BBox-Guided Segmentor: Leveraging expert knowledge for accurate stroke lesion segmentation using weakly supervised bounding box prior

Yanglan Ou, Sharon X. Huang, Kelvin K. Wong, Jonathon Cummock, John Volpi, James Z. Wang, Stephen T. Wong

Research output: Contribution to journalArticlepeer-review

6 Scopus citations

Abstract

Stroke is one of the leading causes of death and disability in the world. Despite intensive research on automatic stroke lesion segmentation from non-invasive imaging modalities including diffusion-weighted imaging (DWI), challenges remain such as a lack of sufficient labeled data for training deep learning models and failure in detecting small lesions. In this paper, we propose BBox-Guided Segmentor, a method that significantly improves the accuracy of stroke lesion segmentation by leveraging expert knowledge. Specifically, our model uses a very coarse bounding box label provided by the expert and then performs accurate segmentation automatically. The small overhead of having the expert provide a rough bounding box leads to large performance improvement in segmentation, which is paramount to accurate stroke diagnosis. To train our model, we employ a weakly-supervised approach that uses a large number of weakly-labeled images with only bounding boxes and a small number of fully labeled images. The scarce fully labeled images are used to train a generator segmentation network, while adversarial training is used to leverage the large number of weakly-labeled images to provide additional learning signals. We evaluate our method extensively using a unique clinical dataset of 99 fully labeled cases (i.e., with full segmentation map labels) and 831 weakly labeled cases (i.e., with only bounding box labels), and the results demonstrate the superior performance of our approach over state-of-the-art stroke lesion segmentation models. We also achieve competitive performance as a SOTA fully supervised method using less than one-tenth of the complete labels. Our proposed approach has the potential to improve stroke diagnosis and treatment planning, which may lead to better patient outcomes.

Original languageEnglish (US)
Article number102236
Pages (from-to)102236
JournalComputerized Medical Imaging and Graphics
Volume107
DOIs
StatePublished - Jul 2023

Keywords

  • Adversarial learning
  • Bounding box
  • Efficient annotation
  • Lesion segmentation
  • Stroke
  • Weakly supervised
  • Image Processing, Computer-Assisted
  • Humans
  • Diffusion Magnetic Resonance Imaging
  • Stroke/diagnostic imaging

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Health Informatics
  • Radiology Nuclear Medicine and imaging
  • Computer Vision and Pattern Recognition
  • Computer Graphics and Computer-Aided Design

Fingerprint

Dive into the research topics of 'BBox-Guided Segmentor: Leveraging expert knowledge for accurate stroke lesion segmentation using weakly supervised bounding box prior'. Together they form a unique fingerprint.

Cite this