Quantitative Automated Segmentation of Lipiodol Deposits on Cone-Beam CT Imaging Acquired during Transarterial Chemoembolization for Liver Tumors: A Deep Learning Approach.

Journal: Journal of vascular and interventional radiology : JVIR
Published Date: Dec 16, 2021

Abstract

PURPOSE: To show that a deep learning (DL)-based, automated model for Lipiodol (Guerbet Pharmaceuticals, Paris, France) segmentation on cone-beam computed tomography (CT) after conventional transarterial chemoembolization performs closer to the "ground truth segmentation" than a conventional thresholding-based model.

Authors

  • Rohil Malpani
    Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, Connecticut.
  • Christopher W Petty
    Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, Connecticut.
  • Junlin Yang
    1Spine Center, Xinhua Hospital Affiliated to Shanghai Jiaotong University School of Medicine, Shanghai, China.
  • Neha Bhatt
    Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, Connecticut.
  • Tal Zeevi
    Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, Connecticut.
  • Vijay Chockalingam
    Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, Connecticut.
  • Rajiv Raju
    Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, Connecticut.
  • Alexandra Petukhova-Greenstein
    Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, Connecticut.
  • Jessica Gois Santana
    Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, Connecticut.
  • Todd R Schlachter
    Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, Connecticut.
  • David C Madoff
    Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, Connecticut.
  • Julius Chapiro
    Department of Radiology and Biomedical Imaging, Yale School of Medicine, 333 Cedar Street, New Haven, CT 06520. Electronic address: julius.chapiro@yale.edu.
  • James Duncan
    Department of Radiology and Biomedical Imaging, Yale University, New Haven, Connecticut, USA.
  • MingDe Lin
    Philips Research North America, Cambridge, Massachusetts.

Keywords

External Resources

Popular Topics
Recent Journals