Abstract
Immunohistochemistry detection technology is able to detect more difficult tumors than regular pathology detection technology only with hematoxylin-eosin stained pathology microscopy images, – for example, neuroendocrine tumor detection. However, making immunohistochemistry pathology microscopy images costs much time and money. In this paper, we propose an effective immunohistochemistry pathology microscopic image-generation method that can generate synthetic immunohistochemistry pathology microscopic images from hematoxylin-eosin stained pathology microscopy images without any annotation. CycleGAN is adopted as the basic architecture for the unpaired and unannotated dataset. Moreover, multiple instances learning algorithms and the idea behind conditional GAN are considered to improve performance. To our knowledge, this is the first attempt to generate immunohistochemistry pathology microscopic images, and our method can achieve good performance, which will be very useful for pathologists and patients when applied in clinical practice.
Highlights
Immunohistochemistry (IHC) detection technology, such as staining with Ki-67 reagent, plays an important role in tumor detection
The generator in raw CycleGAN has been replaced by a more complicated generator because we found that in raw CycleGAN, the discriminator would learn much faster than the generator when training with our data, so the generator could not learn anything and fails to generate synthetic Ki-67 pathology microscopy images of high quality
The HE pathology microscopy image and its corresponding Ki-67 pathology microscopy image appear similar at image level
Summary
Immunohistochemistry (IHC) detection technology, such as staining with Ki-67 reagent, plays an important role in tumor detection. By introducing cycle loss functions during the adversarial training process, the generator finds an accurate mapping between two different domains with unpaired datasets. In this view, CycleGAN is the proper way for unpaired pathology microscopy image datasets. With incomplete or lacking annotations of pathology microscopy images, semi-supervised learning-based methods, unsupervised learning-based methods and self-supervised learning-based methods have been introduced to work on datasets with partial annotations or without any annotation and these methods have proven to be useful (Campanella et al, 2019; Xu G. et al, 2019) Among these methods, multiple instances learning (MIL) algorithms have been applied successfully with unannotated pathology microscopy images, so they have been adopted in this paper (Xu G. et al, 2019).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
