English

Joint Shape Representation and Classification for Detecting PDAC

Computer Vision and Pattern Recognition 2019-08-22 v2

Abstract

We aim to detect pancreatic ductal adenocarcinoma (PDAC) in abdominal CT scans, which sheds light on early diagnosis of pancreatic cancer. This is a 3D volume classification task with little training data. We propose a two-stage framework, which first segments the pancreas into a binary mask, then compresses the mask into a shape vector and performs abnormality classification. Shape representation and classification are performed in a joint manner, both to exploit the knowledge that PDAC often changes the shape of the pancreas and to prevent over-fitting. Experiments are performed on 300 normal scans and 136 PDAC cases. We achieve a specificity of 90.2% (false alarm occurs on less than 1/10 normal cases) at a sensitivity of 80.2% (less than 1/5 PDAC cases are not detected), which show promise for clinical applications.

Keywords

Cite

@article{arxiv.1804.10684,
  title  = {Joint Shape Representation and Classification for Detecting PDAC},
  author = {Fengze Liu and Lingxi Xie and Yingda Xia and Elliot K. Fishman and Alan L. Yuille},
  journal= {arXiv preprint arXiv:1804.10684},
  year   = {2019}
}

Comments

Accepted to MICCAI 2019 Workshop(MLMI)(8 pages, 3 figures)

R2 v1 2026-06-23T01:38:38.508Z