Voxel level dense prediction of acute stroke territory in DWI using deep learning segmentation models and image enhancement strategies.

Journal: Japanese journal of radiology
PMID: 38727961

Abstract

PURPOSE: To build a stroke territory classifier model in DWI by designing the problem as a multiclass segmentation task by defining each stroke territory as distinct segmentation targets and leveraging the guidance of voxel wise dense predictions.

Authors

  • İlker Özgür Koska
    Department of Radiology, Behçet Uz Children's Hospital, İzmir, Turkey.
  • M Alper Selver
    Department of Electrical and Electronics Engineering, Dokuz Eylül University, İzmir, Turkey.
  • Fazil Gelal
    Department of Radiology, Izmir Katip Celebi University Ataturk Training and Research Hospital, Basin Sitesi, Izmir, 35360, Turkey.
  • Muhsin Engin Uluc
    Izmir Katip Celebi University Ataturk Training and Research Hospital, Department of Radiology, 35150 Izmir, Turkey.
  • Yusuf Kenan Cetinoglu
    Batman Training and Research Hospital, Department of Radiology, 72070 Batman, Turkey. Electronic address: kenancetinoglu@hotmail.com.
  • Nursel Yurttutan
    Department of Radiology, Kahramanmaraş Sütçü İmam University Hospital, Kahramanmaraş, Turkey.
  • Mehmet Serindere
    Department of Radiology, Hatay Training and Research Hospital, Güzelburç/Hatay, Turkey.
  • Oğuz Dicle
    Department of Radiology, Dokuz Eylül University School of Medicine, İzmir, Turkey.

Keywords

External Resources

Popular Topics
Recent Journals