Bones Can't Be Triangles: Accurate and Efficient Vertebrae Keypoint Estimation through Collaborative Error Revision
This work addresses vertebrae keypoint estimation for medical imaging, offering an incremental improvement by automating error correction to reduce user intervention.
The paper tackles the problem of inaccurate vertebrae keypoint estimation by introducing KeyBot, a method that identifies and corrects typical errors in existing models, reducing user workload and achieving state-of-the-art performance on three public datasets.
Recent advances in interactive keypoint estimation methods have enhanced accuracy while minimizing user intervention. However, these methods require user input for error correction, which can be costly in vertebrae keypoint estimation where inaccurate keypoints are densely clustered or overlap. We introduce a novel approach, KeyBot, specifically designed to identify and correct significant and typical errors in existing models, akin to user revision. By characterizing typical error types and using simulated errors for training, KeyBot effectively corrects these errors and significantly reduces user workload. Comprehensive quantitative and qualitative evaluations on three public datasets confirm that KeyBot significantly outperforms existing methods, achieving state-of-the-art performance in interactive vertebrae keypoint estimation. The source code and demo video are available at: https://ts-kim.github.io/KeyBot/