Skip to main content
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
    Length: 00:04:53
20 Apr 2023

The common computational pathology tissue slides mainly include Fresh Frozen(FF) slides and Formalin-Fixed Paraffin-Embedded(FFPE) slides. The FF slide has low quality but is easy to prepare, while the FFPE one is the opposite, which is widely used in pathological slide preservation and high-precision diagnosis. Our goal is to generate FFPE images based on FF patches in order to quickly obtain high-quality slides in a short time and to provide doctors with convenient and accurate diagnostic evidence. We propose ST-MKSC, an FF2FFPE image translation network, which contains a Multi-frequency Domain Hierarchical Constraint(MDHC) network based on key consistent information constraints to keep the content information from the FF domain being preserved in the FFPE domain and Released Constraint loss(RC loss) to weaken the existing constraints, so as to reduce the impact of source domain (FF) style information on the appearance of the target domain (FFPE). We conduct FF2FFPE translation experiments on the TCGA-KIRC Dataset and our method is the best among the existing methods. Our model can effectively eliminate or weaken the cavity, artifacts, and other unreasonable structures in FF slides, and generate high-quality FFPE images.