of the prediction. Extensive experiments confirm our method's superiority in handling complex, sparsely annotated medical imaging datasets.