Window Loss for Bone Fracture Detection and Localization in X-ray Images with Point-based Annotation

Authors

  • Xinyu Zhang PAII Inc., Bethesda, Maryland, USA
  • Yirui Wang PAII Inc., Bethesda, Maryland, USA
  • Chi-Tung Cheng Chang Gung Memorial Hospital, Linkou, Taiwan, ROC
  • Le Lu PAII Inc., Bethesda, Maryland, USA
  • Adam P. Harrison PAII Inc., Bethesda, Maryland, USA
  • Jing Xiao Ping An Technology, Shenzhen, China
  • Chien-Hung Liao Chang Gung Memorial Hospital, Linkou, Taiwan, ROC
  • Shun Miao PAII Inc., Bethesda, Maryland, USA

DOI:

https://doi.org/10.1609/aaai.v35i1.16153

Keywords:

Healthcare, Medicine & Wellness, Object Detection & Categorization, Applications

Abstract

Object detection methods are widely adopted for computer-aided diagnosis using medical images. Anomalous findings are usually treated as objects that are described by bounding boxes. Yet, many pathological findings, e.g., bone fractures, cannot be clearly defined by bounding boxes, owing to considerable instance, shape and boundary ambiguities. This makes bounding box annotations, and their associated losses, highly ill-suited. In this work, we propose a new bone fracture detection method for X-ray images, based on a labor effective and flexible annotation scheme suitable for abnormal findings with no clear object-level spatial extents or boundaries. Our method employs a simple, intuitive, and informative point-based annotation protocol to mark localized pathology information. To address the uncertainty in the fracture scales annotated via point(s), we convert the annotations into pixel-wise supervision that uses lower and upper bounds with positive, negative, and uncertain regions. A novel Window Loss is subsequently proposed to only penalize the predictions outside of the uncertain regions. Our method has been extensively evaluated on 4410 pelvic X-ray images of unique patients. Experiments demonstrate that our method outperforms previous state-of-the-art image classification and object detection baselines by healthy margins, with an AUROC of 0.983 and FROC score of 89.6%.

Downloads

Published

2021-05-18

How to Cite

Zhang, X., Wang, Y., Cheng, C.-T., Lu, L., Harrison, A. P., Xiao, J., Liao, C.-H., & Miao, S. (2021). Window Loss for Bone Fracture Detection and Localization in X-ray Images with Point-based Annotation. Proceedings of the AAAI Conference on Artificial Intelligence, 35(1), 724-732. https://doi.org/10.1609/aaai.v35i1.16153

Issue

Section

AAAI Technical Track on Application Domains